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
- harness matrix evals
- fix(sdk): add async methods to StoreBackend for async store support
- fix(sdk): preserve serialized subagent message results
- Propagate LangSmith trace context into sandbox execution
- supervisor over a2a spike
- feat(code): add a hard `--max-cost` spend cap that halts the agent
- `cancel_async_task` records `cancelled` for a run that had already finished, and `list_async_tasks` then never re-fetches it
- feat(sdk): add virtual table middleware example
- task returns an empty ToolMessage when a CompiledSubAgent uses RemoteGraph
- StoreBackend hangs on async stores — missing async methods for ls/glob/grep/download_files
- Docs
- Python not yet supported