{"schema_version":"onlylabs.public_analysis_evidence.v1","title":"OpenBMB (MiniCPM) analysis evidence pack","description":"Public onlylabs evidence pack for cited agent analysis: captured pages, ranked public signals, and stored web-search provenance used by the background analysis workflow.","url":"https://onlylabs.fyi/labs/openbmb","json_url":"https://onlylabs.fyi/analysis/openbmb/evidence.json","generated_at":"2026-06-11T18:06:29.237Z","org":{"slug":"openbmb","name":"OpenBMB (MiniCPM)","category":"neolab","category_label":"Neolab","dossier_url":"https://onlylabs.fyi/labs/openbmb"},"analysis":null,"workflow":{"version":"onlylabs-deepagents-analysis-v3","provider":null,"model":null,"agent":null,"public_pack_mode":"local-pages-and-events","live_web_fetches":false,"note":"Public evidence exports do not trigger live Exa calls; stored Exa provenance is included when analysis metadata contains it."},"stats":{"pages":28,"events":140,"web":0,"evidence":88,"signal_desks":{"hiring":0,"forks":2,"releases":42,"talking":1,"repos":15},"data_radar_lanes":null,"data_radar_matches":null,"stored_analysis_evidence":null,"stored_analysis_web":null,"stored_analysis_signal_desks":null,"stored_analysis_data_radar_lanes":null,"stored_analysis_data_radar_matches":null},"stored_web_provenance":null,"evidence":[{"ref":"P1","kind":"page","title":"openbmb/AgentCPM-Report model card","date":"2026-06-11T02:49:46.408343+00:00","date_source":null,"source_url":"https://huggingface.co/openbmb/AgentCPM-Report/raw/main/README.md","signal_url":null,"signal_json_url":null,"text":"---\nlicense: apache-2.0\nlibrary_name: transformers\npipeline_tag: text-generation\ntags:\n- agent\n- text-generation-inference\n---\n\n# AgentCPM-Report: Gemini-2.5-pro-DeepResearch Level Local DeepResearch\n\n<p align=\"center\">\n<a href='https://huggingface.co/openbmb/AgentCPM-Report'><img src='https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-AgentCPM--Report-yellow'>\n<a href='https://huggingface.co/openbmb/AgentCPM-Report-GGUF'><img src='https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-AgentCPM--Report--GGUF-yellow'>\n<a href='https://github.com/OpenBMB/AgentCPM'><img src='https://img.shields.io/badge/GitHub-AgentCPM-blue?logo=github'>\n<a href='https://github.com/OpenBMB/UltraRAG'><img src='https://img.shields.io/badge/GitHub-UltraRAG-blue?logo=github'>\n<a href='https://arxiv.org/abs/2602.06540'><img src='https://img.shields.io/badge/arXiv-2602.06540-red'>\n</p>\n\nThis repository contains **AgentCPM-Report**, an 8B-parameter deep research agent introduced in the paper [AgentCPM-Report: Interleaving Drafting and Deepening for Open-Ended Deep Research](https://arxiv.org/abs/2602.06540). \n\nAgentCPM-Report uses a **Writing As Reasoning Policy (WARP)** to dynamically revise outlines during report generation, alternating between evidence-based drafting and reasoning-driven deepening to produce high-quality, long-form research reports.\n\n## Links & Resources\n### 📊 AgentCPM-Report Models\n- **[AgentCPM-Report](https://huggingface.co/openbmb/AgentCPM-Report)** The Gemini-2.5-pro-DeepResearch Level Local DeepResearch Model\n- **[AgentCPM-Report-GGUF](https://huggingface.co/openbmb/AgentCPM-Report-GGUF)** The GGUF version of AgentCPM-Report\n\n### 🤖 AgentCPM-Explore Models \n- **[AgentCPM-Explore](https://huggingface.co/openbmb/AgentCPM-Explore)** The first open-source agent model with 4B parameters to appear on 8 widely used long-horizon agent benchmarks.\n- **[AgentCPM-Explore-GGUF](https://huggingface.co/openbmb/AgentCPM-Explore-GGUF)** The GGUF version of AgentCPM-Explore\n\n### 💻 Code & Framework\n- **[AgentCPM](https://github.com/OpenBMB/AgentCPM)** Our code for AgentCPM Series\n- **[UltraRAG](https://github.com/OpenBMB/UltraRAG)** A RAG Framework, Less Code, Lower "},{"ref":"P2","kind":"page","title":"OpenBMB/BMInf repository metadata","date":"2026-06-11T03:20:47.145795+00:00","date_source":null,"source_url":"https://github.com/OpenBMB/BMInf","signal_url":null,"signal_json_url":null,"text":"# OpenBMB/BMInf\n\nDescription: Efficient Inference for Big Models\n\nLanguage: Python\n\nLicense: Apache-2.0\n\nStars: 585\n\nForks: 67\n\nOpen issues: 16\n\nCreated: 2021-08-24T06:36:48Z\n\nPushed: 2023-01-24T14:08:16Z\n\nDefault branch: master\n\nFork: no\n\nArchived: no\n\nREADME:\n<div align=\"center\">\n\n<h1><img src=\"logo.png\" height=\"28px\" /> BMInf </h1>\n\n**Efficient Inference for Big Models**\n\n</div>\n\n<p align=\"center\">\n<a href=\"#overview\">Overview</a> • <a href=\"#install\">Installation</a> • <a href=\"#quick-start\">Quick Start</a> • <a href=\"./README-ZH.md\" target=\"_blank\">简体中文</a>\n<br>\n</p>\n\n<p align=\"center\">\n<a href='https://bminf.readthedocs.io/en/latest/'>\n<img src='https://readthedocs.org/projects/bminf/badge/?version=latest' alt='doc' />\n</a>\n<a href=\"https://github.com/OpenBMB/BMInf/blob/main/LICENSE\">\n<img alt=\"github\" src=\"https://img.shields.io/github/license/OpenBMB/BMInf\">\n</a>\n<a>\n<img alt=\"version\" src=\"https://img.shields.io/badge/version-1.0.0-blue\">\n</a>\n</p> \n\n## What's New\n- 2022/07/31 (**BMInf 2.0.0**) BMInf can now be applied to any transformer-based model.\n- 2021/12/21 (**BMInf 1.0.0**) Now the package no more depends on ``cupy`` and supports PyTorch backpropagation.\n- 2021/10/18 We updated the ``generate`` interface and added a new CPM 2.1 demo.\n- 2021/09/24 We publicly released BMInf on the 2021 Zhongguancun Forum (AI and Multidisciplinary Synergy Innovation Forum).\n\n**Note:** README for `BMInf-1` can be found in `old_docs` directory. Examples of CPM-1/2 and EVA will be published soon.\n\n<div id=\"overview\"></div>\n\n## Overview\n\nBMInf (Big Model Inference) is a low-resource inference package for large-scale pretrained language models (PLMs). \n\nBMInf supports running models with more than 10 billion parameters on a single NVIDIA GTX 1060 GPU in its minimum requirements. Running with better GPUs leads to better performance. In cases where the GPU memory supports the large model inference (such as V100 or A100), BMInf still has a significant performance improvement over the existing PyTorch implementation.\n\nIf you use the code, please cite the following [paper](https://aclanthology.org/2022.acl-demo.22.pdf):\n\n```\n@inproceedings{han2022bminf,\ntitle={BMInf: An Effi"},{"ref":"P3","kind":"page","title":"OpenBMB/BMInf-demos repository metadata","date":"2026-06-11T03:20:46.967651+00:00","date_source":null,"source_url":"https://github.com/OpenBMB/BMInf-demos","signal_url":null,"signal_json_url":null,"text":"# OpenBMB/BMInf-demos\n\nDescription: BMInf demos.\n\nLanguage: JavaScript\n\nStars: 16\n\nForks: 4\n\nOpen issues: 2\n\nCreated: 2021-09-17T09:03:13Z\n\nPushed: 2021-10-14T06:55:09Z\n\nDefault branch: master\n\nFork: no\n\nArchived: no\n\nREADME:\n# **Introduction**\n\nBMInf(Big Model Inference)-Demos is three examples designed according to three models in BMInf. These three examples are:\n\n+ **Fill Blank.** It is a use case designed according to CPM2.1 model. It can support arbitrary input of a paragraph of text and generate corresponding blank content according to context semantics.\n\n+ **Generate Story.** It is an example based on CPM1 model. You only need to write the beginning of a paragraph, and it can create a beautiful essay for you。\n\n+ **Dialogue.** It is an example we created based on EVA model. Here, you can talk freely with the machine.\n\n# Usage\n\n### Step1: \nRun following commands with `nvidia-docker2`.\n\n```console\n$ docker run -it --gpus 1 -v $HOME/.cache/bigmodels:/root/.cache/bigmodels -p 0.0.0.0:8000:8000 --rm openbmb/bminf-demos\n```\n\n### Step2:\n\nVisit http://localhost:8000/ with your browser.\n\n# **Demonstration**\n+ Fill Blank \n<div align=\"center\"> \n<img src=\"./images/demo1.jpg\" width = \"800\" height = \"400\" align=center />\n</div>\n\n+ Generate Story\n\n<div align=\"center\"> \n<img src=\"./images/demo2.jpg\" width = \"800\" height = \"400\" align=center />\n</div>\n\n+ Dialogue\n\n<div align=\"center\"> \n<img src=\"./images/demo3.jpg\" width = \"800\" height = \"400\" align=center />\n</div>"},{"ref":"P4","kind":"page","title":"OpenBMB/BMTrain repository metadata","date":"2026-06-11T03:20:46.821563+00:00","date_source":null,"source_url":"https://github.com/OpenBMB/BMTrain","signal_url":null,"signal_json_url":null,"text":"# OpenBMB/BMTrain\n\nDescription: Efficient Training (including pre-training and fine-tuning) for Big Models\n\nLanguage: Python\n\nLicense: Apache-2.0\n\nStars: 624\n\nForks: 88\n\nOpen issues: 10\n\nCreated: 2021-12-01T02:58:58Z\n\nPushed: 2026-04-23T02:43:21Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n<div align=\"center\">\n\n<h1><img src=\"docs/logo.png\" height=\"28px\" /> BMTrain</h1>\n\n**Efficient Training for Big Models**\n\n<p align=\"center\">\n<a href=\"#overview\">Overview</a> • <a href=\"#documentation\">Documentation</a> • <a href=\"#install\">Installation</a> • <a href=\"#usage\">Usage</a> • <a href=\"#performance\">Performance</a> • <a href=\"./README-ZH.md\" target=\"_blank\">简体中文</a>\n<br>\n</p>\n\n<p align=\"center\">\n\n<a href='https://bmtrain.readthedocs.io/en/latest/?badge=latest'>\n<img src='https://readthedocs.org/projects/bmtrain/badge/?version=latest' alt='Documentation Status' />\n</a>\n\n<a href=\"https://github.com/OpenBMB/BMTrain/releases\">\n<img alt=\"GitHub release (latest by date including pre-releases)\" src=\"https://img.shields.io/github/v/release/OpenBMB/BMTrain?include_prereleases\">\n</a>\n\n<a href=\"https://github.com/OpenBMB/BMTrain/blob/main/LICENSE\">\n<img alt=\"GitHub\" src=\"https://img.shields.io/github/license/OpenBMB/BMTrain\">\n</a>\n\n</p>\n\n</div>\n\n## What's New\n- 2024/02/26 **BMTrain** [1.0.0](https://github.com/OpenBMB/BMTrain/releases/tag/v1.0.0) released. Code refactoring and Tensor parallel support. See the detail in [update log](docs/UPDATE_1.0.0.md)\n- 2023/08/17 **BMTrain** [0.2.3](https://github.com/OpenBMB/BMTrain/releases/tag/v0.2.3) released. See the [update log](docs/UPDATE_0.2.3.md).\n- 2022/12/15 **BMTrain** [0.2.0](https://github.com/OpenBMB/BMTrain/releases/tag/0.2.0) released. See the [update log](docs/UPDATE_0.2.0.md).\n- 2022/06/14 **BMTrain** [0.1.7](https://github.com/OpenBMB/BMTrain/releases/tag/0.1.7) released. ZeRO-2 optimization is supported!\n- 2022/03/30 **BMTrain** [0.1.2](https://github.com/OpenBMB/BMTrain/releases/tag/0.1.2) released. Adapted to [OpenPrompt](https://github.com/thunlp/OpenPrompt)and [OpenDelta](https://github.com/thunlp/OpenDelta).\n- 2022/03/16 **BMTrain** [0.1.1](https://github.com/OpenBMB/BMTrain/releases/tag/0.1.1) has public"},{"ref":"P5","kind":"page","title":"OpenBMB/cpm_kernels repository metadata","date":"2026-06-11T03:20:46.732441+00:00","date_source":null,"source_url":"https://github.com/OpenBMB/cpm_kernels","signal_url":null,"signal_json_url":null,"text":"# OpenBMB/cpm_kernels\n\nLanguage: Python\n\nLicense: Apache-2.0\n\nStars: 26\n\nForks: 10\n\nOpen issues: 8\n\nCreated: 2021-12-01T03:00:35Z\n\nPushed: 2023-10-02T19:33:26Z\n\nDefault branch: master\n\nFork: no\n\nArchived: no\n\nREADME:\n# CPM kernels\n\nCUDA Kernels for cpm."},{"ref":"P6","kind":"page","title":"OpenBMB/BMList repository metadata","date":"2026-06-11T03:20:46.62649+00:00","date_source":null,"source_url":"https://github.com/OpenBMB/BMList","signal_url":null,"signal_json_url":null,"text":"# OpenBMB/BMList\n\nDescription: A List of Big Models\n\nLanguage: Python\n\nLicense: Apache-2.0\n\nStars: 345\n\nForks: 15\n\nOpen issues: 1\n\nCreated: 2022-07-07T02:54:25Z\n\nPushed: 2023-06-30T14:34:50Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n<div align=\"center\">\n\n<h1>BMList</h1>\n\n**A List of Big Models**\n\n</div>\n\n# Introduction\n\nWelcome to BMList! We wish to use this list to show the recent trend of big models.\n\nIn BMList, we list models that:\n\n1. Have at least 1 billion parameters;\n2. Have been publicly released either by a paper, an artice or a piece of news.\n\nIf you find any typos or mistakes in this repo, please feel free to create issues or pull requests!\n\n# What's New\n\n* 2022/08/05 We have upgraded the multi-dimensional table, and now you can filter the records as you wish!\n\n# Model Expo\n\n**We maintain a [website](https://openbmb.github.io/BMList) to show statistics of big models from multiple perspectives.**\n\n## Big Model List\n\nWe show all information of big models in a [multi-dimensional table](https://openbmb.github.io/BMList/list), in which you can easily classify models by organizations, languages, domains, etc.\n\n<img src=\"figures/bmlist.png\" width=\"1000px\">\n\n## Big Model Gallery\n\nWe also host a gallery to present figures about big models. Currently, there are five figures, previewed below, and any ideas for new figures are welcomed!\n\n### Big Model Trend\n\n<img src=\"figures/scatter.png\" width=\"1000px\">\n\n### Model Numbers by Organizations\n\n<img src=\"figures/affiliation_cnt.png\" width=\"1000px\">\n\n### Model Parameters by Organizations\n\n<img src=\"figures/affiliation_params.png\" width=\"1000px\">\n\n### Model Numbers by Time\n\n<img src=\"figures/time_cnt.png\" width=\"1000px\">\n\n### Model Parameters by Time\n\n<img src=\"figures/time_params.png\" width=\"1000px\">\n\n# Contribution\n\nWe welcome everyone to add new models. Please check our [contributing guidelines](https://github.com/OpenBMB/BMList/blob/main/CONTRIBUTING.md) to see how to contribute.\n\nOnce you added a model, the multi-dimensional table and the website will be automatically updated. Don't worry about that!\n\n## Contributors\n\n<a href=\"https://github.com/OpenBMB/BMList/graphs/contributors\">\n<img src=\"https://c"},{"ref":"P7","kind":"page","title":"OpenBMB/General-Model-License repository metadata","date":"2026-06-11T03:20:46.26133+00:00","date_source":null,"source_url":"https://github.com/OpenBMB/General-Model-License","signal_url":null,"signal_json_url":null,"text":"# OpenBMB/General-Model-License\n\nStars: 8\n\nForks: 1\n\nOpen issues: 1\n\nCreated: 2022-01-04T13:55:20Z\n\nPushed: 2023-05-27T02:03:23Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# 通用模型许可协议\n\n通用模型许可协议（General Model License，GML）为一系列开源模型许可协议的总称，适用于计算机科学人工智能领域中基于机器学习、深度学习等技术产生的计算机模型的开源与共享。协议起草过程中参考了Apache 2.0，MIT等一系列[开源软件协议](https://choosealicense.com/licenses/)与[知识共享许可协议（Creative Commons License）](https://creativecommons.org/share-your-work/)。针对通用模型的具体特点，我们设计并起草了本协议。\n\n## 相关定义\n\n在开始了解本协议前，用户需要了解的协议中的相关名词定义如下：\n\n- **通用模型**：是指本协议项下涉及的源模型和派生模型的统称。\n- **源模型**：是指发布者使用特定代码经数据训练后生成并发布的计算机算法及其参数。\n- **派生模型**：是指使用者通过改变源模型算法或参数等方式而生成的新模型。\n- **发布者**：指发布源模型的单位或个人。\n- **使用**：除非另有说明，本协议下的使用包括模型的下载、运算、共享、修改、分发等操作，以及对于模型结果的共享、修改等操作。\n- **使用者**：指根据本协议使用源模型的单位或个人。\n- **模型结果**：指在不改变参数的情况下，使用通用模型在输入特定数据下运行（即进行模型推理）得到的模型输出。\n\n## 使用者基础权利\n要使用本协议，用户需要明确本协议赋予的模型使用者的基础权利如下：\n\n- **模型共享** 使用者有权在不违反协议的前提下通过任何媒介或形式共享源模型。\n- **模型推理** 使用者有权在不违反协议的前提下使用经源模型或派生模型推理得到的结果。\n- **模型修改** 使用者有权在不违反协议的前提下通过改变算法或参数的方式修改源模型以取得派生模型。\n\n## 发布者可选限制\n除使用者基础权利外，协议也为模型发布者提供了一系列可定制的权利保障条款，供发布者在发布模型与协议时进行选择，从而约束使用者行为。包括：\n\n- **来源说明** 使用者使用通用模型和通用模型结果时须附上此通用模型的来源及本许可协议链接。\n- **限制修改发布** 使用者不可发布与传播经自行修改源模型后的派生模型以及派生模型结果。\n- **修改说明** 使用者通过修改源模型得到并发布派生模型或者在任何媒介上使用修改后的通用模型结果时，该使用者须以显著的方式说明修改内容，包括但不限于模型架构、模型训练方式、模型使用数据、结果修改方式等。\n- **相同方式再许可** 使用者须采取与此许可协议相同方式授权下游使用者使用派生模型且不得对本协议所授权利的行使施以进一步的限制。\n- **宣传限制** 使用者不得以发布者的名义推广宣传此通用模型。\n- **商业授权** 使用者获得发布者书面授权后，可以以任何商业目的使用此通用模型。\n- **非商业化** 使用者不可以任何商业目的使用此通用模型。\n\n## 协议定制\n针对发布者可选限制，我们提供了简单快捷的基于选择题的方式进行协议定制，仅需完成相关选择题，便可以轻松地为您的模型找到适合的许可协议。\n\n## 常见问题\n\n1. 通用模型许可协议与开源软件协议（Apache 2.0、MIT等）和知识共享许可协议（CC 4.0）的区别？我该如何选择它们？\n\n通用模型协议集合了知识共享许可协议的基于组合的协议选择方式与开源软件协议中对于使用者义务进行约定的相关内容，针对通用模型的特点（譬如模型由代码和参数组成，并且模型使用中包括训练和推理等不同阶段）我们进行了相应的整合与完善。\n\n至于协议选择，我们认为模型包括代码+参数，通用模型协议适用于代码和参数的共同保护。如果您发布的内容仅为软件，那么您可以选择使用一款开源软件协议。知识共享协议的授权内容更加宽泛，如果您要发布图片、文本等内容，可以参阅知识共享协议。\n\n## 参与贡献\n如果您有任何意见与建议，欢迎您在issue中提出，我们将持续对通用模型协议进行更新与完善。"},{"ref":"P8","kind":"page","title":"OpenBMB/ModelCenter repository metadata","date":"2026-06-11T03:20:46.18733+00:00","date_source":null,"source_url":"https://github.com/OpenBMB/ModelCenter","signal_url":null,"signal_json_url":null,"text":"# OpenBMB/ModelCenter\n\nDescription: Efficient, Low-Resource, Distributed transformer implementation based on BMTrain\n\nLanguage: Python\n\nLicense: Apache-2.0\n\nStars: 271\n\nForks: 32\n\nOpen issues: 12\n\nCreated: 2022-02-18T02:41:46Z\n\nPushed: 2023-11-27T08:37:53Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n<div align=\"center\">\n\n<h1><img src=\"docs/source/_static/images/logo.png\" height=\"32px\"/> ModelCenter</h1>\n\n**Efficient Low-Resource Implementations of Big Models**\n\n</div>\n\n<p align=\"center\">\n<a href=\"#overview\">Overview</a> •\n<a href=\"#documentation\">Documentation</a> •\n<a href=\"#installation\">Installation</a> •\n<a href=\"#quick-start\">Quick Start</a> •\n<a href=\"#supported-models\">Supported Models</a> •\n<a href=\"./README-ZH.md\" target=\"_blank\">简体中文</a>\n</p>\n\n<p align=\"center\">\n\n<a href='https://modelcenter.readthedocs.io/en/latest/?badge=latest'>\n<img src='https://readthedocs.org/projects/modelcenter/badge/?version=latest' alt='Documentation Status' />\n</a>\n\n<a href=\"https://github.com/OpenBMB/ModelCenter/releases\">\n<img alt=\"GitHub release (latest by date including pre-releases)\" src=\"https://img.shields.io/github/v/release/OpenBMB/ModelCenter?include_prereleases\">\n</a>\n\n<a href=\"https://github.com/OpenBMB/ModelCenter/blob/main/LICENSE\">\n<img alt=\"GitHub\" src=\"https://img.shields.io/github/license/OpenBMB/ModelCenter\">\n</a>\n\n</p>\n\n## What's New\n- 2023/06/13 [**ModelCenter 1.0.3**]() ModelCenter supports T5's beam search generation.\n- 2023/05/28 [**ModelCenter 1.0.2**]() ModelCenter supports LLaMA and its generation.\n- 2023/02/28 [**ModelCenter 1.0.1**]() ModelCenter supports FLAN-T5 (fp32) version.\n- 2022/11/21 [**ModelCenter 1.0.0**]() ModelCenter supports BMTrain>=0.2.0.\n- 2022/07/14 [**ModelCenter 0.1.5**]() ModelCenter supports Mengzi, GLM, Longformer, and KV_PLM.\n- 2022/07/05 [**ModelCenter 0.1.3**]() ModelCenter supports mT5, T5v1.1, ViT, and Wenzhong.\n- 2022/04/27 [**ModelCenter 0.1.1**]() ModelCenter supports RoBERTa. \n- 2022/04/06 [**ModelCenter 0.1.0**]() ModelCenter has publicly released the first stable version, which fixes some bugs in model performance and GPU memory usage.\n- 2022/03/21 [**ModelCenter 0.0.1-beta**]() ModelCenter has publicly"},{"ref":"P9","kind":"page","title":"OpenBMB/BMCook repository metadata","date":"2026-06-11T03:20:46.054631+00:00","date_source":null,"source_url":"https://github.com/OpenBMB/BMCook","signal_url":null,"signal_json_url":null,"text":"# OpenBMB/BMCook\n\nDescription: Model Compression for Big Models\n\nLanguage: Python\n\nLicense: Apache-2.0\n\nStars: 169\n\nForks: 25\n\nOpen issues: 6\n\nCreated: 2022-03-09T07:51:28Z\n\nPushed: 2023-06-30T08:57:51Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n<div align=\"center\">\n\n<h1><img src=\"docs/_static/logo.png\" height=\"28px\" /> BMCook</h1>\n\n**Model Compression for Big Models**\n\n</div>\n\n<p align=\"center\">\n<a href=\"#overview\">Overview</a> • <a href=\"#documentation\">Documentation</a> • <a href=\"#install\">Installation</a> • <a href=\"#usage\">Usage</a> • <a href=\"#quick-start\">Quick Start</a> • <a href=\"./README-ZH.md\" target=\"_blank\">简体中文</a>\n<br>\n</p>\n\n<p align=\"center\">\n<a href='https://bmcook.readthedocs.io/en/main/'>\n<img src='https://readthedocs.org/projects/bmcook/badge/?version=main' alt='doc' />\n</a>\n<a href=\"https://github.com/OpenBMB/BMCook/blob/main/LICENSE\">\n<img alt=\"github\" src=\"https://img.shields.io/github/license/OpenBMB/BMCook\">\n</a>\n<a>\n<img alt=\"version\" src=\"https://img.shields.io/badge/version-0.1.0-blue\">\n</a>\n</p> \n\n## What's New\n\n- 2023/5/27 Support structured pruning of Decoder-only models, and the compression of [CPM-Live](https://github.com/OpenBMB/CPM-Live/tree/master) models。\n- 2022/5/17 Support PLMs in [model-center](https://github.com/OpenBMB/ModelCenter).\n- 2022/3/29 (**BMCook 0.1.0**) Now we publicly release the first version of BMCook.\n\n<div id=\"overview\"></div>\n\n## Overview\n\nBMCook is a model compression toolkit for large-scale pre-trained language models (PLMs), which integrates multiple model compression methods. You can combine them in any way to achieve the desired speedup. Specifically, we implement the following four model compression methods, knowledge distillation, model pruning, model quantization, and model MoEfication. It has following features:\n\n- **Various Supported Methods.** Compared to existing compression toolkits, BMCook supports all mainstream acceleration methods for pre-trained language models.\n- **User Friendly.** Based on BMCook, we can implement different compression methods with just a few lines of codes.\n- **Combination in Any Way.** Due to the decoupled implications, the compression methods can be com"},{"ref":"P10","kind":"page","title":"OpenBMB/CPM-Live repository metadata","date":"2026-06-11T03:20:45.876881+00:00","date_source":null,"source_url":"https://github.com/OpenBMB/CPM-Live","signal_url":null,"signal_json_url":null,"text":"# OpenBMB/CPM-Live\n\nDescription: Live Training for Open-source Big Models\n\nLanguage: Python\n\nStars: 500\n\nForks: 40\n\nOpen issues: 7\n\nCreated: 2022-05-21T12:24:40Z\n\nPushed: 2023-05-30T09:08:02Z\n\nDefault branch: master\n\nFork: no\n\nArchived: no\n\nREADME:\n<div align=\"center\">\n\n<h1>CPM-Live</h1>\n\n**Live Training for Open-source Big Models**\n\n<p align=\"center\">\n<a href=\"https://live.openbmb.org/\" target=\"_blank\">Website</a> • <a href=\"./plans/CPM-Live训练计划书.md\" target=\"_blank\">Plan</a> • <a href=\"https://github.com/OpenBMB/CPM-Live/discussions\">Discussion</a> • <a href=\"./README-ZH.md\" target=\"_blank\">简体中文</a>\n<br>\n<br>\n</p>\n\n</div>\n\n## What's New\n- 2023/05/27 [CPM-Bee](https://github.com/OpenBMB/CPM-Bee) is released!\n- 2023/04/12 CPM-Ant has been integrated into [HuggingFace Transformers](https://huggingface.co/openbmb/cpm-ant-10b)!\n- 2022/10/12 [CPM-Ant+](https://github.com/OpenBMB/CPM-Live/tree/cpm-ant-plus/cpm-live), a bilingual model, is released! In addition to generating Chinese/English text, you can now use our model for QA, summarization and translation tasks!\n- 2022/09/16 [CPM-Ant](https://github.com/OpenBMB/CPM-Live/tree/cpm-ant/cpm-live) is released!\n- 2022/05/29 The training of CPM-Live has launched today! See [training dynamics](https://live.openbmb.org/home).\n- 2022/05/25 The [training plan](./plans/CPM-Live训练计划书.md) for CPM-Live is now published. Look forward to the training! \n\n## Milestones\n\n- **CPM-Bee** (2022/10/13-2023/05/27) [[Code](https://github.com/OpenBMB/CPM-Bee)][[Model](https://github.com/OpenBMB/CPM-Bee#%E6%A8%A1%E5%9E%8B)][[Plan](./plans/CPM-Bee训练计划书.md)]\n- **CPM-Ant+** (2022/08/05-2022/10/12) [[Code](https://github.com/OpenBMB/CPM-Live/tree/cpm-ant-plus/cpm-live)][[Model](https://github.com/OpenBMB/CPM-Live/tree/cpm-ant-plus/cpm-live#model-checkpoints)]\n- **CPM-Ant** (2022/05/29-2022/08/05) [[Code](https://github.com/OpenBMB/CPM-Live/tree/cpm-ant/cpm-live)][[Model](https://github.com/OpenBMB/CPM-Live/tree/cpm-ant/cpm-live#model-checkpoints)][[Website](https://live.openbmb.org/ant)][[Blog](https://www.openbmb.org/en/community/blogs/blogpage?id=98afef2ce45f4fe9a4bc15a66d7ccb92)][[Plan](./plans/CPM-Ant训练计划书.md)]\n\n## Training Plan\nConsidering th"},{"ref":"P11","kind":"page","title":"OpenBMB/BMTools repository metadata","date":"2026-06-11T03:20:45.494662+00:00","date_source":null,"source_url":"https://github.com/OpenBMB/BMTools","signal_url":null,"signal_json_url":null,"text":"# OpenBMB/BMTools\n\nDescription: Tool Learning for Big Models, Open-Source Solutions of ChatGPT-Plugins\n\nLanguage: Python\n\nLicense: Apache-2.0\n\nStars: 2773\n\nForks: 248\n\nOpen issues: 12\n\nCreated: 2023-03-31T08:00:43Z\n\nPushed: 2023-12-05T05:25:27Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n<div align= \"center\">\n<h1><img src=\"assets/logo.png\" height=\"28px\" /> BMTools</h1>\n</div>\n\n<p align=\"center\">\n<a href=\"#whats-new\">News</a> •\n<a href=\"#1-setup\">Setup</a> •\n<a href=\"#2-use-existing-tools\">How To Use</a> •\n<a href=\"https://arxiv.org/abs/2304.08354\">Paper</a> •\n<a href=\"https://bmtools.readthedocs.io/en/main/\">Docs</a> •\n<a href=\"https://github.com/thunlp/ToolLearningPapers\">Paper List</a> •\n<a href=\"https://huggingface.co/spaces/congxin95/BMTools-demo\">Demo</a> •\n<a href=\"#citation\">Citation</a> •\n</p>\n\n*Read this in [Chinese](README_zh.md).*\n\n<br>\n\n<div align=\"center\">\n<img src=\"assets/overview.png\" width=\"700px\">\n</div>\n<br>\n\nBMTools is an open-source repository that extends language models using tools and serves as a platform for the community to build and share tools. In this repository, you can (1) easily build a plugin by writing python functions (2) use external ChatGPT-Plugins. \n\nThis project is inspired by the open-source project [LangChain](https://github.com/hwchase17/langchain/) and optimized for the usage of open-sourced tools like [ChatGPT-Plugins](https://openai.com/blog/chatgpt-plugins), striving to achieve the open-source academic version of ChatGPT-Plugins.\n\n- **For new features and further developments, please go to [XAgent](https://github.com/OpenBMB/XAgent).**\n\n- **A demo of using BMTools to manipulate tools for meta analysis.**\n\n<div align=\"center\">\n\n<img src=\"assets/meta0423.gif\" width=\"700px\">\n\n</div>\n\n## What's New\n\n- **[2023/5/28]** We release [ToolBench](https://github.com/OpenBMB/ToolBench), a large-scale tool learning benchmark together with a capable model.\n\n- **[2023/5/25]** The evaluation data used in the paper is partially released at [data-test](https://cloud.tsinghua.edu.cn/d/2dab79f7b66841329f45/), we have also created large-scale SFT (100k+) high-quality tool-use training data at [data-sft](https://drive.google.com/"},{"ref":"P12","kind":"page","title":"OpenBMB/CPM-Bee repository metadata","date":"2026-06-11T03:20:45.455059+00:00","date_source":null,"source_url":"https://github.com/OpenBMB/CPM-Bee","signal_url":null,"signal_json_url":null,"text":"# OpenBMB/CPM-Bee\n\nDescription: 百亿参数的中英文双语基座大模型\n\nLanguage: Python\n\nStars: 2406\n\nForks: 179\n\nOpen issues: 52\n\nCreated: 2023-04-25T14:40:39Z\n\nPushed: 2023-07-28T04:00:33Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n<div align=\"center\">\n\n# CPM-Bee\n\n**百亿参数的开源中英文双语基座大模型**\n\n<p align=\"center\">\n<a href=\"#模型\">模型</a> •\n<a href=\"#预训练\">OpenBMB体系</a> •\n<a href=\"#零样本评测\">性能表现</a> •\n<a href=\"#模型协议\">开源协议</a>\n</p>\n\n</div>\n\n## ✨ 模型介绍\n\n**CPM-Bee**是一个完全开源、允许商用的百亿参数中英文基座模型，也是[**CPM-Live**](https://live.openbmb.org/)训练的第二个里程碑。它采用Transformer自回归架构（auto-regressive），在超万亿（trillion）高质量语料上进行预训练，拥有强大的基础能力。开发者和研究者可以在CPM-Bee基座模型的基础上在各类场景进行适配来以创建特定领域的应用模型。\n\n- **👐 开源可商用**：OpenBMB始终秉承“让大模型飞入千家万户”的开源精神，CPM-Bee基座模型将完全开源并且可商用，以推动大模型领域的发展。我们鼓励全球范围内的科研机构、企业和个人开发者在遵守[开源许可协议](#模型协议)的前提下，自由地在CPM-Bee基座模型上进行创新。\n\n- **💫 中英双语性能优异**：CPM-Bee基座模型在预训练语料上进行了严格的筛选和配比，同时在中英双语上具有亮眼表现，具体可参见[评测任务和结果](#零样本评测)。\n\n- **📖 超大规模高质量语料**：CPM-Bee基座模型在超万亿语料进行训练，是开源社区内经过语料最多的模型之一。同时，我们对预训练语料进行了严格的筛选、清洗和后处理以确保质量。\n\n- **<img src=\"https://i.imgloc.com/2023/05/21/V4nLS3.png\" width=\"20px\"> OpenBMB大模型系统生态支持**：OpenBMB大模型系统围绕高性能预训练、适配、压缩、推理开发了一系列工具，CPM-Bee基座模型将配套所有的工具脚本，高效支持开发者进行进阶使用。\n\n- **🔨 对话和工具使用能力**： 结合OpenBMB在指令微调和工具学习的探索，我们在CPM-Bee基座模型的基础上进行微调，训练出了具有强大对话和工具使用能力的实例模型，API和内测将于近期开放。\n\n*Read this in [English](https://github.com/OpenBMB/CPM-Bee/blob/main/README_en.md).*\n\n说明：CPM-Bee是一个**基座**模型，即从零开始通过**预训练**得来。我们鼓励用户在自己的场景和数据上**适配/微调/对齐**后再进行使用。例如，[WebCPM](https://github.com/thunlp/WebCPM) 以CPM-Bee为基座，在人类网络检索的序列化数据上进行适配，获得了复杂问答和上网检索的能力。后续我们将会发布更多在CPM-Bee基座模型基础上适配的模型。\n\n<div align=\"center\">\n<img src=\"https://i.imgloc.com/2023/06/07/VwgLLN.png\" width=\"660px\">\n<div align=\"center\">\n本仓库主要提供 CPM-Bee 基座模型\n</div>\n</div>\n\n## 📰 更新信息\n\n- **[2023/06/30]** 基于CPM-Bee的多模态系列模型[VisCPM](https://github.com/OpenBMB/VisCPM)发布，支持多模态对话和文生图！\n- **[2023/06/16]** CPM-Bee现已支持🤗[Transformers](https://huggingface.co/openbmb/cpm-bee-10b)。\n- **[2023/06/08]** 更新了使用CPM-Bee进行基础任务微调的[教程](https://github.com/OpenBMB/CPM-Bee/tree/main/tutorials/basic_task_finetune)。\n- **[2023/05/27]** 百亿参数，允许商用的中英双语基座模型CPM-Bee开源了，它是[**CPM-Live**](https://live.openbmb.org/)的第二个里程碑。\n\n## 🍯 CPM-Bee系列模型\n\n| 模型 | 描述 | \n| :---: | :---: | \n|[VisCPM](https://github.com/OpenBMB/VisCPM)| 支持多模态对"},{"ref":"P13","kind":"page","title":"OpenBMB/DecT repository metadata","date":"2026-06-11T03:20:45.264563+00:00","date_source":null,"source_url":"https://github.com/OpenBMB/DecT","signal_url":null,"signal_json_url":null,"text":"# OpenBMB/DecT\n\nDescription: Source code for ACL 2023 paper Decoder Tuning: Efficient Language Understanding as Decoding\n\nLanguage: Python\n\nLicense: MIT\n\nStars: 53\n\nForks: 8\n\nOpen issues: 0\n\nCreated: 2023-05-05T01:50:11Z\n\nPushed: 2023-06-25T08:57:48Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# DecT\n\nSource code for ACL 2023 paper [Decoder Tuning](https://arxiv.org/abs/2212.08408)\n\n## Installation\n\nOur code is based on PyTorch, HuggingFace Transformers, and [OpenPrompt](https://github.com/thunlp/OpenPrompt), please install dependencies by\n\n```bash\npip install -r requirements.txt\n```\n\n## Download Datasets\n\nDownload the 10 datasets with the following scripts\n\n```bash\ncd datasets\nbash download_datasets.sh\ncd ..\n```\n\n## Run DecT\n\nThen you can run DecT by running `run_dect.py`, for example\n\n```bash\npython src/run_dect.py \\\n--model roberta \\\n--size large \\\n--type mlm \\\n--model_name_or_path roberta-large \\\n--shot 1 \\\n--dataset sst2 \\\n--proto_dim 128 \\\n--model_logits_weight 1 \\\n```\n\nIn `run_dect.py` we provide instructions for each argument. To reproduce the results in paper, please run the following combinations\n\n```bash\npython src/run_dect.py \\\n--shot [1, 4, 16] \\\n--dataset [sst2, imdb, yelp, agnews, dbpedia, yahoo, rte, snli, mnli-m, mnli-mm, fewnerd] \\\n--seed [0, 1, 2, 3, 4] \\\n```\n\n## Configure Models\n\nYou can configure different models by setting `model`, `type`, `size`, `model_name_or_path` parameters. \n- `model`: Model name. We now support plms in OpenPrompt, LLaMA, Alpaca and Vicuna.\n- `type`: `mlm`, `lm` or `chat`. This will determine the prompt template. For `lm` type models, we put the `[mask]` token at the end of the template. For `chat` models, we implement the chat template for [Vicuna](https://lmsys.org/blog/2023-03-30-vicuna/) v1.1. You may change the template if you use other models.\n- `size`: Model size. Currently, it is used to set the hidden state dimension for LLaMA models.\n- `model_name_or_path`: Path to model weights. \n\nYou can also modify the `load_model` function in `src/run_dect.py` to support more models!"},{"ref":"P14","kind":"page","title":"OpenBMB/AgentVerse repository metadata","date":"2026-06-11T03:20:44.985413+00:00","date_source":null,"source_url":"https://github.com/OpenBMB/AgentVerse","signal_url":null,"signal_json_url":null,"text":"# OpenBMB/AgentVerse\n\nDescription: 🤖 AgentVerse 🪐 is designed to facilitate the deployment of multiple LLM-based agents in various applications, which primarily provides two frameworks: task-solving and simulation\n\nLanguage: JavaScript\n\nLicense: Apache-2.0\n\nStars: 5052\n\nForks: 514\n\nOpen issues: 35\n\nCreated: 2023-05-06T01:43:19Z\n\nPushed: 2024-09-09T05:47:44Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n<h1 align=\"center\"> 🤖 AgentVerse 🪐 </h1>\n\n<!--\n<h3 align=\"center\">\n<p>A Framework for Multi-LLM Environment Simulation</p>\n</h3>\n-->\n\n<p align=\"center\">\n<a href=\"https://github.com/OpenBMB/AgentVerse/blob/main/LICENSE\">\n<img alt=\"License: Apache2\" src=\"https://img.shields.io/badge/License-Apache_2.0-green.svg\">\n</a>\n<a href=\"https://www.python.org/downloads/release/python-3916/\">\n<img alt=\"Python Version\" src=\"https://img.shields.io/badge/python-3.9+-blue.svg\">\n</a>\n<a href=\"https://github.com/OpenBMB/AgentVerse/actions/\">\n<img alt=\"Build\" src=\"https://img.shields.io/github/actions/workflow/status/OpenBMB/AgentVerse/test.yml\">\n</a>\n<a href=\"https://github.com/psf/black\">\n<img alt=\"Code Style: Black\" src=\"https://img.shields.io/badge/code%20style-black-black\">\n<!-- </a>\n<a href=\"https://github.com/OpenBMB/AgentVerse/issues\">\n<img alt=\"Contributions: Welcome\" src=\"https://img.shields.io/badge/contributions-welcome-brightgreen.svg?style=flat\">\n</a> -->\n<a href=\"https://huggingface.co/AgentVerse\">\n<img alt=\"HuggingFace\" src=\"https://img.shields.io/badge/hugging_face-play-yellow\">\n</a>\n<a href=\"https://discord.gg/gDAXfjMw\">\n<img alt=\"Discord\" src=\"https://img.shields.io/badge/AgentVerse-Discord-purple?style=flat\">\n</a>\n\n</p>\n\n<p align=\"center\">\n<img src=\"./imgs/title.png\" width=\"512\">\n</p>\n\n<p align=\"center\">\n【<a href=\"https://arxiv.org/abs/2308.10848\">Paper</a>】 \n</p>\n\n<p align=\"center\">\n【English | <a href=\"README_zh.md\">Chinese</a>】 \n</p>\n\n**AgentVerse** is designed to facilitate the deployment of multiple LLM-based agents in various applications. AgentVerse primarily provides two frameworks: **task-solving** and **simulation**. \n\n- Task-solving: This framework assembles multiple agents as an automatic multi-agent system ([AgentVerse-Tasksolving](https:/"},{"ref":"P15","kind":"page","title":"OpenBMB/BMPrinciples repository metadata","date":"2026-06-11T03:20:44.886789+00:00","date_source":null,"source_url":"https://github.com/OpenBMB/BMPrinciples","signal_url":null,"signal_json_url":null,"text":"# OpenBMB/BMPrinciples\n\nDescription: A collection of phenomenons observed during the scaling of big foundation models, which may be developed into consensus, principles, or laws in the future\n\nLicense: MIT\n\nStars: 285\n\nForks: 20\n\nOpen issues: 1\n\nCreated: 2023-05-10T13:24:03Z\n\nPushed: 2023-08-13T09:08:36Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# BM-Principles\n\n🌟 The big models have proven their potential to lead to artificial general intelligence. However 😕, due to their rapid development, people have not fully grasped the principles of understanding and training big models. Therefore, in order to learn about big models together, we have decided to collect **new phenomena observed on the big models** and summarize them in this repository 📚 in the form of short entries. We hope this collection of phenomena observed during the scaling of big models may form future consensuses, principles, or patterns 📝. \n\nThe repository focuses on two aspects:\n\n- **How**: How to train powerful big models? 🚀\n- **What**: What properties are interesting for big models? 🤔\n\nThe repo is far from exclusive currently. Let's work together to improve it! 💪\n\n## How: how to train a powerful big model.\n\n1. **Scaling of Computation**\n1. **Training loss decreases predictably.**\n- Training loss can be written as a smooth function of model parameters and computation.\n<img src=\"https://github.com/OpenBMB/BMPrinciples/blob/main/figs/H1.1.loss_descrease.png\" alt=\"\" width=\"400\" height=\"250\">\n\n> [Scaling Laws for Neural Language Models](https://arxiv.org/abs/2001.08361)\n\n> [Scaling Laws for Autoregressive Generative Modeling](https://arxiv.org/abs/2010.14701)\n\n2. **Computational-optimal language model.**\n- Given a fixed computational budget, if we train an excessively large model, we can only iterate for a very limited number of steps. On the other hand, if we train a model that is too small, the limit of the loss will not be as good as that of a larger model. Therefore, there exists an *optimal model size*, *optimal training compute*, and *optimal tokens*. \n- From previous experience, it's roughly $20 * N$, where $N$ is the number of model parameters.\n<img src=\"https://github.com"},{"ref":"P16","kind":"page","title":"OpenBMB/ToolBench repository metadata","date":"2026-06-11T03:20:44.699331+00:00","date_source":null,"source_url":"https://github.com/OpenBMB/ToolBench","signal_url":null,"signal_json_url":null,"text":"# OpenBMB/ToolBench\n\nDescription: [ICLR'24 spotlight] An open platform for training, serving, and evaluating large language model for tool learning.\n\nLanguage: Python\n\nLicense: Apache-2.0\n\nStars: 5663\n\nForks: 485\n\nOpen issues: 161\n\nCreated: 2023-05-28T03:46:17Z\n\nPushed: 2025-05-21T15:46:59Z\n\nDefault branch: master\n\nFork: no\n\nArchived: no\n\nREADME:\n<div align= \"center\">\n<h1> 🛠️ToolBench🤖</h1>\n</div>\n\n<div align=\"center\">\n\n![Dialogues](https://img.shields.io/badge/Tool\\_Num-3451-red?style=flat-square)\n![Dialogues](https://img.shields.io/badge/API\\_Num-16464-red?style=flat-square)\n![Dialogues](https://img.shields.io/badge/Current\\_Dataset\\_Size-126K-red?style=flat-square)\n![Dialogues](https://img.shields.io/badge/Total\\_API\\_Call-469K-red?style=flat-square)\n![Dialogues](https://img.shields.io/badge/Average\\_Reasoning\\_Traces-4.0-red?style=flat-square)\n![Dialogues](https://img.shields.io/badge/Tool\\_LLaMA-Released-green?style=flat-square)\n\n</div>\n\n<p align=\"center\">\n<a href=\"#model\">Model</a> •\n<a href=\"#data\">Data Release</a> •\n<a href=\"#web-ui\">Web Demo</a> •\n<a href=\"#tooleval\">Tool Eval</a> •\n<a href=\"https://arxiv.org/pdf/2307.16789.pdf\">Paper</a> •\n<a href=\"#citation\">Citation</a>\n\n</p>\n\n</div>\n\n<div align=\"center\">\n<img src=\"assets/ToolLLaMA-logo.png\" width=\"350px\">\n</div>\n\n🔨This project (ToolLLM) aims to construct **open-source, large-scale, high-quality** instruction tuning SFT data to facilitate the construction of powerful LLMs with general **tool-use** capability. We aim to empower open-source LLMs to master thousands of diverse real-world APIs. We achieve this by collecting a high-quality instruction-tuning dataset. It is constructed automatically using the latest ChatGPT (gpt-3.5-turbo-16k), which is upgraded with enhanced [function call](https://openai.com/blog/function-calling-and-other-api-updates) capabilities. We provide the dataset, the corresponding training and evaluation scripts, and a capable model ToolLLaMA fine-tuned on ToolBench.\n\n**2024.8 Update** We have updated the RapidAPI server with a new IP, please make sure you get the latest code. You can also build it locally using codes [here](https://drive.google.com/file/d/1JdbHkL2D8as1docfH"},{"ref":"P17","kind":"page","title":"OpenBMB/VisCPM repository metadata","date":"2026-06-11T03:20:44.676222+00:00","date_source":null,"source_url":"https://github.com/OpenBMB/VisCPM","signal_url":null,"signal_json_url":null,"text":"# OpenBMB/VisCPM\n\nDescription: [ICLR'24 spotlight] Chinese and English Multimodal Large Model Series (Chat and Paint) | 基于CPM基础模型的中英双语多模态大模型系列\n\nLanguage: Python\n\nStars: 1068\n\nForks: 89\n\nOpen issues: 8\n\nCreated: 2023-06-30T03:35:01Z\n\nPushed: 2024-06-13T14:02:54Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n<div align=\"center\">\n\n# VisCPM\n**基于CPM基础模型的中英双语多模态大模型系列**\n<p align=\"center\">\n<a href=\"#-viscpm-chat\">多模态对话模型VisCPM-Chat</a> •\n<a href=\"#-viscpm-paint\">文生图模型VisCPM-Paint</a> •\n<a href=\"#-使用\">使用</a> •\n<a href=\"https://arxiv.org/pdf/2308.12038.pdf\">论文</a>\n</p>\n<p>\n<a href=\"http://120.92.209.146/\">VisCPM-Chat Demo</a> •\n<a href=\"https://huggingface.co/spaces/openbmb/viscpm-paint\">VisCPM-Paint Demo</a> •\n<a href=\"https://huggingface.co/openbmb/VisCPM-Chat\"> VisCPM-Chat🤗 </a> •\n<a href=\"https://huggingface.co/openbmb/VisCPM-Paint\"> VisCPM-Paint🤗 </a>\n</p>\n\n<p align=\"center\">\n简体中文 | <a href=\"README_en.md\">English</a>\n</p>\n</div>\n\n**`VisCPM`** is a family of open-source large multimodal models, which support multimodal conversational capabilities (`VisCPM-Chat` model) and text-to-image generation capabilities (`VisCPM-Paint` model) in both Chinese and English, achieving state-of-the-art performance among Chinese open-source multimodal models. VisCPM is trained based on the large language model [CPM-Bee](https://github.com/OpenBMB/CPM-Bee) with 10B parameters, fusing visual encoder (Muffin) and visual decoder (Diffusion-UNet) to support visual inputs and outputs. Thanks to the good bilingual capability of CPM-Bee, `VisCPM` can be pre-trained with English multimodal data only and well generalize to achieve promising Chinese multimodal capabilities.\n\n**`VisCPM`** 是一个开源的多模态大模型系列，支持中英双语的多模态对话能力（`VisCPM-Chat`模型）和文到图生成能力（`VisCPM-Paint`模型），在中文多模态开源模型中达到最佳水平。VisCPM基于百亿参数量语言大模型[CPM-Bee](https://github.com/OpenBMB/CPM-Bee)（10B）训练，融合视觉编码器[Muffin](https://github.com/thunlp/Muffin)和视觉解码器[Diffusion-UNet](https://github.com/CompVis/stable-diffusion)以支持视觉信号的输入和输出。得益于CPM-Bee基座优秀的双语能力，`VisCPM`可以仅通过英文多模态数据预训练，泛化实现优秀的中文多模态能力。\n\n- **👐 开源使用**：VisCPM可以自由被用于个人和研究用途。我们希望通过开源VisCPM模型系列，推动多模态大模型开源社区和相关研究的发展。\n- **🌟 涵盖图文双向生成**：VisCPM模型系列较为全面地支持了图文多模态能力，涵盖多模态对话（图到文生成）能力和文到图生成能力。\n- **💫 "},{"ref":"P18","kind":"page","title":"OpenBMB/UltraFeedback repository metadata","date":"2026-06-11T03:20:44.485359+00:00","date_source":null,"source_url":"https://github.com/OpenBMB/UltraFeedback","signal_url":null,"signal_json_url":null,"text":"# OpenBMB/UltraFeedback\n\nDescription: A large-scale, fine-grained, diverse preference dataset (and models).\n\nLanguage: Python\n\nLicense: MIT\n\nStars: 368\n\nForks: 17\n\nOpen issues: 12\n\nCreated: 2023-08-18T02:17:47Z\n\nPushed: 2023-12-29T16:39:19Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n<div align=\"center\">\n\n<img src=\"figures/logo.png\" width=\"400px\">\n\n**A large-scale, fine-grained, diverse preference dataset**\n\n<p align=\"center\">\n<a href=\"#introduction\"> Introduction</a> •\n<a href=\"#dataset-construction\">Dataset Construction</a> •\n<a href=\"#dataset-example\">Example</a> •\n<a href=\"#ultrarm\">UltraRM</a> •\n<a href=\"#ultrarm\">UltraCM</a>\n</p>\n\n</div>\n\n# News\n- [2023/12/29]: We have fixed the `overall_score` as pointed in [this issue](https://github.com/OpenBMB/UltraFeedback/issues/8) and updated the dataset on [HuggingFace](https://huggingface.co/datasets/openbmb/UltraFeedback). Please refer to the below \"Update\" section for details.\n- [2023/09/26]: UltraRM unleashes the power of [UltraLM-13B-v2.0](https://huggingface.co/openbmb/UltraLM-13b-v2.0) and [UltraLM-13B](https://huggingface.co/openbmb/UltraLM-13b)! A simple best-of-16 sampling achieves **92.30%** (UltraLM2, 🥇 in 13B results) and **91.54%** (UltraLM, 🥇 in LLaMA-1 results) win rates against text-davinci-003 on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/) benchmark!\n- [2023/09/26]: We release the [UltraFeedback](https://huggingface.co/datasets/openbmb/UltraFeedback) dataset, along with UltraFeedback-powered reward model [UltraRM](https://huggingface.co/openbmb/UltraRM-13b) and critique model [UltraCM](https://huggingface.co/openbmb/UltraCM-13b)! Both built **new SOTAs** over open-source models! \n\n# Update\nThe initial version of UltraFeedback includes 2628 completions that were assigned an overall score of `10`. However, as pointed in Issue [#8](https://github.com/OpenBMB/UltraFeedback/issues/8), many of these completions should have been assigned a score of `1`. Intuitively, a completion with an overall score of `10` should be high-quality, which can be reflected in its corresponding `averaged` fine-grained scores. Hence, to rectify the scores, we processed all the potentially faulty compl"},{"ref":"P19","kind":"page","title":"OpenBMB/ChatDev repository metadata","date":"2026-06-11T03:20:44.214156+00:00","date_source":null,"source_url":"https://github.com/OpenBMB/ChatDev","signal_url":null,"signal_json_url":null,"text":"# OpenBMB/ChatDev\n\nDescription: ChatDev 2.0: Dev All through LLM-powered Multi-Agent Collaboration\n\nLanguage: Python\n\nLicense: Apache-2.0\n\nStars: 33364\n\nForks: 4158\n\nOpen issues: 62\n\nCreated: 2023-08-28T02:18:13Z\n\nPushed: 2026-05-27T12:41:14Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# ChatDev 2.0 - DevAll\n\n<p align=\"center\">\n<img src=\"frontend/public/media/logo.png\" alt=\"DevAll Logo\" width=\"500\"/>\n</p>\n\n<p align=\"center\">\n<strong>A Zero-Code Multi-Agent Platform for Developing Everything</strong>\n</p>\n\n<p align=\"center\">\n【<a href=\"./README.md\">English</a> | <a href=\"./README-zh.md\">简体中文</a>】\n</p>\n<p align=\"center\">\n【📚 <a href=\"#developers\">Developers</a> | 👥 <a href=\"#primary-contributors\">Contributors</a>｜⭐️ <a href=\"https://github.com/OpenBMB/ChatDev/tree/chatdev1.0\">ChatDev 1.0 (Legacy)</a>】\n</p>\n\n## 📖 Overview\nChatDev has evolved from a specialized software development multi-agent system into a comprehensive multi-agent orchestration platform.\n\n- <a href=\"https://github.com/OpenBMB/ChatDev/tree/main\">**ChatDev 2.0 (DevAll)**</a> is a **Zero-Code Multi-Agent Platform** for \"Developing Everything\". It empowers users to rapidly build and execute customized multi-agent systems through simple configuration. No coding is required—users can define agents, workflows, and tasks to orchestrate complex scenarios such as data visualization, 3D generation, and deep research.\n- <a href=\"https://github.com/OpenBMB/ChatDev/tree/chatdev1.0\">**ChatDev 1.0 (Legacy)**</a> operates as a **Virtual Software Company**. It utilizes various intelligent agents (e.g., CEO, CTO, Programmer) participating in specialized functional seminars to automate the entire software development life cycle—including designing, coding, testing, and documenting. It serves as the foundational paradigm for communicative agent collaboration.\n\n## 🎉 News\n• **Jan 07, 2026: 🚀 We are excited to announce the official release of ChatDev 2.0 (DevAll)!** This version introduces a zero-code multi-agent orchestration platform. The classic ChatDev (v1.x) has been moved to the [`chatdev1.0`](https://github.com/OpenBMB/ChatDev/tree/chatdev1.0) branch for maintenance. More details about ChatDev 2.0 ca"},{"ref":"P20","kind":"page","title":"OpenBMB/XAgent-doc repository metadata","date":"2026-06-11T03:20:44.063643+00:00","date_source":null,"source_url":"https://github.com/OpenBMB/XAgent-doc","signal_url":null,"signal_json_url":null,"text":"# OpenBMB/XAgent-doc\n\nDescription: Document for XAgent.\n\nLicense: Apache-2.0\n\nStars: 21\n\nForks: 8\n\nOpen issues: 0\n\nCreated: 2023-10-30T12:25:49Z\n\nPushed: 2023-11-30T14:30:10Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# This is doc of XAgent website.\n> Develop in win11 by Arno\n\n1. Create virtual environment\n```python\npython -m venv .venv\n```\n\n2. Activate virtual environment\n\n| Platform | Shell | Command to activate virtual environment |\n|----------|------------|---------------------------------------------------|\n| POSIX | bash/zsh | `source .venv/bin/activate` |\n| | fish | `source .venv/bin/activate.fish` |\n| | csh/tcsh | `source .venv/bin/activate.csh` |\n| | PowerShell | `.venv/bin/Activate.ps1` |\n| Windows | cmd.exe | `.venv\\Scripts\\activate.bat` |\n| | PowerShell | `.venv\\\\Scripts\\Activate.ps1` |\n\n3. Install `poetry` and use it to install dependencies\n\n```python\npip install poetry\npoetry install\n```\n\n4. Build html \n\n```bash\n.\\docs\\make html\n```"},{"ref":"P21","kind":"page","title":"OpenBMB/XAgent repository metadata","date":"2026-06-11T03:20:43.962911+00:00","date_source":null,"source_url":"https://github.com/OpenBMB/XAgent","signal_url":null,"signal_json_url":null,"text":"# OpenBMB/XAgent\n\nDescription: An Autonomous LLM Agent for Complex Task Solving\n\nLanguage: Python\n\nLicense: Apache-2.0\n\nStars: 8529\n\nForks: 904\n\nOpen issues: 61\n\nCreated: 2023-10-16T03:44:57Z\n\nPushed: 2024-08-12T06:41:38Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n<div align= \"center\">\n<h1> <img src=\"assets/readme/xagent_logo.png\" height=40 align=\"texttop\">XAgent</h1>\n</div>\n\n<div align=\"center\">\n\n[![Twitter](https://img.shields.io/twitter/follow/XAgent?style=social)](https://twitter.com/XAgentTeam) [![Discord](https://img.shields.io/badge/XAgent-Discord-purple?style=flat)](https://discord.gg/zncs5aQkWZ) [![License: Apache 2.0](https://img.shields.io/badge/License-Apache_2.0-green.svg)](https://opensource.org/license/apache-2-0/) ![Welcome](https://img.shields.io/badge/contributions-welcome-brightgreen.svg?style=flat)\n\n</div>\n\n<p align=\"center\">\n<a>English</a> •\n<a href=\"README_ZH.md\">中文</a> •\n<a href=\"README_JA.md\">日本語</a>\n</p>\n\n<p align=\"center\">\n<a href=\"#quickstart\">Tutorial</a> •\n<a href=\"https://www.youtube.com/watch?v=QGkpd-tsFPA\">Demo</a> •\n<a href=\"https://blog.x-agent.net/blog/xagent/\">Blog</a> •\n<a href=\"https://xagent-doc.readthedocs.io/en/latest/\">Documentation</a> •\n<a href=\"#Citation\">Citation</a>\n</p>\n\n## 📖 Introduction\n\nXAgent is an open-source experimental Large Language Model (LLM) driven autonomous agent that can automatically solve various tasks. \nIt is designed to be a general-purpose agent that can be applied to a wide range of tasks. XAgent is still in its early stages, and we are working hard to improve it.\n\n🏆 Our goal is to create a super-intelligent agent that can solve any given task!\n\nWe welcome diverse forms of collaborations, including full-time and part-time roles and more. If you are interested in the frontiers of agents and want to join us in realizing true autonomous agents, please contact us at xagentteam@gmail.com.\n\n<div align=\"center\">\n<img src=\"assets/readme/overview.png\" alt=\"Overview of Xagent\" width=\"700\"/>\n<br/>\n<figcaption>Overview of XAgent.</figcaption>\n</div>\n\n### <img src=\"assets/readme/xagent_logo.png\" height=30 align=\"texttop\"> XAgent\n\nXAgent is designed with the following features:\n- **Autonomy**: "},{"ref":"P22","kind":"page","title":"OpenBMB/ProAgent repository metadata","date":"2026-06-11T03:20:43.890995+00:00","date_source":null,"source_url":"https://github.com/OpenBMB/ProAgent","signal_url":null,"signal_json_url":null,"text":"# OpenBMB/ProAgent\n\nDescription: An LLM-based Agent for the New Automation Paradigm - Agentic Process Automation\n\nLanguage: Python\n\nLicense: Apache-2.0\n\nStars: 864\n\nForks: 94\n\nOpen issues: 12\n\nCreated: 2023-11-03T01:20:14Z\n\nPushed: 2023-12-27T13:53:35Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n# ProAgent: From Robotic Process Automation to Agentic Process Automation\n\n<img src=\"./images/intro.png\">\n\nFrom water wheels to Robotic Process Automation (RPA), automation technology has evolved throughout history to liberate human beings from arduous tasks. Yet, RPA struggles with tasks needing human-like intelligence, especially in elaborate design of workflow construction and dynamic decision-making in workflow execution. As Large Language Models (LLMs) have emerged human-like intelligence, this paper introduces `Agentic Process Automation`(APA), a groundbreaking automation paradigm using LLM-based agents for advanced automation by offloading the human labor to agents associated with construction and execution. We then instantiate `ProAgent`, an LLM-based agent designed to craft workflows from human instructions and make intricate decisions by coordinating specialized agents. Empirical experiments are conducted to detail its construction and execution procedure of workflow, showcasing the feasibility of APA, unveiling the possibility of a new paradigm of automation driven by agents\n\n## <img src=\"./images/table.png\">\n\nAnd this is the official code of `Agentic Process Automation` paper, you can download our paper [here](https://arxiv.org/abs/2311.10751).\n\n## Code Setup\n\n### 1. Install packages\n\n```Shell\npip install -r requirements.txt\n```\n\nespecially, We use the OpenAI version before Dev Day, so you can't use the latest version of OpenAI \n\n### 2. Prepare for n8n\n\nOur projects use a self-host n8n, you can either prepare a n8n environment and connect ProAgent with a realworld APP service. \n\nOr you can load our record to re-produce the case reported in our paper **without** n8n environment\n\n> prepare a n8n service is not an eazy thing, you may face some problems or bug that we haven't encountered before, and you must handle the situation. For example, you may f"},{"ref":"P23","kind":"page","title":"OpenBMB/UltraEval repository metadata","date":"2026-06-11T03:20:43.770244+00:00","date_source":null,"source_url":"https://github.com/OpenBMB/UltraEval","signal_url":null,"signal_json_url":null,"text":"# OpenBMB/UltraEval\n\nDescription: [ACL 2024 Demo] Official GitHub repo for UltraEval: An open source framework for evaluating foundation models.\n\nLanguage: Python\n\nLicense: Apache-2.0\n\nStars: 258\n\nForks: 23\n\nOpen issues: 4\n\nCreated: 2023-11-15T12:43:28Z\n\nPushed: 2024-10-30T09:16:01Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n<div align=\"center\">\n<img src=\"docs/pics/ultraeval_logo_white.jpg\" width=\"500px\"/>\n<br />\n<br />\n<p align=\"center\">\n<a href=\"https://arxiv.org/abs/2404.07584\">📖Paper</a> •\n<a href=\"https://ultraeval.openbmb.cn/home\"> 🌐Website</a> •\n<a href=\"#Overview\">📖Overview</a> •\n<a href=\"#Quick start\">🔧Quick start</a> •\n<a href=\"docs/tutorials/en/ultraeval.md\">🛠️Tutorials</a> •\n<a href=\"README_zh.md\">中文</a> \n</p>\n</div>\n\n# Colab\n[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1hNXtaR3V-VgmG59QJMW7YPaAYgwtmyuH?usp=sharing)\n\nWe provide a Colab notebook to help you get started with UltraEval.\n\n# News!\n\n- \\[2024.6.4\\] **UltraEval** was accepted by ACL 2024 System Demonstration Track (SDT).🔥🔥🔥\n- \\[2024.4.11\\] We published the [UltraEval paper](https://arxiv.org/abs/2404.07584)🔥🔥🔥, and we welcome discussions and exchanges on this topic.\n- \\[2024.2.1\\] [MiniCPM](https://github.com/OpenBMB/MiniCPM) has been released🔥🔥🔥, using UltraEval as its evaluation framework!\n- \\[2023.11.23\\] We open sourced the UltraEval evaluation framework and published the first version of the list.🔥🔥🔥\n\n# Overview\nUltraEval is an open-source framework for evaluating the capabilities of foundation models, providing a suite of lightweight, easy-to-use evaluation systems that support the performance assessment of mainstream LLMs. \n\nUltraEval's overall workflow is as follows:\n<div align=\"center\">\n<p align=\"center\">\n<img src=\"docs/pics/ultraeval_pipeline_white.png\" width=\"800px\">\n</p>\n</div>\n\nIts main features are as follows:\n1. **Lightweight and Easy-to-use Evaluation Framework:** Seamlessly designed with an intuitive interface, minimal dependencies, effortless deployment, excellent scalability, adaptable to diverse evaluation scenarios.\n\n2. **Flexible and Diverse Evaluation Methods:** Support"},{"ref":"P24","kind":"page","title":"OpenBMB/InfiniteBench repository metadata","date":"2026-06-11T03:20:43.424248+00:00","date_source":null,"source_url":"https://github.com/OpenBMB/InfiniteBench","signal_url":null,"signal_json_url":null,"text":"# OpenBMB/InfiniteBench\n\nDescription: Codes for the paper \"∞Bench: Extending Long Context Evaluation Beyond 100K Tokens\": https://arxiv.org/abs/2402.13718\n\nLanguage: Python\n\nLicense: MIT\n\nStars: 386\n\nForks: 33\n\nOpen issues: 10\n\nCreated: 2023-11-22T12:05:56Z\n\nPushed: 2024-09-25T20:06:30Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n<div align=\"center\">\n<img src=\"figs/InfiniteBench.jpg\" width=\"500px\"/>\n<br />\n<br />\n\n# InfiniteBench: Extending Long Context Evaluation Beyond 100K Tokens\n\n<p align=\"center\">\n<a href=\"./README_ZH.md\">中文</a> •\n<a href=\"./README.md\">English</a> •\n<a href=\"https://arxiv.org/abs/2402.13718\">Paper</a>\n</p>\n\n</div>\n\n## Introduction\n\nWelcome to InfiniteBench, a cutting-edge benchmark tailored for evaluating the capabilities of language models to process, understand, and reason over super long contexts (100k+ tokens). Long contexts are crucial for enhancing applications with LLMs and achieving high-level interaction. InfiniteBench is designed to push the boundaries of language models by testing them against a context length of 100k+, which is 10 times longer than traditional datasets.\n\n## Features\n\n- **Loooong Context:** InfiniteBench is a pioneer in testing language models with a context length of 100k+, offering an unparalleled challenge in the field.\n- **Diverse Domain:** The benchmark comprises 12 unique tasks, each crafted to assess different aspects of language processing and comprehension in extended contexts.\n- **Specialized Test:** InfiniteBench consists of tasks that state-of-the-art LLMs are known to be capable of when using shorter context. This ensures that the performance degradation is only caused by the length of the contexts.\n- **Real-World and Synthetic Scenarios:** The tasks are a mix of real-world scenarios and synthetic constructs, ensuring a comprehensive evaluation of models. Real-world scenarios make the test pragmatic, and synthetic ones leave the space for extending the context length further with ease.\n\n## Task Composition\n\n<div align=\"center\">\n<img src=\"figs/data_pie.png\" width=\"480px\">\n</div>\n\n| Task Name | Context | # Examples | Avg Input Tokens | Avg Output Tokens | Description |\n| --------------------"},{"ref":"P25","kind":"page","title":"OpenBMB/MiniCPM-V repository metadata","date":"2026-06-11T03:20:43.171622+00:00","date_source":null,"source_url":"https://github.com/OpenBMB/MiniCPM-V","signal_url":null,"signal_json_url":null,"text":"# OpenBMB/MiniCPM-V\n\nDescription: A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone\n\nLanguage: Python\n\nLicense: Apache-2.0\n\nStars: 25582\n\nForks: 2006\n\nOpen issues: 52\n\nCreated: 2024-01-29T05:30:33Z\n\nPushed: 2026-06-04T10:01:45Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n<div align=\"center\">\n\n<img src=\"./assets/minicpm_v_and_minicpm_o_title.png\" width=\"500em\" ></img> \n\n**A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone**\n\n<strong>[中文](./README_zh.md) |\nEnglish</strong>\n\n<span style=\"display: inline-flex; align-items: center; margin-right: 2px;\">\n<img src=\"./assets/feishu_logo.png\" alt=\"feishu\" width=\"15\" height=\"15\" style=\"margin-right: 4px;\">\n<a href=\"./assets/feishu_qrcode.png\" target=\"_blank\"> Feishu (Lark)</a> &nbsp;|\n</span>\n&nbsp;\n<span style=\"display: inline-flex; align-items: center; margin-left: -8px;\">\n<img src=\"./assets/discord.png\" alt=\"Discord\" style=\"margin-right: 4px;\">\n<a href=\"https://discord.gg/pBZuTA3hj\" target=\"_blank\"> Discord</a> &nbsp;\n</span>\n\n<p align=\"center\">\nMiniCPM-V 4.6 <a href=\"https://huggingface.co/openbmb/MiniCPM-V-4.6\">🤗</a> <a href=\"https://huggingface.co/spaces/openbmb/MiniCPM-V-4.6-Demo\">🤖</a> <a href=\"https://github.com/OpenBMB/MiniCPM-V-Apps/blob/main/DOWNLOAD.md\">📱</a> | MiniCPM-o 4.5 <a href=\"https://huggingface.co/openbmb/MiniCPM-o-4_5\">🤗</a> <a href=\"https://openbmb.github.io/MiniCPM-o-Demo/\">📞</a> <a href=\"https://minicpmo45.modelbest.cn\">🤖</a> | <a href=\"https://huggingface.co/papers/2604.27393\">📄 Technical Report</a> | <a href=\"https://github.com/OpenSQZ/MiniCPM-V-Cookbook\">🍳 Cookbook</a> | <a href=\"./docs/api.md\">🌐 API</a>\n</p>\n\n</div>\n\n**MiniCPM-V** and **MiniCPM-o** are multimodal LLM series designed for **strong performance and efficient deployment on devices**. MiniCPM-V focuses on efficient vision-language understanding across image, video and text inputs. MiniCPM-o extends the family toward real-time end-to-end omnimodal interaction with streaming video and audio inputs plus text and speech outputs. The most notable models in the series currently include:\n\n- **MiniCPM-V 4.6**: 🔥🔥🔥 The latest and most efficient model in"},{"ref":"P26","kind":"page","title":"OpenBMB/MiniCPM repository metadata","date":"2026-06-11T03:20:43.127997+00:00","date_source":null,"source_url":"https://github.com/OpenBMB/MiniCPM","signal_url":null,"signal_json_url":null,"text":"# OpenBMB/MiniCPM\n\nDescription: MiniCPM5-1B: A SOTA 1B on-device LLM, small yet powerful.\n\nLanguage: Jupyter Notebook\n\nLicense: Apache-2.0\n\nStars: 9421\n\nForks: 620\n\nOpen issues: 18\n\nCreated: 2024-01-29T08:21:15Z\n\nPushed: 2026-05-31T09:32:22Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n<div align=\"center\">\n<img src=\"./assets/minicpm_logo.png\" width=\"500em\" ></img> \n</div>\n\n<h4 align=\"center\">\n<p>\n<a href=\"https://github.com/OpenBMB/MiniCPM/blob/minicpm5/README-cn.md\">中文</a> | <b>English</b>\n<p>\n</h4>\n\n<p align=\"center\">\n<a href=\"https://arxiv.org/pdf/2506.07900\" target=\"_blank\">MiniCPM Tech Report</a> |\n<a href=\"https://modelbest.feishu.cn/wiki/D2tFw8Pcsi5CIzkaHNacLK64npg\" target=\"_blank\">MiniCPM Wiki (in Chinese)</a> |\n<a href=\"https://github.com/OpenBMB/MiniCPM-V/\" target=\"_blank\">MiniCPM-V Repo</a> |\n<a href=\"https://ultradata.openbmb.cn/\" target=\"_blank\">UltraData</a>\n</p>\n\n<p align=\"center\">\nJoin our <a href=\"https://discord.gg/3cGQn9b3YM\" target=\"_blank\">discord</a> and <a href=\"https://applink.feishu.cn/client/chat/chatter/add_by_link?link_token=559o65ab-9086-442a-96c9-cf382e80b22d\" target=\"_blank\">Feishu/Lark</a> |\n<a href=\"https://mp.weixin.qq.com/s/KIhH2nCURBXuFXAtYRpuXg?poc_token=HBIsUWijxino8oJ5s6HcjcfXFRi0Xj2LJlxPYD9c\">Join Us</a>\n</p>\n\n> [!NOTE]\n> ### 🏆 2026 Sparse Operator Acceleration & Race (SOAR) is Now Live!\n>\n> **The MiniCPM-SALA architecture is just the beginning. Realizing its full potential requires deep system-level synergy and cross-layer compilation optimization.**\n>\n> OpenBMB, in collaboration with **SGLang** and **NVIDIA**, invites global geeks to tackle the limits of **9B-scale, 1M-token inference** on a dedicated **NVIDIA 6000D** environment.\n>\n> * 💰 **Prize Pool:** >$100,000 USD (Top Prize: **$89,000**)\n> * 🚀 **Goal:** Optimize single and multi-batch performance via cross-layer compilation.\n>\n> 👉 **[Learn more and Register](https://soar.openbmb.cn/)**\n\n## ✨ Highlights\n\nWe are releasing **MiniCPM5-1B**, the first model in the **MiniCPM5** series. It is a dense 1B Transformer built for on-device, local deployment, and resource-constrained scenarios, reaching 1B-class open-source SOTA.\n\n🏆 **1B-class open-source SOTA**: "},{"ref":"P27","kind":"page","title":"OpenBMB/RepoAgent repository metadata","date":"2026-06-11T03:20:43.109928+00:00","date_source":null,"source_url":"https://github.com/OpenBMB/RepoAgent","signal_url":null,"signal_json_url":null,"text":"# OpenBMB/RepoAgent\n\nDescription: An LLM-powered repository agent designed to assist developers and teams in generating documentation and understanding repositories quickly.\n\nLanguage: Python\n\nLicense: Apache-2.0\n\nStars: 983\n\nForks: 139\n\nOpen issues: 11\n\nCreated: 2023-11-28T10:41:28Z\n\nPushed: 2024-12-23T11:48:52Z\n\nDefault branch: main\n\nFork: no\n\nArchived: no\n\nREADME:\n<h1 align=\"center\">\n<img src=\"https://github.com/OpenBMB/RepoAgent/assets/138990495/06bc2449-c82d-4b9e-8c83-27640e541451\" width=\"50\" alt=\"RepoAgent logo\"/> <em>RepoAgent: An LLM-Powered Framework for Repository-level Code Documentation Generation.</em>\n</h1>\n\n<p align=\"center\">\n<img src=\"https://img.shields.io/pypi/dm/repoagent\" alt=\"PyPI - Downloads\"/>\n<a href=\"https://pypi.org/project/repoagent/\">\n<img src=\"https://img.shields.io/pypi/v/repoagent\" alt=\"PyPI - Version\"/>\n</a>\n<a href=\"Pypi\">\n<img src=\"https://img.shields.io/pypi/pyversions/repoagent\" alt=\"PyPI - Python Version\"/>\n</a>\n<img alt=\"GitHub License\" src=\"https://img.shields.io/github/license/LOGIC-10/RepoAgent\">\n<img alt=\"GitHub Repo stars\" src=\"https://img.shields.io/github/stars/LOGIC-10/RepoAgent?style=social\">\n<img alt=\"GitHub issues\" src=\"https://img.shields.io/github/issues/LOGIC-10/RepoAgent\">\n<a href=\"https://arxiv.org/abs/2402.16667v1\">\n<img src=\"https://img.shields.io/badge/cs.CL-2402.16667-b31b1b?logo=arxiv&logoColor=red\" alt=\"arXiv\"/>\n</a>\n</p>\n\n<p align=\"center\">\n<img src=\"https://raw.githubusercontent.com/OpenBMB/RepoAgent/main/assets/images/RepoAgent.png\" alt=\"RepoAgent\"/>\n</p>\n\n<p align=\"center\">\n<a href=\"https://github.com/LOGIC-10/RepoAgent/blob/main/README.md\">English readme</a>\n• \n<a href=\"https://github.com/LOGIC-10/RepoAgent/blob/main/README_CN.md\">简体中文 readme</a>\n</p>\n\n## :tv: Demo\n\n[![Watch the video](https://img.youtube.com/vi/YPPJBVOP71M/hqdefault.jpg)](https://youtu.be/YPPJBVOP71M)\n\n## 👾 Background\n\nIn the realm of computer programming, the significance of comprehensive project documentation, including detailed explanations for each Python file, cannot be overstated. Such documentation serves as the cornerstone for understanding, maintaining, and enhancing the codebase. It provides essential context and ration"},{"ref":"P28","kind":"page","title":"OpenBMB/Tell_Me_More repository metadata","date":"2026-06-11T03:20:42.95503+00:00","date_source":null,"source_url":"https://github.com/OpenBMB/Tell_Me_More","signal_url":null,"signal_json_url":null,"text":"# OpenBMB/Tell_Me_More\n\nDescription: Repo for paper \"Tell Me More! Towards Implicit User Intention Understanding of Language Model Driven Agents\"\n\nLanguage: Python\n\nLicense: Apache-2.0\n\nStars: 66\n\nForks: 9\n\nOpen issues: 1\n\nCreated: 2024-02-01T15:10:26Z\n\nPushed: 2024-02-20T03:28:31Z\n\nDefault branch: master\n\nFork: no\n\nArchived: no\n\nREADME:\n<div align=\"center\">\n<h1> <img src=\"figures/agent.png\" height=50 align=\"texttop\"> Tell Me More!</h1>\n</div>\n\n<p align=\"center\">\n<a target=\"_blank\">\n<img src=\"https://img.shields.io/badge/License-Apache_2.0-green.svg\">\n</a>\n<a target=\"_blank\">\n<img alt=\"GitHub\" src=\"https://img.shields.io/badge/contributions-welcome-brightgreen.svg?style=flat\">\n</a>\n</p>\n\n<p align=\"center\">\n<a href=\"#features\">Features</a> •\n<a href=\"#training\">Training</a> •\n<a href=\"#Evaluation\">Evaluation</a> •\n<a href=\"#Citation\">Citation</a>\n</p>\n\nThe repo is for the implementation and evaluation of Mistral-Interact, a powerful model that proactively assesses task vagueness, inquires user intentions, and refines them into actionable goals before starting downstream agent task execution.\n\nSource codes and datasets for **[Tell Me More! Towards Implicit User Intention Understanding of Language Model Driven Agents](https://arxiv.org/abs/2402.09205)**. We release Intention-in-Interaction (IN3) benchmark and develop Mistral-Interact, capable of discerning vague instructions and recovering missing details.\n\n## ✨ Features\n\nMistral-Interact has the following features:\n\n- **Better understanding of user judgments:** Among all the open-source models, Mistral-Interact is the best at predicting task vagueness and missing details that users regard as necessary.\n- **Comprehensive summarization of user intentions:** Mistral-Interact is effective in making an explicit and comprehensive summary based on detailed user intentions.\n\n- **Enhanced model-user interaction experience:** Mistral-Interact inquires about missing details in vague tasks more reasonably and friendly than other open-source models, thus promoting a clearer understanding of the user’s implicit intentions.\n\n- **Comparable performance with closed-source GPT-4:** We prove that smaller-scale model experts can appr"},{"ref":"E1","kind":"event","title":"openbmb/VoxCPM2","date":"2026-04-03T05:25:50+00:00","date_source":"source","source_url":"https://huggingface.co/openbmb/VoxCPM2","signal_url":"https://onlylabs.fyi/signals/e27d2b9f-564b-457b-8a60-7d0399444617","signal_json_url":"https://onlylabs.fyi/signals/e27d2b9f-564b-457b-8a60-7d0399444617/signal.json","text":"model_released · openbmb/VoxCPM2 · signal_desk=releases · occurred_at=2026-04-03T05:25:50+00:00 · url=https://huggingface.co/openbmb/VoxCPM2 · hf_downloads=262677 · hf_likes=1382 · hf_params=2290004544 · pipeline=text-to-speech · license=apache-2.0"},{"ref":"E2","kind":"event","title":"openbmb/MiniCPM-V-4.6","date":"2026-04-13T09:12:47+00:00","date_source":"source","source_url":"https://huggingface.co/openbmb/MiniCPM-V-4.6","signal_url":"https://onlylabs.fyi/signals/8b45bdaf-793a-45ba-af30-efa53cb69e1d","signal_json_url":"https://onlylabs.fyi/signals/8b45bdaf-793a-45ba-af30-efa53cb69e1d/signal.json","text":"model_released · openbmb/MiniCPM-V-4.6 · signal_desk=releases · occurred_at=2026-04-13T09:12:47+00:00 · url=https://huggingface.co/openbmb/MiniCPM-V-4.6 · hf_downloads=615509 · hf_likes=1106 · hf_params=1300428016 · pipeline=image-text-to-text · license=apache-2.0"},{"ref":"E3","kind":"event","title":"openbmb/MiniCPM-V-4_5","date":"2025-08-24T10:39:55+00:00","date_source":"source","source_url":"https://huggingface.co/openbmb/MiniCPM-V-4_5","signal_url":"https://onlylabs.fyi/signals/6ed44841-273d-46b8-bdd8-a83af5ba43e1","signal_json_url":"https://onlylabs.fyi/signals/6ed44841-273d-46b8-bdd8-a83af5ba43e1/signal.json","text":"model_released · openbmb/MiniCPM-V-4_5 · signal_desk=releases · occurred_at=2025-08-24T10:39:55+00:00 · url=https://huggingface.co/openbmb/MiniCPM-V-4_5 · hf_downloads=93355 · hf_likes=1093 · hf_params=8695895280 · pipeline=image-text-to-text · license=apache-2.0"},{"ref":"E4","kind":"event","title":"openbmb/MiniCPM5-1B","date":"2026-05-21T07:27:59+00:00","date_source":"source","source_url":"https://huggingface.co/openbmb/MiniCPM5-1B","signal_url":"https://onlylabs.fyi/signals/6c09972b-77c4-4e2d-b9b7-d5e9ae5fb41c","signal_json_url":"https://onlylabs.fyi/signals/6c09972b-77c4-4e2d-b9b7-d5e9ae5fb41c/signal.json","text":"model_released · openbmb/MiniCPM5-1B · signal_desk=releases · occurred_at=2026-05-21T07:27:59+00:00 · url=https://huggingface.co/openbmb/MiniCPM5-1B · hf_downloads=137337 · hf_likes=795 · hf_params=1080632832 · pipeline=text-generation · license=apache-2.0"},{"ref":"E5","kind":"event","title":"openbmb/VoxCPM-0.5B","date":"2025-09-16T06:56:48+00:00","date_source":"source","source_url":"https://huggingface.co/openbmb/VoxCPM-0.5B","signal_url":"https://onlylabs.fyi/signals/790da5e1-2b2f-4765-a8fc-7ad0c1891ba2","signal_json_url":"https://onlylabs.fyi/signals/790da5e1-2b2f-4765-a8fc-7ad0c1891ba2/signal.json","text":"model_released · openbmb/VoxCPM-0.5B · signal_desk=releases · occurred_at=2025-09-16T06:56:48+00:00 · url=https://huggingface.co/openbmb/VoxCPM-0.5B · hf_downloads=7115 · hf_likes=803 · pipeline=text-to-speech · license=apache-2.0 · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E6","kind":"event","title":"openbmb/MiniCPM-SALA","date":"2026-02-11T07:03:05+00:00","date_source":"source","source_url":"https://huggingface.co/openbmb/MiniCPM-SALA","signal_url":"https://onlylabs.fyi/signals/c8b91f2c-aaa2-441e-b1ff-e445fa2b85f2","signal_json_url":"https://onlylabs.fyi/signals/c8b91f2c-aaa2-441e-b1ff-e445fa2b85f2/signal.json","text":"model_released · openbmb/MiniCPM-SALA · signal_desk=releases · occurred_at=2026-02-11T07:03:05+00:00 · url=https://huggingface.co/openbmb/MiniCPM-SALA · hf_downloads=6328 · hf_likes=682 · hf_params=9477203968 · pipeline=text-generation · license=apache-2.0"},{"ref":"E7","kind":"event","title":"openbmb/MiniCPM-V-4","date":"2025-07-12T11:08:49+00:00","date_source":"source","source_url":"https://huggingface.co/openbmb/MiniCPM-V-4","signal_url":"https://onlylabs.fyi/signals/a0c68d50-ca11-4f57-81f1-29b08b49b75c","signal_json_url":"https://onlylabs.fyi/signals/a0c68d50-ca11-4f57-81f1-29b08b49b75c/signal.json","text":"model_released · openbmb/MiniCPM-V-4 · signal_desk=releases · occurred_at=2025-07-12T11:08:49+00:00 · url=https://huggingface.co/openbmb/MiniCPM-V-4 · hf_downloads=231582 · hf_likes=465 · hf_params=4059533040 · pipeline=image-text-to-text · license=apache-2.0"},{"ref":"E8","kind":"event","title":"openbmb/AgentCPM-Explore","date":"2026-01-11T07:17:50+00:00","date_source":"source","source_url":"https://huggingface.co/openbmb/AgentCPM-Explore","signal_url":"https://onlylabs.fyi/signals/c823ff51-1c70-4e68-be19-1557cb5edac8","signal_json_url":"https://onlylabs.fyi/signals/c823ff51-1c70-4e68-be19-1557cb5edac8/signal.json","text":"model_released · openbmb/AgentCPM-Explore · signal_desk=releases · occurred_at=2026-01-11T07:17:50+00:00 · url=https://huggingface.co/openbmb/AgentCPM-Explore · hf_downloads=871 · hf_likes=415 · hf_params=4022468096 · pipeline=text-generation · license=apache-2.0 · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E9","kind":"event","title":"openbmb/MiniCPM4.1-8B","date":"2025-09-02T07:14:25+00:00","date_source":"source","source_url":"https://huggingface.co/openbmb/MiniCPM4.1-8B","signal_url":"https://onlylabs.fyi/signals/c4bfb833-4edd-44c7-9f44-85ca6ea2a81b","signal_json_url":"https://onlylabs.fyi/signals/c4bfb833-4edd-44c7-9f44-85ca6ea2a81b/signal.json","text":"model_released · openbmb/MiniCPM4.1-8B · signal_desk=releases · occurred_at=2025-09-02T07:14:25+00:00 · url=https://huggingface.co/openbmb/MiniCPM4.1-8B · hf_downloads=49977 · hf_likes=389 · hf_params=8185253888 · pipeline=text-generation · license=apache-2.0"},{"ref":"E10","kind":"event","title":"openbmb/VoxCPM1.5","date":"2025-12-05T09:58:12+00:00","date_source":"source","source_url":"https://huggingface.co/openbmb/VoxCPM1.5","signal_url":"https://onlylabs.fyi/signals/5ba9b4a2-2275-4626-983d-8e8ce2c8b78b","signal_json_url":"https://onlylabs.fyi/signals/5ba9b4a2-2275-4626-983d-8e8ce2c8b78b/signal.json","text":"model_released · openbmb/VoxCPM1.5 · signal_desk=releases · occurred_at=2025-12-05T09:58:12+00:00 · url=https://huggingface.co/openbmb/VoxCPM1.5 · hf_downloads=10626 · hf_likes=362 · hf_params=801729856 · pipeline=text-to-speech · license=apache-2.0 · raw={\"derived_reason\":\"first-party-finetune\"}"},{"ref":"E11","kind":"event","title":"openbmb/AgentCPM-Report","date":"2026-01-19T03:47:39+00:00","date_source":"source","source_url":"https://huggingface.co/openbmb/AgentCPM-Report","signal_url":"https://onlylabs.fyi/signals/c87c279d-d4ec-4978-8d81-f03d4fa6394b","signal_json_url":"https://onlylabs.fyi/signals/c87c279d-d4ec-4978-8d81-f03d4fa6394b/signal.json","text":"model_released · openbmb/AgentCPM-Report · signal_desk=releases · occurred_at=2026-01-19T03:47:39+00:00 · url=https://huggingface.co/openbmb/AgentCPM-Report · hf_downloads=797 · hf_likes=300 · hf_params=8185253888 · pipeline=text-generation · license=apache-2.0"},{"ref":"E12","kind":"event","title":"OpenBMB/VoxCPM","date":"2025-09-16T03:41:49+00:00","date_source":"source","source_url":"https://github.com/OpenBMB/VoxCPM","signal_url":"https://onlylabs.fyi/signals/bb5cc230-5881-44ad-a7a6-c9e865d262e3","signal_json_url":"https://onlylabs.fyi/signals/bb5cc230-5881-44ad-a7a6-c9e865d262e3/signal.json","text":"repo_new · OpenBMB/VoxCPM · signal_desk=repos · occurred_at=2025-09-16T03:41:49+00:00 · url=https://github.com/OpenBMB/VoxCPM · stars=28343 · hn=3 points/0 comments · raw={\"repo\":\"OpenBMB/VoxCPM\",\"description\":\"VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning\",\"language\":\"Python\"}"},{"ref":"E13","kind":"event","title":"OpenBMB/MiniCPM-V","date":"2024-01-29T05:30:33+00:00","date_source":"source","source_url":"https://github.com/OpenBMB/MiniCPM-V","signal_url":"https://onlylabs.fyi/signals/1eba2185-99f0-4dfe-b9ed-4508c0725c0f","signal_json_url":"https://onlylabs.fyi/signals/1eba2185-99f0-4dfe-b9ed-4508c0725c0f/signal.json","text":"repo_new · OpenBMB/MiniCPM-V · signal_desk=repos · occurred_at=2024-01-29T05:30:33+00:00 · url=https://github.com/OpenBMB/MiniCPM-V · stars=25585 · hn=3 points/1 comments · raw={\"repo\":\"OpenBMB/MiniCPM-V\",\"description\":\"A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone\",\"language\":\"Python\"}"},{"ref":"E14","kind":"event","title":"openbmb/BitCPM-CANN-8B","date":"2026-05-15T13:10:51+00:00","date_source":"source","source_url":"https://huggingface.co/openbmb/BitCPM-CANN-8B","signal_url":"https://onlylabs.fyi/signals/f4e5206e-b33e-4729-8735-5fd3473add55","signal_json_url":"https://onlylabs.fyi/signals/f4e5206e-b33e-4729-8735-5fd3473add55/signal.json","text":"model_released · openbmb/BitCPM-CANN-8B · signal_desk=releases · occurred_at=2026-05-15T13:10:51+00:00 · url=https://huggingface.co/openbmb/BitCPM-CANN-8B · hf_downloads=7165 · hf_likes=100 · pipeline=text-generation · license=apache-2.0"},{"ref":"E15","kind":"event","title":"openbmb/MiniCPM5-1B-SFT","date":"2026-05-21T07:27:50+00:00","date_source":"source","source_url":"https://huggingface.co/openbmb/MiniCPM5-1B-SFT","signal_url":"https://onlylabs.fyi/signals/22cee439-4f56-4eee-b821-779f63f837c3","signal_json_url":"https://onlylabs.fyi/signals/22cee439-4f56-4eee-b821-779f63f837c3/signal.json","text":"model_released · openbmb/MiniCPM5-1B-SFT · signal_desk=releases · occurred_at=2026-05-21T07:27:50+00:00 · url=https://huggingface.co/openbmb/MiniCPM5-1B-SFT · hf_downloads=12424 · hf_likes=26 · hf_params=1080632832 · pipeline=text-generation · license=apache-2.0"},{"ref":"E16","kind":"event","title":"openbmb/MiniCPM-V-4.6-Thinking","date":"2026-05-08T12:05:34+00:00","date_source":"source","source_url":"https://huggingface.co/openbmb/MiniCPM-V-4.6-Thinking","signal_url":"https://onlylabs.fyi/signals/b5fbc3f0-a3da-49ba-a042-261d8dcfd6d2","signal_json_url":"https://onlylabs.fyi/signals/b5fbc3f0-a3da-49ba-a042-261d8dcfd6d2/signal.json","text":"model_released · openbmb/MiniCPM-V-4.6-Thinking · signal_desk=releases · occurred_at=2026-05-08T12:05:34+00:00 · url=https://huggingface.co/openbmb/MiniCPM-V-4.6-Thinking · hf_downloads=66271 · hf_likes=26 · hf_params=1300428016 · pipeline=image-text-to-text · license=apache-2.0"},{"ref":"E17","kind":"event","title":"OpenBMB/PilotDeck","date":"2026-05-22T06:50:28+00:00","date_source":"source","source_url":"https://github.com/OpenBMB/PilotDeck","signal_url":"https://onlylabs.fyi/signals/09fa79c2-c357-4b35-9137-3382d7b781fe","signal_json_url":"https://onlylabs.fyi/signals/09fa79c2-c357-4b35-9137-3382d7b781fe/signal.json","text":"repo_new · OpenBMB/PilotDeck · signal_desk=repos · occurred_at=2026-05-22T06:50:28+00:00 · url=https://github.com/OpenBMB/PilotDeck · stars=3140 · raw={\"repo\":\"OpenBMB/PilotDeck\",\"description\":\"Task-oriented AI Agent productivity platform\",\"language\":\"TypeScript\"}"},{"ref":"E18","kind":"event","title":"openbmb/SciCore-Omics","date":"2026-06-03T09:49:00+00:00","date_source":"source","source_url":"https://huggingface.co/openbmb/SciCore-Omics","signal_url":"https://onlylabs.fyi/signals/12094dec-3678-49ff-9a67-357cd2c648f4","signal_json_url":"https://onlylabs.fyi/signals/12094dec-3678-49ff-9a67-357cd2c648f4/signal.json","text":"model_released · openbmb/SciCore-Omics · signal_desk=releases · occurred_at=2026-06-03T09:49:00+00:00 · url=https://huggingface.co/openbmb/SciCore-Omics · hf_downloads=238 · hf_likes=8 · hf_params=8191537648 · pipeline=image-feature-extraction · license=apache-2.0"},{"ref":"E19","kind":"event","title":"OpenBMB/XAgent","date":"2023-10-16T03:44:57+00:00","date_source":"source","source_url":"https://github.com/OpenBMB/XAgent","signal_url":"https://onlylabs.fyi/signals/054e7c95-7849-4c59-a0a9-ddc9f4bdd072","signal_json_url":"https://onlylabs.fyi/signals/054e7c95-7849-4c59-a0a9-ddc9f4bdd072/signal.json","text":"repo_new · OpenBMB/XAgent · signal_desk=repos · occurred_at=2023-10-16T03:44:57+00:00 · url=https://github.com/OpenBMB/XAgent · stars=8529 · hn=1 points/0 comments · raw={\"repo\":\"OpenBMB/XAgent\",\"description\":\"An Autonomous LLM Agent for Complex Task Solving\",\"language\":\"Python\"}"},{"ref":"E20","kind":"event","title":"OpenBMB/MiniCPM","date":"2024-01-29T08:21:15+00:00","date_source":"source","source_url":"https://github.com/OpenBMB/MiniCPM","signal_url":"https://onlylabs.fyi/signals/2e4b4a77-8768-4098-a8ec-fbd48eb0f7fd","signal_json_url":"https://onlylabs.fyi/signals/2e4b4a77-8768-4098-a8ec-fbd48eb0f7fd/signal.json","text":"repo_new · OpenBMB/MiniCPM · signal_desk=repos · occurred_at=2024-01-29T08:21:15+00:00 · url=https://github.com/OpenBMB/MiniCPM · stars=9422 · raw={\"repo\":\"OpenBMB/MiniCPM\",\"description\":\"MiniCPM5-1B: A SOTA 1B on-device LLM, small yet powerful.\",\"language\":\"Jupyter Notebook\"}"},{"ref":"E21","kind":"event","title":"OpenBMB/PilotDeck v0.1.0","date":"2026-06-10T09:08:12+00:00","date_source":"source","source_url":"https://github.com/OpenBMB/PilotDeck/releases/tag/v0.1.0","signal_url":"https://onlylabs.fyi/signals/79b99986-f963-41ef-8c1c-e0aade1e6fe6","signal_json_url":"https://onlylabs.fyi/signals/79b99986-f963-41ef-8c1c-e0aade1e6fe6/signal.json","text":"release · OpenBMB/PilotDeck v0.1.0 · signal_desk=releases · occurred_at=2026-06-10T09:08:12+00:00 · url=https://github.com/OpenBMB/PilotDeck/releases/tag/v0.1.0 · raw={\"repo\":\"OpenBMB/PilotDeck\"}"},{"ref":"E22","kind":"event","title":"OpenBMB/AceBench","date":"2026-06-07T07:34:14+00:00","date_source":"source","source_url":"https://github.com/OpenBMB/AceBench","signal_url":"https://onlylabs.fyi/signals/f409d6eb-9f25-4cb4-8684-3c0300d920cb","signal_json_url":"https://onlylabs.fyi/signals/f409d6eb-9f25-4cb4-8684-3c0300d920cb/signal.json","text":"repo_new · OpenBMB/AceBench · signal_desk=repos · occurred_at=2026-06-07T07:34:14+00:00 · url=https://github.com/OpenBMB/AceBench · stars=5 · raw={\"repo\":\"OpenBMB/AceBench\",\"language\":\"Python\"}"},{"ref":"E23","kind":"event","title":"OpenBMB/MiniCPM-V-Apps v2.3","date":"2026-06-05T16:35:31+00:00","date_source":"source","source_url":"https://github.com/OpenBMB/MiniCPM-V-Apps/releases/tag/v2.3","signal_url":"https://onlylabs.fyi/signals/6145f786-64e7-4466-9a37-e59cdcba6830","signal_json_url":"https://onlylabs.fyi/signals/6145f786-64e7-4466-9a37-e59cdcba6830/signal.json","text":"release · OpenBMB/MiniCPM-V-Apps v2.3 · signal_desk=releases · occurred_at=2026-06-05T16:35:31+00:00 · url=https://github.com/OpenBMB/MiniCPM-V-Apps/releases/tag/v2.3 · raw={\"repo\":\"OpenBMB/MiniCPM-V-Apps\"}"},{"ref":"E24","kind":"event","title":"openbmb/BitCPM-CANN-3B","date":"2026-05-15T13:10:02+00:00","date_source":"source","source_url":"https://huggingface.co/openbmb/BitCPM-CANN-3B","signal_url":"https://onlylabs.fyi/signals/efbcdec8-7d82-4904-b8ab-3ebf6616d1f3","signal_json_url":"https://onlylabs.fyi/signals/efbcdec8-7d82-4904-b8ab-3ebf6616d1f3/signal.json","text":"model_released · openbmb/BitCPM-CANN-3B · signal_desk=releases · occurred_at=2026-05-15T13:10:02+00:00 · url=https://huggingface.co/openbmb/BitCPM-CANN-3B · hf_downloads=6535 · hf_likes=10 · pipeline=text-generation · license=apache-2.0"},{"ref":"E25","kind":"event","title":"openbmb/BitCPM-CANN-0.5B","date":"2026-05-15T13:09:11+00:00","date_source":"source","source_url":"https://huggingface.co/openbmb/BitCPM-CANN-0.5B","signal_url":"https://onlylabs.fyi/signals/4b8005db-af0d-4d50-87fa-806c4e74aec1","signal_json_url":"https://onlylabs.fyi/signals/4b8005db-af0d-4d50-87fa-806c4e74aec1/signal.json","text":"model_released · openbmb/BitCPM-CANN-0.5B · signal_desk=releases · occurred_at=2026-05-15T13:09:11+00:00 · url=https://huggingface.co/openbmb/BitCPM-CANN-0.5B · hf_downloads=6410 · hf_likes=9 · pipeline=text-generation · license=apache-2.0"},{"ref":"E26","kind":"event","title":"openbmb/BitCPM-CANN-1B","date":"2026-05-15T13:09:42+00:00","date_source":"source","source_url":"https://huggingface.co/openbmb/BitCPM-CANN-1B","signal_url":"https://onlylabs.fyi/signals/bd1f3842-2d3f-4a5e-8ef8-fa7fcdc6e1ca","signal_json_url":"https://onlylabs.fyi/signals/bd1f3842-2d3f-4a5e-8ef8-fa7fcdc6e1ca/signal.json","text":"model_released · openbmb/BitCPM-CANN-1B · signal_desk=releases · occurred_at=2026-05-15T13:09:42+00:00 · url=https://huggingface.co/openbmb/BitCPM-CANN-1B · hf_downloads=5803 · hf_likes=8 · pipeline=text-generation · license=apache-2.0"},{"ref":"E27","kind":"event","title":"OpenBMB/MiniCPM-Desk-Pet v0.7.3","date":"2026-05-28T14:08:06+00:00","date_source":"source","source_url":"https://github.com/OpenBMB/MiniCPM-Desk-Pet/releases/tag/v0.7.3","signal_url":"https://onlylabs.fyi/signals/13452602-0185-43f4-bd92-c1a3a624da64","signal_json_url":"https://onlylabs.fyi/signals/13452602-0185-43f4-bd92-c1a3a624da64/signal.json","text":"release · OpenBMB/MiniCPM-Desk-Pet v0.7.3 · signal_desk=releases · occurred_at=2026-05-28T14:08:06+00:00 · url=https://github.com/OpenBMB/MiniCPM-Desk-Pet/releases/tag/v0.7.3 · raw={\"repo\":\"OpenBMB/MiniCPM-Desk-Pet\"}"},{"ref":"E28","kind":"event","title":"OpenBMB/MiniCPM-Desk-Pet v0.7.2","date":"2026-05-26T14:55:28+00:00","date_source":"source","source_url":"https://github.com/OpenBMB/MiniCPM-Desk-Pet/releases/tag/v0.7.2","signal_url":"https://onlylabs.fyi/signals/3916a112-1c5b-4fbd-9e87-bc44f2504103","signal_json_url":"https://onlylabs.fyi/signals/3916a112-1c5b-4fbd-9e87-bc44f2504103/signal.json","text":"release · OpenBMB/MiniCPM-Desk-Pet v0.7.2 · signal_desk=releases · occurred_at=2026-05-26T14:55:28+00:00 · url=https://github.com/OpenBMB/MiniCPM-Desk-Pet/releases/tag/v0.7.2 · raw={\"repo\":\"OpenBMB/MiniCPM-Desk-Pet\"}"},{"ref":"E29","kind":"event","title":"OpenBMB/MiniCPM 5.0","date":"2026-05-26T02:48:10+00:00","date_source":"source","source_url":"https://github.com/OpenBMB/MiniCPM/releases/tag/5.0","signal_url":"https://onlylabs.fyi/signals/1b469515-2f3b-4883-a3ed-2b55ae2555d0","signal_json_url":"https://onlylabs.fyi/signals/1b469515-2f3b-4883-a3ed-2b55ae2555d0/signal.json","text":"release · OpenBMB/MiniCPM 5.0 · signal_desk=releases · occurred_at=2026-05-26T02:48:10+00:00 · url=https://github.com/OpenBMB/MiniCPM/releases/tag/5.0 · raw={\"repo\":\"OpenBMB/MiniCPM\"}"},{"ref":"E30","kind":"event","title":"OpenBMB/MiniCPM-V-Apps harmonyos-v2.2","date":"2026-05-25T16:49:51+00:00","date_source":"source","source_url":"https://github.com/OpenBMB/MiniCPM-V-Apps/releases/tag/harmonyos-v2.2","signal_url":"https://onlylabs.fyi/signals/bb452cdf-8f4b-4c30-a762-fa6c251db013","signal_json_url":"https://onlylabs.fyi/signals/bb452cdf-8f4b-4c30-a762-fa6c251db013/signal.json","text":"release · OpenBMB/MiniCPM-V-Apps harmonyos-v2.2 · signal_desk=releases · occurred_at=2026-05-25T16:49:51+00:00 · url=https://github.com/OpenBMB/MiniCPM-V-Apps/releases/tag/harmonyos-v2.2 · raw={\"repo\":\"OpenBMB/MiniCPM-V-Apps\"}"},{"ref":"E31","kind":"event","title":"OpenBMB/MiniCPM-V-Apps android-v2.2","date":"2026-05-25T16:49:23+00:00","date_source":"source","source_url":"https://github.com/OpenBMB/MiniCPM-V-Apps/releases/tag/android-v2.2","signal_url":"https://onlylabs.fyi/signals/0fd9afd1-1b4f-462a-a657-b92da25b3cea","signal_json_url":"https://onlylabs.fyi/signals/0fd9afd1-1b4f-462a-a657-b92da25b3cea/signal.json","text":"release · OpenBMB/MiniCPM-V-Apps android-v2.2 · signal_desk=releases · occurred_at=2026-05-25T16:49:23+00:00 · url=https://github.com/OpenBMB/MiniCPM-V-Apps/releases/tag/android-v2.2 · raw={\"repo\":\"OpenBMB/MiniCPM-V-Apps\"}"},{"ref":"E32","kind":"event","title":"OpenBMB/MiniCPM-Desk-Pet v0.7.1","date":"2026-05-25T11:01:02+00:00","date_source":"source","source_url":"https://github.com/OpenBMB/MiniCPM-Desk-Pet/releases/tag/v0.7.1","signal_url":"https://onlylabs.fyi/signals/469c5c9a-a6cc-450c-8f81-44979b67ed65","signal_json_url":"https://onlylabs.fyi/signals/469c5c9a-a6cc-450c-8f81-44979b67ed65/signal.json","text":"release · OpenBMB/MiniCPM-Desk-Pet v0.7.1 · signal_desk=releases · occurred_at=2026-05-25T11:01:02+00:00 · url=https://github.com/OpenBMB/MiniCPM-Desk-Pet/releases/tag/v0.7.1 · raw={\"repo\":\"OpenBMB/MiniCPM-Desk-Pet\"}"},{"ref":"E33","kind":"event","title":"OpenBMB/ArcLight v1.1","date":"2026-05-24T04:37:23+00:00","date_source":"source","source_url":"https://github.com/OpenBMB/ArcLight/releases/tag/v1.1","signal_url":"https://onlylabs.fyi/signals/473ff381-2545-48d5-a526-21a684a140da","signal_json_url":"https://onlylabs.fyi/signals/473ff381-2545-48d5-a526-21a684a140da/signal.json","text":"release · OpenBMB/ArcLight v1.1 · signal_desk=releases · occurred_at=2026-05-24T04:37:23+00:00 · url=https://github.com/OpenBMB/ArcLight/releases/tag/v1.1 · raw={\"repo\":\"OpenBMB/ArcLight\"}"},{"ref":"E34","kind":"event","title":"openbmb/MiniCPM5-1B-Base","date":"2026-05-21T07:27:42+00:00","date_source":"source","source_url":"https://huggingface.co/openbmb/MiniCPM5-1B-Base","signal_url":"https://onlylabs.fyi/signals/1af6cda6-f605-4a60-bee8-9331ee843a72","signal_json_url":"https://onlylabs.fyi/signals/1af6cda6-f605-4a60-bee8-9331ee843a72/signal.json","text":"model_released · openbmb/MiniCPM5-1B-Base · signal_desk=releases · occurred_at=2026-05-21T07:27:42+00:00 · url=https://huggingface.co/openbmb/MiniCPM5-1B-Base · hf_downloads=17 · hf_likes=1 · hf_params=1080632832 · pipeline=text-generation · license=apache-2.0"},{"ref":"E35","kind":"event","title":"OpenBMB/MiniCPM-Desk-Pet","date":"2026-05-18T13:08:37+00:00","date_source":"source","source_url":"https://github.com/OpenBMB/MiniCPM-Desk-Pet","signal_url":"https://onlylabs.fyi/signals/7bb917a1-5397-4dea-9822-9e930c5c7be3","signal_json_url":"https://onlylabs.fyi/signals/7bb917a1-5397-4dea-9822-9e930c5c7be3/signal.json","text":"repo_new · OpenBMB/MiniCPM-Desk-Pet · signal_desk=repos · occurred_at=2026-05-18T13:08:37+00:00 · url=https://github.com/OpenBMB/MiniCPM-Desk-Pet · stars=274 · raw={\"repo\":\"OpenBMB/MiniCPM-Desk-Pet\",\"description\":\"a local-first desktop pet powered by MiniCPM5\",\"language\":\"JavaScript\"}"},{"ref":"E36","kind":"event","title":"OpenBMB/ForgeTrain","date":"2026-05-14T08:01:19+00:00","date_source":"source","source_url":"https://github.com/OpenBMB/ForgeTrain","signal_url":"https://onlylabs.fyi/signals/3b4dec65-36de-4552-a00b-2c4920646acc","signal_json_url":"https://onlylabs.fyi/signals/3b4dec65-36de-4552-a00b-2c4920646acc/signal.json","text":"repo_new · OpenBMB/ForgeTrain · signal_desk=repos · occurred_at=2026-05-14T08:01:19+00:00 · url=https://github.com/OpenBMB/ForgeTrain · stars=225 · raw={\"repo\":\"OpenBMB/ForgeTrain\",\"language\":\"Python\"}"},{"ref":"E37","kind":"event","title":"OpenBMB/Omni-DuplexEval","date":"2026-05-15T09:44:36+00:00","date_source":"source","source_url":"https://github.com/OpenBMB/Omni-DuplexEval","signal_url":"https://onlylabs.fyi/signals/f4e5394e-af13-4293-a2b4-89c6d0df2b54","signal_json_url":"https://onlylabs.fyi/signals/f4e5394e-af13-4293-a2b4-89c6d0df2b54/signal.json","text":"repo_new · OpenBMB/Omni-DuplexEval · signal_desk=repos · occurred_at=2026-05-15T09:44:36+00:00 · url=https://github.com/OpenBMB/Omni-DuplexEval · stars=8 · raw={\"repo\":\"OpenBMB/Omni-DuplexEval\",\"language\":\"Python\"}"},{"ref":"E38","kind":"event","title":"OpenBMB/MiniCPM-V-Apps harmonyos-v2.0","date":"2026-05-14T16:44:58+00:00","date_source":"source","source_url":"https://github.com/OpenBMB/MiniCPM-V-Apps/releases/tag/harmonyos-v2.0","signal_url":"https://onlylabs.fyi/signals/bf06a680-6be1-48c7-bb14-968b4c46e22e","signal_json_url":"https://onlylabs.fyi/signals/bf06a680-6be1-48c7-bb14-968b4c46e22e/signal.json","text":"release · OpenBMB/MiniCPM-V-Apps harmonyos-v2.0 · signal_desk=releases · occurred_at=2026-05-14T16:44:58+00:00 · url=https://github.com/OpenBMB/MiniCPM-V-Apps/releases/tag/harmonyos-v2.0 · raw={\"repo\":\"OpenBMB/MiniCPM-V-Apps\"}"},{"ref":"E39","kind":"event","title":"OpenBMB/MiniCPM-V-Apps android-v2.0","date":"2026-05-14T16:44:35+00:00","date_source":"source","source_url":"https://github.com/OpenBMB/MiniCPM-V-Apps/releases/tag/android-v2.0","signal_url":"https://onlylabs.fyi/signals/4ad0c20e-2a71-4c61-92d1-0df5f70bd300","signal_json_url":"https://onlylabs.fyi/signals/4ad0c20e-2a71-4c61-92d1-0df5f70bd300/signal.json","text":"release · OpenBMB/MiniCPM-V-Apps android-v2.0 · signal_desk=releases · occurred_at=2026-05-14T16:44:35+00:00 · url=https://github.com/OpenBMB/MiniCPM-V-Apps/releases/tag/android-v2.0 · raw={\"repo\":\"OpenBMB/MiniCPM-V-Apps\"}"},{"ref":"E40","kind":"event","title":"OpenBMB/VoxCPM 2.0.3","date":"2026-05-11T11:59:20+00:00","date_source":"source","source_url":"https://github.com/OpenBMB/VoxCPM/releases/tag/2.0.3","signal_url":"https://onlylabs.fyi/signals/faed1570-3a46-461e-a193-9826691ee20f","signal_json_url":"https://onlylabs.fyi/signals/faed1570-3a46-461e-a193-9826691ee20f/signal.json","text":"release · OpenBMB/VoxCPM 2.0.3 · signal_desk=releases · occurred_at=2026-05-11T11:59:20+00:00 · url=https://github.com/OpenBMB/VoxCPM/releases/tag/2.0.3 · raw={\"repo\":\"OpenBMB/VoxCPM\"}"},{"ref":"E41","kind":"event","title":"openbmb/SciCore-Mol","date":"2026-04-29T05:49:27+00:00","date_source":"source","source_url":"https://huggingface.co/openbmb/SciCore-Mol","signal_url":"https://onlylabs.fyi/signals/2bc74b16-cdda-4005-86ee-0f9dae3ec4ef","signal_json_url":"https://onlylabs.fyi/signals/2bc74b16-cdda-4005-86ee-0f9dae3ec4ef/signal.json","text":"model_released · openbmb/SciCore-Mol · signal_desk=releases · occurred_at=2026-04-29T05:49:27+00:00 · url=https://huggingface.co/openbmb/SciCore-Mol · hf_downloads=178 · hf_likes=6 · hf_params=8188556288 · pipeline=text-generation · license=apache-2.0"},{"ref":"E42","kind":"event","title":"OpenBMB/UltraRAG","date":"2025-01-16T10:56:02+00:00","date_source":"source","source_url":"https://github.com/OpenBMB/UltraRAG","signal_url":"https://onlylabs.fyi/signals/a307f290-a998-4644-8da4-b75d2e062547","signal_json_url":"https://onlylabs.fyi/signals/a307f290-a998-4644-8da4-b75d2e062547/signal.json","text":"repo_new · OpenBMB/UltraRAG · signal_desk=repos · occurred_at=2025-01-16T10:56:02+00:00 · url=https://github.com/OpenBMB/UltraRAG · stars=5581 · raw={\"repo\":\"OpenBMB/UltraRAG\",\"description\":\"A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines\",\"language\":\"Python\"}"},{"ref":"E43","kind":"event","title":"OpenBMB/IoA","date":"2024-07-08T06:22:07+00:00","date_source":"source","source_url":"https://github.com/OpenBMB/IoA","signal_url":"https://onlylabs.fyi/signals/bc22749d-6154-468e-9105-267c297f1f68","signal_json_url":"https://onlylabs.fyi/signals/bc22749d-6154-468e-9105-267c297f1f68/signal.json","text":"repo_new · OpenBMB/IoA · signal_desk=repos · occurred_at=2024-07-08T06:22:07+00:00 · url=https://github.com/OpenBMB/IoA · stars=821 · hn=3 points/1 comments · raw={\"repo\":\"OpenBMB/IoA\",\"description\":\"An open-source framework for collaborative AI agents, enabling diverse, distributed agents to team up and tackle complex tasks through internet-like connectivity.\",\"language\":\"Python\"}"},{"ref":"E44","kind":"event","title":"OpenBMB/UltraRAG v0.3.0.2","date":"2026-04-09T04:41:05+00:00","date_source":"source","source_url":"https://github.com/OpenBMB/UltraRAG/releases/tag/v0.3.0.2","signal_url":"https://onlylabs.fyi/signals/9cd43731-cb1e-468c-8eee-1e39787256e7","signal_json_url":"https://onlylabs.fyi/signals/9cd43731-cb1e-468c-8eee-1e39787256e7/signal.json","text":"release · OpenBMB/UltraRAG v0.3.0.2 · signal_desk=releases · occurred_at=2026-04-09T04:41:05+00:00 · url=https://github.com/OpenBMB/UltraRAG/releases/tag/v0.3.0.2 · raw={\"repo\":\"OpenBMB/UltraRAG\"}"},{"ref":"E45","kind":"event","title":"OpenBMB/VoxCPM 2.0.2","date":"2026-04-08T10:19:15+00:00","date_source":"source","source_url":"https://github.com/OpenBMB/VoxCPM/releases/tag/2.0.2","signal_url":"https://onlylabs.fyi/signals/deaff153-3e79-40b6-bdca-f44d888324b8","signal_json_url":"https://onlylabs.fyi/signals/deaff153-3e79-40b6-bdca-f44d888324b8/signal.json","text":"release · OpenBMB/VoxCPM 2.0.2 · signal_desk=releases · occurred_at=2026-04-08T10:19:15+00:00 · url=https://github.com/OpenBMB/VoxCPM/releases/tag/2.0.2 · raw={\"repo\":\"OpenBMB/VoxCPM\"}"},{"ref":"E46","kind":"event","title":"OpenBMB/VoxCPM 2.0.1","date":"2026-04-08T06:06:15+00:00","date_source":"source","source_url":"https://github.com/OpenBMB/VoxCPM/releases/tag/2.0.1","signal_url":"https://onlylabs.fyi/signals/061ddd17-c925-4be4-a3cf-f078e0d82201","signal_json_url":"https://onlylabs.fyi/signals/061ddd17-c925-4be4-a3cf-f078e0d82201/signal.json","text":"release · OpenBMB/VoxCPM 2.0.1 · signal_desk=releases · occurred_at=2026-04-08T06:06:15+00:00 · url=https://github.com/OpenBMB/VoxCPM/releases/tag/2.0.1 · raw={\"repo\":\"OpenBMB/VoxCPM\"}"},{"ref":"E47","kind":"event","title":"OpenBMB/VoxCPM 2.0.0","date":"2026-04-06T14:51:18+00:00","date_source":"source","source_url":"https://github.com/OpenBMB/VoxCPM/releases/tag/2.0.0","signal_url":"https://onlylabs.fyi/signals/90bf1388-d782-49b2-a3c6-889d5770abf3","signal_json_url":"https://onlylabs.fyi/signals/90bf1388-d782-49b2-a3c6-889d5770abf3/signal.json","text":"release · OpenBMB/VoxCPM 2.0.0 · signal_desk=releases · occurred_at=2026-04-06T14:51:18+00:00 · url=https://github.com/OpenBMB/VoxCPM/releases/tag/2.0.0 · raw={\"repo\":\"OpenBMB/VoxCPM\"}"},{"ref":"E48","kind":"event","title":"OpenBMB/voxcpm2-demopage","date":"2026-04-06T06:59:02+00:00","date_source":"source","source_url":"https://github.com/OpenBMB/voxcpm2-demopage","signal_url":"https://onlylabs.fyi/signals/dc2c1782-3073-4882-8dda-1887de471b5b","signal_json_url":"https://onlylabs.fyi/signals/dc2c1782-3073-4882-8dda-1887de471b5b/signal.json","text":"repo_new · OpenBMB/voxcpm2-demopage · signal_desk=repos · occurred_at=2026-04-06T06:59:02+00:00 · url=https://github.com/OpenBMB/voxcpm2-demopage · stars=5 · raw={\"repo\":\"OpenBMB/voxcpm2-demopage\",\"language\":\"JavaScript\"}"},{"ref":"E49","kind":"event","title":"OpenBMB/Eurus","date":"2024-03-30T10:10:12+00:00","date_source":"source","source_url":"https://github.com/OpenBMB/Eurus","signal_url":"https://onlylabs.fyi/signals/693385b2-a553-47ea-bad3-8c74d64065ef","signal_json_url":"https://onlylabs.fyi/signals/693385b2-a553-47ea-bad3-8c74d64065ef/signal.json","text":"repo_new · OpenBMB/Eurus · signal_desk=repos · occurred_at=2024-03-30T10:10:12+00:00 · url=https://github.com/OpenBMB/Eurus · stars=323 · hn=2 points/0 comments · raw={\"repo\":\"OpenBMB/Eurus\",\"language\":\"Python\"}"},{"ref":"E50","kind":"event","title":"OpenBMB/ClawXMemory v0.1.5","date":"2026-04-03T07:14:35+00:00","date_source":"source","source_url":"https://github.com/OpenBMB/ClawXMemory/releases/tag/v0.1.5","signal_url":"https://onlylabs.fyi/signals/cfee7187-5703-4243-9e66-b8723241ffcc","signal_json_url":"https://onlylabs.fyi/signals/cfee7187-5703-4243-9e66-b8723241ffcc/signal.json","text":"release · OpenBMB/ClawXMemory v0.1.5 · signal_desk=releases · occurred_at=2026-04-03T07:14:35+00:00 · url=https://github.com/OpenBMB/ClawXMemory/releases/tag/v0.1.5 · raw={\"repo\":\"OpenBMB/ClawXMemory\"}"},{"ref":"E51","kind":"event","title":"OpenBMB/ClawXMemory v0.1.4","date":"2026-04-03T02:04:47+00:00","date_source":"source","source_url":"https://github.com/OpenBMB/ClawXMemory/releases/tag/v0.1.4","signal_url":"https://onlylabs.fyi/signals/9fb535f0-8f7a-4103-8f0d-d5119424dcd8","signal_json_url":"https://onlylabs.fyi/signals/9fb535f0-8f7a-4103-8f0d-d5119424dcd8/signal.json","text":"release · OpenBMB/ClawXMemory v0.1.4 · signal_desk=releases · occurred_at=2026-04-03T02:04:47+00:00 · url=https://github.com/OpenBMB/ClawXMemory/releases/tag/v0.1.4 · raw={\"repo\":\"OpenBMB/ClawXMemory\"}"},{"ref":"E52","kind":"event","title":"openbmb/NOSA-8B","date":"2026-01-04T07:51:57+00:00","date_source":"source","source_url":"https://huggingface.co/openbmb/NOSA-8B","signal_url":"https://onlylabs.fyi/signals/a44511a1-9e53-49fb-8302-54488732d408","signal_json_url":"https://onlylabs.fyi/signals/a44511a1-9e53-49fb-8302-54488732d408/signal.json","text":"model_released · openbmb/NOSA-8B · signal_desk=releases · occurred_at=2026-01-04T07:51:57+00:00 · url=https://huggingface.co/openbmb/NOSA-8B · hf_downloads=1035 · hf_likes=10 · hf_params=8185270336 · pipeline=text-generation · license=apache-2.0"},{"ref":"E53","kind":"event","title":"OpenBMB/ClawXMemory v0.1.3","date":"2026-04-01T01:27:54+00:00","date_source":"source","source_url":"https://github.com/OpenBMB/ClawXMemory/releases/tag/v0.1.3","signal_url":"https://onlylabs.fyi/signals/b6116d62-8d77-44fc-a6ca-dcb20f5a6d67","signal_json_url":"https://onlylabs.fyi/signals/b6116d62-8d77-44fc-a6ca-dcb20f5a6d67/signal.json","text":"release · OpenBMB/ClawXMemory v0.1.3 · signal_desk=releases · occurred_at=2026-04-01T01:27:54+00:00 · url=https://github.com/OpenBMB/ClawXMemory/releases/tag/v0.1.3 · raw={\"repo\":\"OpenBMB/ClawXMemory\"}"},{"ref":"E54","kind":"event","title":"openbmb/InfLLM-V2-Short-Dense-Base","date":"2025-10-25T16:08:00+00:00","date_source":"source","source_url":"https://huggingface.co/openbmb/InfLLM-V2-Short-Dense-Base","signal_url":"https://onlylabs.fyi/signals/3be030f1-a7e3-46ee-ba93-d341227e98f4","signal_json_url":"https://onlylabs.fyi/signals/3be030f1-a7e3-46ee-ba93-d341227e98f4/signal.json","text":"model_released · openbmb/InfLLM-V2-Short-Dense-Base · signal_desk=releases · occurred_at=2025-10-25T16:08:00+00:00 · url=https://huggingface.co/openbmb/InfLLM-V2-Short-Dense-Base · hf_downloads=103 · hf_likes=9 · hf_params=8185253888 · license=apache-2.0"},{"ref":"E55","kind":"event","title":"openbmb/RLPR-Qwen2.5-7B-Base","date":"2025-06-22T12:08:49+00:00","date_source":"source","source_url":"https://huggingface.co/openbmb/RLPR-Qwen2.5-7B-Base","signal_url":"https://onlylabs.fyi/signals/49c2afe9-46fc-41f7-be96-921b0e533a2a","signal_json_url":"https://onlylabs.fyi/signals/49c2afe9-46fc-41f7-be96-921b0e533a2a/signal.json","text":"model_released · openbmb/RLPR-Qwen2.5-7B-Base · signal_desk=releases · occurred_at=2025-06-22T12:08:49+00:00 · url=https://huggingface.co/openbmb/RLPR-Qwen2.5-7B-Base · hf_downloads=56 · hf_likes=9 · hf_params=7615616512 · pipeline=text-generation · license=apache-2.0"},{"ref":"E56","kind":"event","title":"OpenBMB/ClawXRouter","date":"2026-03-27T07:49:24+00:00","date_source":"source","source_url":"https://github.com/OpenBMB/ClawXRouter","signal_url":"https://onlylabs.fyi/signals/97432b29-1737-4952-a4f9-880b69a029b7","signal_json_url":"https://onlylabs.fyi/signals/97432b29-1737-4952-a4f9-880b69a029b7/signal.json","text":"repo_new · OpenBMB/ClawXRouter · signal_desk=repos · occurred_at=2026-03-27T07:49:24+00:00 · url=https://github.com/OpenBMB/ClawXRouter · stars=187 · raw={\"repo\":\"OpenBMB/ClawXRouter\",\"language\":\"TypeScript\"}"},{"ref":"E57","kind":"event","title":"OpenBMB/ClawXMemory","date":"2026-03-27T08:28:13+00:00","date_source":"source","source_url":"https://github.com/OpenBMB/ClawXMemory","signal_url":"https://onlylabs.fyi/signals/368d3595-28dc-4e13-bef4-121ad12e773d","signal_json_url":"https://onlylabs.fyi/signals/368d3595-28dc-4e13-bef4-121ad12e773d/signal.json","text":"repo_new · OpenBMB/ClawXMemory · signal_desk=repos · occurred_at=2026-03-27T08:28:13+00:00 · url=https://github.com/OpenBMB/ClawXMemory · stars=44 · raw={\"repo\":\"OpenBMB/ClawXMemory\",\"description\":\"ClawXMemory: A Multi-Level Memory Plugin for OpenClaw with Long-Term Context\",\"language\":\"TypeScript\"}"},{"ref":"E58","kind":"event","title":"OpenBMB/EdgeClaw","date":"2026-02-13T03:49:56+00:00","date_source":"source","source_url":"https://github.com/OpenBMB/EdgeClaw","signal_url":"https://onlylabs.fyi/signals/4f5c5aa0-6457-4918-ad20-3d1751e988a9","signal_json_url":"https://onlylabs.fyi/signals/4f5c5aa0-6457-4918-ad20-3d1751e988a9/signal.json","text":"repo_forked · OpenBMB/EdgeClaw · signal_desk=forks · occurred_at=2026-02-13T03:49:56+00:00 · url=https://github.com/OpenBMB/EdgeClaw · stars=1222 · raw={\"repo\":\"OpenBMB/EdgeClaw\",\"parent\":\"openclaw/openclaw\"}"},{"ref":"E59","kind":"event","title":"OpenBMB/sglang","date":"2025-06-06T03:10:57+00:00","date_source":"source","source_url":"https://github.com/OpenBMB/sglang","signal_url":"https://onlylabs.fyi/signals/04b05592-9ae4-4cb0-956c-d3ee4d2e28ab","signal_json_url":"https://onlylabs.fyi/signals/04b05592-9ae4-4cb0-956c-d3ee4d2e28ab/signal.json","text":"repo_forked · OpenBMB/sglang · signal_desk=forks · occurred_at=2025-06-06T03:10:57+00:00 · url=https://github.com/OpenBMB/sglang · stars=15 · raw={\"repo\":\"OpenBMB/sglang\",\"parent\":\"sgl-project/sglang\"}"},{"ref":"E60","kind":"event","title":"ModelBest Adopts the LLM-Based AI Agents to Launch ChatDev, its First SaaS Product","date":"2023-11-16T08:13:49+00:00","date_source":"rss.item_date","source_url":"https://medium.com/@openbmb/modelbest-adopts-the-llm-based-ai-agents-to-launch-chatdev-its-first-saas-product-fd70f3b969f7?source=rss-4a6e3e4a369a------2","signal_url":"https://onlylabs.fyi/signals/5fde82ff-1129-4549-ad43-d68e0d3e9cd7","signal_json_url":"https://onlylabs.fyi/signals/5fde82ff-1129-4549-ad43-d68e0d3e9cd7/signal.json","text":"post_published · ModelBest Adopts the LLM-Based AI Agents to Launch ChatDev, its First SaaS Product · signal_desk=talking · occurred_at=2023-11-16T08:13:49+00:00 · url=https://medium.com/@openbmb/modelbest-adopts-the-llm-based-ai-agents-to-launch-chatdev-its-first-saas-product-fd70f3b969f7?source=rss-4a6e3e4a369a------2"}]}