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
- Support an optional full-state checkpoint policy for Deep Agents
- release(deepagents-talon): 0.1.1
- Add OpenRouter OAuth login
- Support a shared, stateful shell for user and agent commands
- feat(quickjs): make runtime startup behavior configurable
- feat(sdk): expose subagents on the `task` tool for graph drawing
- Selective shared memory between a subset of sub-agents (memory groups)
- Handoff mode: let users chat directly with a subagent
- check_async_task returns the subagent's last message instead of its structured_response
- feat(code): add shell completion scripts via `dcode completion`
- Docs
- Python not yet supported