LangChain Changelog

Sign up for our newsletter to stay up to date

Powered by LaunchNotes

Loading...

July 2025

Introducing Align Evals: Streamlining LLM Application Evaluation

Evaluations are a key technique for improving your application — whether you’re working on a single prompt or a complex agent. Iterating on evaluators has...

Keep external systems in sync with scheduled exports

You can now schedule automatic exports of your LangSmith traces, without needing to set up your own infrastructure. Whether you're syncing to a data...

LangGraph Platform

View deployment metrics in LangGraph Platform

You can now monitor your LangGraph Platform deployments directly from the LangSmith UI. View your deployment’s CPU & memory usage, API request latency,...

Set expiration dates on LangSmith API keys!

You can now set expiration dates on LangSmith API keys! Adding expiration helps you: Learn how to set and manage API key expirations in our documentation.

Create custom views when viewing evaluation results

You can now create custom views to highlight important information when viewing evaluation results in LangSmith: Docs:...

June 2025

LangGraph Platform

Run Agent Evals in LangGraph Studio

Get started with evaluating your agent directly from the UI — you can now run evaluations over your agent in LangGraph Studio with no code required! Test how...

Use built-in tools in LangSmith's Playground!

You can now call built-in tools from OpenAI and Anthropic directly from within the LangSmith Playground. Pre-configured tools, such as web search and MCP,...

LangGraph Workflow Updates (Python & JS)

We’ve rolled out a batch of new features across both LangGraph.js and LangGraph for Python — giving you faster development cycles, more efficient executions,...

Track costs across multi-modal inputs and token-caching

Cost tracking is especially important for agentic applications because resource usage is determined dynamically by the agent itself. Our new cost-tracking...

May 2025

LangChain Sandbox: Run untrusted Python in your AI Agents

LangChain Sandbox lets you safely run untrusted Python in your AI agents! Built on Pyodide (Python in WebAssembly), LangChain Sandbox lets you execute code...

Powered by LaunchNotes