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
- Make memory write guidance configurable and support bounded, progressive loading
- compact_conversation skips _offload_inline_media: inline images lost from both summary and archive
- Summary input limit can produce a content-free compaction
- quickjs: let `CodeInterpreterMiddleware` run the REPL inline on the caller's loop (loops that cannot be woken from another thread)
- Extract Auto mode approval middleware for use outside dcode
- Extract persistent goals and acceptance-criteria generation from dcode into the SDK
- quickjs: JS `task()` subagent dispatch runs without the parent run's callbacks
- Dependency minimums raising is failing
- Track `ChatAnthropicVertex` prompt-caching parity and provider consolidation
- fix(sdk): preserve output from timed-out shell commands
- Docs
- Python not yet supported