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
- list_async_tasks filters by stale cached status before fetching live statuses
- fix(code): keep highlighted `/model` rows readable
- fix(code): serialize dcode self-upgrades across processes
- Startup auto-update has no cross-process lock; concurrent dcode launches all upgrade
- fix(code): collapse finished dynamic subagents
- fix(sdk): enforce full criterion coverage in `RubricMiddleware`
- Distinguish empty and whitespace-only files in `read_file` output
- style(code): render `/cost` and `/tokens` as markdown
- fix(code): surface `cursor_blink` and `terminal_progress` in `dcode config`
- feat(code): report tmux setup in `dcode doctor`
- Docs
- Python not yet supported