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
- fix(sdk): handle `None` summary in `SummarizationMiddleware`
- fix(evals): forward credentials for `research_judge_models`
- feat(sdk): collect per-skill load failures during listing
- ci(infra): fail on unexpected test warnings
- fix(code): hide incomplete extras from version output
- Add OpenRouter free-tier variant to text-to-SQL example
- feat(code): prune expired sessions automatically
- For the use of asynchronous sub-agents, the ASGI protocol must utilize langgraph.json. How can it be supported in the case of dynamic multi-agent systems
- release(deepagents-code): 0.1.54
- `read_file` two-space gutter separator is ambiguous with space indentation, breaking `edit_file` round-trips on space-indented code
- Docs
- Python not yet supported