DeepResearch
Tongyi Deep Research, the Leading Open-source Deep Research Agent
Explore and test a large AI model designed for deep research through online demos.
From the README
pip install -r requirements.txt
- SERPERKEYID: Get your key from Serper.dev for web search and Google Scholar
- JINAAPIKEYS: Get your key from Jina.ai for web page reading
- APIKEY/APIBASE: OpenAI-compatible API for page summarization from OpenAI
- DASHSCOPEAPIKEY: Get your key from Dashscope for file parsing
- SANDBOXFUSIONENDPOINT: Python interpreter sandbox endpoints (see SandboxFusion)
- MODELPATH: Path to your model weights
Excerpts from the project README on GitHub. Copyright and licensing remain with the respective authors.
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
Get an email alert on its next release or when it starts trending — never miss the moment.
Free · no card · unsubscribe anytimeTongyi Deep Research, the Leading Open-source Deep Research Agent
DeepResearch has 19.9k stars on GitHub. It has been forked 1.5k times. DeepResearch is written mainly in Python. It has been in active development since 2025. DeepResearch is available under the Apache-2.0 license. Its main topics are agent, alibaba, artificial-intelligence, deep-research.
Compare with the paid tools it replacesWhat is DeepResearch?
Tongyi Deep Research, the Leading Open-source Deep Research Agent
Is DeepResearch open source?
DeepResearch is an open-source project. It is released under the Apache-2.0 license.
Is DeepResearch free?
Yes. DeepResearch is free and open source — you can use, modify and self-host it.
What license does DeepResearch use?
DeepResearch is available under the Apache-2.0 license.
What language is DeepResearch written in?
DeepResearch is written mainly in Python.
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://olud.ai/project/alibaba-nlp-deepresearch.html)
Measured from GitHub topics shared by both projects, weighted by how rare each topic is.