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
- Docs "Dynamic skill lists" example silently loads zero skills — `skills=` sources must be a container of subdirectories, not a leaf skill directory
- feat(evals): A/B Test Changes Simultaneously on Deep Agents Eval Suite
- fix(sdk): treat `read_file` offset at EOF as a benign boundary
- RFC: converge read_file offset on 1-indexed line numbers (input + output)
- Give offloaded tool-result files a recognizable text extension
- Show attention states in the terminal tab title
- feat(code): add playwright browser use
- `/statusline` config to customize footer status line
- dcode (Deep Agents Code) Roadmap — Coding Agent Harness: K8s-native operator, LSP, and feature parity
- Let `FileInfo` carry per-entry context (e.g. a stable id) and surface it in `ls` output
- Docs
- Python not yet supported