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
- Async subagent runs are not nested under the parent's trace
- Explicit ownership and sharing semantics for subagent learned memory
- Async subagents should be able to share the parent's filesystem / sandbox
- CompositeBackend.ls/als skip intermediate directories for nested routes
- FilesystemMiddleware can emit an unreadable /conversation_history/<uuid>.md reference after oversized HumanMessage eviction
- `task` tool discards the subagent's token usage, making subagent spend invisible to agent-state accounting
- `MemoryMiddleware` cannot distinguish project-authored `AGENTS.md` instructions from learned memory
- Avoid checkpointing middleware-loaded skill and memory content at every step
- Revisit memory middleware cache boundaries across model providers
- Expose public Harness Profile discovery and resolution introspection
- Docs
- Python not yet supported