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
- test(quickjs): track WASM marshaling calls and per-turn latency
- feat(quickjs): return each tool's data to `tools.*` callers
- After a run stops mid-turn with a pending Anthropic `web_search` call, every later request on the thread fails with 400
- Support adding memory and skill sources during a run, loaded before the next model call
- `langchain-google-genai` is a required dependency but is never imported
- `FilesystemBackend.edit` rewrites CRLF line endings to LF across the whole file
- BaseSandbox.ls() and grep() silently return partial results when execute() reports truncated=True
- `StoreBackend.upload_files` stores UTF-8 NUL as text incompatible with PostgreSQL JSONB
- fix(quickjs): render dict (MCP) `args_schema` inline in PTC signatures
- fix(quickjs): keep slot build and teardown off the caller's event loop
- Docs
- Python not yet supported