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
- Model switch not propagated to subagents
- Async subagents: `last_updated_at` not updated when task status changes
- Indicate when inside a sandbox
- Middleware tools should use concrete `ToolRuntime` type parameters
- feat: add Databricks as native model provider
- Stream output of tool and message out of order (ACP)
- Jump to message
- Press twice to interrupt
- Agent-initiated model switching via tool call
- `CompiledSubAgent` with custom `StateGraph` causes infinite loop when last message is `ToolMessage`
- Docs
- Python not yet supported