deepagents
https://github.com/langchain-ai/deepagents
Python
Deep Agents is an agent harness built on langchain and langgraph. Deep Agents are equipped with a planning tool, a filesystem backend, and the ability to spawn subagents - making them well-equipped to handle complex agentic tasks.
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported1 Subscribers
Add a CodeTriage badge to deepagents
Help out
- Issues
- Hierarchical `AGENTS.md` discovery (ancestor walk + subdir auto-discovery)
- Support `~/.deepagents/.env` for global API key overrides
- Model ends after only calling the `get_weather` tool, without returning the final result after executing the tool.
- fix(cli): use max-height for tool-info-scroll to shrink-wrap content
- fix(harbor): `grep` literal search, implement missing `download_files`
- - INFO - `write_todos` is not strict. Only `strict` function tools can be auto-parsed
- fix(daytona): use session-based execution to avoid 5-minute SDK timeout
- `SubAgentMiddleware` does not propagate `recursion_limit` to subagent graphs — subagents silently use default limit of 25
- Better MCP screen
- CLI hangs randomly
- Docs
- Python not yet supported