Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
An End-to-End Infrastructure for Training and Evaluating Various LLM Agents
| Date | Stars |
|---|---|
| 2026-07-31 | 823 |
| 2026-08-04 | 825 |
| 2026-08-06 | 825 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center">
<img src="./assets/light.svg" alt="AgentCPM标志" width="400em"></img>
</div>
<p align="center">
【<a href="README_zh.md">中文</a> | English】
</p>
<p align="center">
<span style="display: inline-flex; align-items: center; justify-content: center; margin-right: 2px;">
<img src="./assets/wechat.png" alt="WeChat" style="margin-right: 4px;">
<a href="assets/wechat.md" target="_blank"> WeChat</a>
</span>
</p>
# Latest News
* [2026-01-20] 🚀🚀🚀 We have open-sourced **AgentCPM-Report**, built on MiniCPM4.1-8B, which can rival top closed-source commercial systems for report generation such as Gemini-2.5-pro-DeepResearch.
* [2026-01-12] 🚀🚀🚀 We have open-sourced **AgentCPM-Explore**—an agent LLM with only **4B parameters**—along with all code for training, inference, and the tool sandbox environment. It successfully made it onto eight classic long-horizon and challenging agent leaderboards, including GAIA, HLE, and BrowseComp. Its SOTA performance at this scale enables longer action chains and more accurate Deep Research, breaking the performance barrier for on-device agents.
## Table of Contents
- [Latest News](#latest-news)
- [Table of Contents](#table-of-contents)
- [Overview](#overview)
- [Model List](#model-list)
- [AgentCPM-Explore](#agentcpm-explore)
- [Demo](#demo)
- [QuickStart](#quickstart)
- [AgentCPM-Report](#agentcpm-report)
- [Introduction](#introduction)
- [Demo](#demo-1)
- [QuickStart](#quickstart-1)
- [Docker Deployment](#docker-deployment)
- [License](#license)
- [Citation](#citation)
- [Explore More](#explore-more)
# Overview
AgentCPM is a series of open-source LLM agents jointly developed by [THUNLP (Tsinghua NLP Lab)](https://nlp.csai.tsinghua.edu.cn), [Renmin University of China](http://ai.ruc.edu.cn/), [ModelBest](https://modelbest.cn/en), and the [OpenBMB community](https://www.openbmb.cn/home). To address challenges faced by agents in real-world applications—such as limited long-horizon capability, autonomy, and generalization—we propose a series of model-building approaches. Recently, the team has focused on comprehensively building deep research capabilities for agents, releasing [AgentCPM-Explore](./AgentCPM-Explore), a deep-search LLM agent, and [AgentCPM-Report](./AgentCPM-Report), a deep-research LLM agent.
# Model List
| Model | Download Links | Open-Sourced Content | Technical Report | How to Use |
|------------------|-----------------------------------------------------------------------------------------------------------------------------------------------|------------|-----------|-----------|
| [AgentCPM-Explore](https://github.com/OpenBMB/AgentCPM/blob/main/AgentCPM-Explore) | [🤗 Hugging Face](https://huggingface.co/openbmb/AgentCPM-Explore)<br> [🤖 ModelScope](https://modelscope.cn/models/OpenBMB/AgentCPM-Explore/) | [AgentDock](./AgentCPM-Explore/AgentDock): unified tool sandbox management & scheduling platform <br> [AgentRL](./AgentCPM-Explore/AgentRL): fully asynchronous agent reinforcement learning framework <br> [AgentToLeaP](./AgentCPM-Explore/AgentToLeaP): one-click evaluation framework for agent tool-learning capability | [AgentCPM-Explore: Realizing Long-Horizon Deep Exploration for Edge-Scale Agents](http://arxiv.org/abs/2602.06485) | [README.md](./AgentCPM-Explore)
| [AgentCPM-Report](https://github.com/OpenBMB/AgentCPM/blob/main/AgentCPM-Report) | [🤗 Hugging Face](https://huggingface.co/openbmb/AgentCPM-Report)<br> [🤖 ModelScope](https://modelscope.cn/models/OpenBMB/AgentCPM-Report/) | [UltraRAG](https://github.com/OpenBMB/UltraRAG): low-code RAG framework | [AgentCPM-Report: Interleaving Drafting and Deepening for Open-Ended Deep Research](https://arxiv.org/abs/2602.06540) | [README.md](./AgentCPM-Report)
Excerpt of 12,010 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:b29fdffa81d75435, llm:Repository description: 'An End-to-End Infrastructure for Training and Evaluating Various LLM Agents' (language: Python).
matched fp:b29fdffa81d75435, llm:Repository description: 'An End-to-End Infrastructure for Training and Evaluating Various LLM Agents' (language: Python).
matched fp:b29fdffa81d75435, llm:Repository description: 'An End-to-End Infrastructure for Training and Evaluating Various LLM Agents' (language: Python).
