langchain
https://github.com/langchain-ai/langchain
Python
⚡ Building applications with LLMs through composability ⚡
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 supported39 Subscribers
Add a CodeTriage badge to langchain
Help out
- Issues
- Add `BackendIntegrationTests` for Deep Agents `BackendProtocol` implementations
- Add Agent Magnet as a memory integration for LangChain agents
- Feature: Memory write validation hooks to prevent prompt injection persistence (OWASP ASI-06)
- create_agent discards state_schema subclass in inferred return type
- perplexity: _convert_message_to_dict drops AIMessage.tool_calls and raises on ToolMessage
- convert_to_openai_messages mutates the caller's input message in place
- feat(agents): AgentRuntime fields + _build_runtime hook for middleware
- AgentExecutor._execute_model_async uses ainvoke (non-streaming) — on_llm_new_token never fires; LangGraph use_astream=True does not enable token-level streaming
- fix(langchain): sanitize anthropic cache markers on fallback retries
- Agent factory _execute_model_async uses ainvoke (non-streaming) and cannot trigger on_llm_new_token callback; LangGraph use_astream=True only controls graph-level streaming not model token-by-token streaming
- Docs
- Python not yet supported