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
- PTC returns success for Command-producing tools but drops state updates
- `async_subagents`: `acheck_async_task` and `acancel_async_task` let `KeyError` from `get_async()` escape unhandled
- Undoing a deleted `[image N]` placeholder restores bare text — the attachment is silently dropped
- Dragging a folder into the chat input turns the draft into a slash command
- Arrow keys and word jumps should treat media/paste placeholders as single units
- fix(sdk): use placeholder in subagent middleware prompting
- Large-result eviction silently skipped when tool_call_id is long (LiteLLM Gemini ids carry ~1.5KB thought signatures) — filename over OS limit, write fails, original kept
- Runtime `/model` switches filter multimodal inputs using the startup model profile
- pluggable memory-provider abstraction
- A2A client support / remote subagent delegation
- Docs
- Python not yet supported