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
- Pre-execution authorization layer — a complement to sandbox enforcement
- `read_file` pagination skips lines after wrapping due to double limit application
- Async subagents option to pass certain state vars from the parent
- Skills not working: `read_file` for `SKILL.md` not read fully before execute it
- `/doctor`
- Recommended models in switcher
- Structured compaction prompt
- test(evals): focus `MemoryAgentBench` suite on cherry-picked questions
- MCP servers duplicated in approval prompt when both `.mcp.json` and `.deepagents/.mcp.json` exist
- `SubAgentMiddleware` regression — runtime config not passed to subagent invocations (PR #602 fix lost in #1041 refactor)
- Docs
- Python not yet supported