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.
Agent Laboratory is an end-to-end autonomous research workflow meant to assist you as the human researcher toward implementing your research ideas
| Date | Stars |
|---|---|
| 2026-07-31 | 5778 |
| 2026-08-02 | 5784 |
| 2026-08-06 | 5784 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Agent Laboratory: Using LLM Agents as Research Assistants
<p align="center">
<img src="media/AgentLabLogo.png" alt="Demonstration of the flow of AgentClinic" style="width: 99%;">
</p>
<p align="center">
【English | <a href="readme/README-chinese.md">中文</a> | <a href="readme/README-japanese.md">日本語</a> | <a href="readme/README-korean.md">한국어</a> | <a href="readme/README-filipino.md">Filipino</a> | <a href="readme/README-french.md">Français</a> | <a href="readme/README-slovak.md">Slovenčina</a> | <a href="readme/README-portugese.md">Português</a> | <a href="readme/README-spanish.md">Español</a> | <a href="readme/README-turkish.md">Türkçe</a> | <a href="readme/README-hindi.md">हिंदी</a> | <a href="readme/README-bengali.md">বাংলা</a> | <a href="readme/README-vietnamese.md">Tiếng Việt</a> | <a href="readme/README-russian.md">Русский</a> | <a href="readme/README-arabic.md">العربية</a> | <a href="readme/README-farsi.md">فارسی</a> | <a href="readme/README-italian.md">Italiano</a>】
</p>
<p align="center">
【📝 <a href="https://arxiv.org/pdf/2501.04227">Paper</a> | 🌐 <a href="https://agentlaboratory.github.io/">Website</a> | 🌐 <a href="https://agentrxiv.github.io/">AgentRxiv Website</a> | 💻 <a href="https://github.com/SamuelSchmidgall/AgentLaboratory">Software</a> | 📰 <a href="https://agentlaboratory.github.io/#citation-ref">Citation</a>】
</p>
### News
* [March/24/2025] 🎉 🎊 🎉 Now introducing **AgentRxiv**, a framework where autonomous research agents can upload, retrieve, and build on each other’s research. This allows agents to make cumulative progress on their research.
## 📖 Overview
- **Agent Laboratory** is an end-to-end autonomous research workflow meant to assist **you** as the human researcher toward **implementing your research ideas**. Agent Laboratory consists of specialized agents driven by large language models to support you through the entire research workflow—from conducting literature reviews and formulating plans to executing experiments and writing comprehensive reports.
- This system is not designed to replace your creativity but to complement it, enabling you to focus on ideation and critical thinking while automating repetitive and time-intensive tasks like coding and documentation. By accommodating varying levels of computational resources and human involvement, Agent Laboratory aims to accelerate scientific discovery and optimize your research productivity.
<p align="center">
<img src="media/AgentLab.png" alt="Demonstration of the flow of AgentClinic" style="width: 99%;">
</p>
- Agent Laboratory also supports **AgentRxiv**, a framework where autonomous research agents can upload, retrieve, and build on each other’s research. This allows agents to make cumulative progress on their research.
<p align="center">
<img src="media/agentrxiv.png" alt="Demonstration of the flow of AgentClinic" style="width: 99%;">
</p>
### 🔬 How does Agent Laboratory work?
- Agent Laboratory consists of three primary phases that systematically guide the research process: (1) Literature Review, (2) Experimentation, and (3) Report Writing. During each phase, specialized agents driven by LLMs collaborate to accomplish distinct objectives, integrating external tools like arXiv, Hugging Face, Python, and LaTeX to optimize outcomes. This structured workflow begins with the independent collection and analysis of relevant research papers, progresses through collaborative planning and data preparation, and results in automated experimentation and comprehensive report generation. Details on specific agent roles and their contributions across these phases are discussed in the paper.
<p align="center">
<img src="media/AgentLabWF.png" alt="Demonstration of the flow of AgentClinic" style="width: 99%;">
</p>
### 👾 Currently supported models
* **OpenAI**: o1, o1-preview, o1-mini, gpt-4o, o3-mini
* **DeepSeek**: deepseek-chat (deepseek-v3)
To select a specific llm set the flag `--llm-backend="llm_model"` for exaExcerpt of 9,984 characters
Read on GitHub
13
2
1
1
1
1
@voxel51
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:20fb77ce2a443196, llm:Repository description: 'Agent Laboratory is an end-to-end autonomous research workflow meant to assist you as the human researcher toward implementing your research ideas' (SamuelSchmidgall/AgentLaboratory). Language: Python. No topics provided.
matched fp:20fb77ce2a443196, llm:Repository description: 'Agent Laboratory is an end-to-end autonomous research workflow meant to assist you as the human researcher toward implementing your research ideas' (SamuelSchmidgall/AgentLaboratory). Language: Python. No topics provided.