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
- Preserve the prompt-cache prefix during automatic summarization
- `list_async_tasks` filters by stale cached status before fetching live statuses
- Distinguish empty and whitespace-only files in `read_file` output
- Model invents skill paths by joining skill-root dirs + skill name instead of using listed Read paths
- Fail closed when server hook context disappears during resume
- BaseSandbox.grep path globs fail because the inline Python command is not shell-safe
- bug(talon): send_message raises UnboundLocalError on empty text
- Summarization overflow fallback (`_slice_read_file_tm`) silently drops image blocks from `read_file` tool results
- Native Communication and Coordination Between Peer-Level Deep Agents
- Approval policy file for fine-grained auto-approval rules
- Docs
- Python not yet supported