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
- Incorrect error classification in LangSmithSandbox file transfers
- Add `ignore_case` to `FilesystemBackend.grep` for case-insensitive literal search
- Revisit developer experience for nested skill directories
- Async summarization can return before its admitted history write settles
- bug: ripgrep-backed grep retains CR in CRLF matching text
- compute_summarization_defaults does not scale trim_tokens_to_summarize to the model window
- Expose backend as a runtime capability and support typed platform extensions
- SkillsMiddleware silently skips SKILL.md files saved with a UTF-8 BOM
- Subagent structured output fails to serialize date/UUID fields in dataclass and TypedDict schemas
- No-op subagent duplicates inherited custom state with an additive reducer
- Docs
- Python not yet supported