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): re-attach media when undo or redo restores its placeholder
- Deficiencies & Improvement Proposals for DeepAgent Plan & Todo Mechanism
- A task subagent's state can't be read back: 'Subgraph tools not found'
- feat(code): quieter diff hunks with word-level highlights
- RubricMiddleware: max_iterations_reached returns last (potentially worst) response instead of best across iterations
- BaseSandbox.grep path globs fail because the inline Python command is not shell-safe
- bug(acp): cancel() ignores session_id and cancels every in-flight prompt
- feat(code): add `multi_select` question type to `ask_user`
- fix(sdk): isolate parallel subagent failures in `task` tool
- bug(talon): send_message raises UnboundLocalError on empty text
- Docs
- Python not yet supported