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
- fix(code): send terminal escapes through the tmux passthrough
- feat(code): complete the `dcode config` surface
- fix(code): don't claim kitty-keyboard support inside tmux
- fix(code): prevent re-denied mutation targets from being rewritten via shell
- fix(sdk): only explain truncation markers when preview omits lines
- Model invents skill paths by joining skill-root dirs + skill name instead of using listed Read paths
- `_after_model` discards a computed `PreToolUse` deny when the session gate vanishes
- `SubAgentMiddleware.private_state_keys` is assigned after construction, so a caller-supplied instance keeps an empty key set
- `SubagentStop` hooks always receive `continuation_count=0`, so they cannot self-limit
- Subagents no longer inherit parent hook state, and nothing asserts why that is safe
- Docs
- Python not yet supported