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
- Validate paths in StateBackend methods for consistency and defense in depth
- feat(sdk): record the subagent's checkpoint namespace on the `task` tool message
- AsyncSubAgent: per-request headers, e.g. to forward the caller's credentials to a remote subagent
- fix(sdk): report async subagents with unfinished async tasks as `delegated`
- feat(examples): add multi-level engineering org with async subagents
- fix(sdk): append dangling tool call results instead of rewriting history
- feat(sdk): tag Context Hub reads with provenance in LangSmith traces
- feat(quickjs): show the model content blocks returned by `eval`
- Drop temporary `langchain-core` floor once SDK pin requires >=1.7.5
- feat(sdk): prototype opt-in per-call approvals
- Docs
- Python not yet supported