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
- Strip or convert unsupported multimedia formats
- `_glob_search_files` raises `KeyError: 'modified_at'` when a `FileData` omits the optional timestamp
- Runtime-resolve rubric grader model
- `dcode` execute subprocesses can steal TUI input via `/dev/tty` prompts
- Add parent-side lifecycle hooks for synchronous subagent task completion
- Vercel sandbox: execute() truncates output by code points, not UTF-8 bytes
- Add an example for running Vercel Sandbox in production (snapshots, network policy, lifecycle)
- feat(evals): OOLONG long-context eval as a Harbor dataset (plain + RLM arms)
- Add TTL/cleanup for thread history and optional cache-TTL-aware resumption
- Add workflow mode for declarative multi-agent orchestration
- Docs
- Python not yet supported