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
- `StateBackend.upload_files` corrupts binary files: download returns base64 text, not the original bytes
- feat(code): model-node retry middleware for transient model errors
- langchain-quickjs: parallel eval on same thread_id with mode="call" — ConcurrentEval cleanup crashes sibling eval (ValueError: already closed)
- Setting `system_prompt="..."` on SubAgentMiddleware appends all subagent descriptions
- Keep CodeInterpreterMiddleware's QuickJS heap snapshot out of public state responses
- RubricMiddleware: "satisfied" verdict with empty/incomplete criteria list silently ends the self-improve loop
- Support remotely refreshed model profiles for dcode model selection
- Refactor dcode streaming hooks to use protocol terminal signals app-wide
- Lifecycle hook commands are killed at a hardcoded 5s timeout with no way to configure it
- `/summarization-model` command
- Docs
- Python not yet supported