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
- 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
- Support remotely refreshed model profiles for dcode model selection
- Refactor dcode streaming hooks to use protocol terminal signals app-wide
- ``deepagents-evals trials --eval-category-exclude`` is accepted but silently ignored
- 🐛 Bug: OOM vulnerability in sandbox read() bypasses MAX_BINARY_BYTES in is_binary fallback
- Vercel sandbox: execute() truncates output by code points, not UTF-8 bytes
- Add an example for running Vercel Sandbox in production (snapshots, network policy, lifecycle)
- `dcode --acp` does not advertise session selectors (model/mode)
- Docs
- Python not yet supported