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
- perf: OpenAI many-tool latency profiler
- refactor(sdk): move subagent initialization into middleware
- Native Communication and Coordination Between Peer-Level Deep Agents
- Glob rejects allowed absolute patterns when path is omitted under filesystem permissions
- fix(quickjs): uncontrolled resource consumption
- `dcode threads export` for a structured tool-call/approval audit trail
- Project-level approval policy file for fine-grained auto-approval rules
- Guest `try/catch` around `task()` swallows a propagated `GraphInterrupt`, so a HITL gate inside a dispatched subagent is silently skipped
- Resuming a HITL interrupt raised inside `eval` re-executes the whole eval body against the already-mutated REPL
- [Feature Request] Dynamic Tool Allocation (DTA) Pipeline for deepagents-code
- Docs
- Python not yet supported