Join LangChain and Fireworks August 25th for a hands-on workshop where you'll learn to train a model yourself, followed by a rooftop happy hour. Evals are the foundation for all system improvements, but building agentic systems is challenging. Human-in-the-loop evaluations are costly and time intensive, while LLM as a judge systems can be unreliable and subject to bias. In this workshop, you'll learn to build customized eval models that you can leverage in LangSmith to optimize your agent performance. RSVP here:

New langchain python release! 🚀 Highlights: • Internal middleware model calls no longer leak into messages / event stream ( reported by • SummarizationMiddleware retries failed summaries (reported by + faster token counting for tool schemas • Batch of langchain-anthropic bug fixes ( • OpenRouter preserves provider info in response metadata ( This release also includes cross-provider standardization of reasoning effort, including supported values per-model in model.profile: Huge thanks to our external contributors for helping to shape and improve our harness!

ICYMI: @LangChain Deep Agents on @nvidia Nemotron 3 Ultra. frontier open-model agents at ~10x lower cost than closed. Run on Fireworks, then post-train it into specialized intelligence you own.

Are you heading to @LangChain Interrupt26, NYC? Stop by our booth, say hello, and join the closing reception we're sponsoring from 5:00-6:30pm. During the event, you'll hear keynotes from industry leaders, have access to hands-on workshops, and see LangChain agents using real-time web retrieval with Tavily. After the event, we're hosting an exclusive dinner with Nebius, where our Founder and CEO, Rotem Weiss, and @nebiusai's Developer Relations Advisor, Rob Spectre, will get the conversations started on what it takes to move agents from demo to production. Request to join the dinner:

Our partners @LangChain generate billions of tokens of agent traces a day, their richest signal on how real users react. Judging every one with a frontier closed model like GPT-5.5 or Opus is too costly, so they fine-tuned a Qwen base model on Fireworks that matches it at up to 100x lower cost. Build your own frontier:

Now you can learn LangChain using your favorite coding agent with LangChain Academy Tutors. Tutors use skills to teach concepts, ask questions, run quizzes, and give feedback. You can also customize the teaching style to match how you learn. LangChain Academy:  LCA Tutors Repo: 

What's new in LangChain? 🚀 🔌 Support for OpenAI's 3.0 SDK (using httpx2) ✨ Support for gemini-3.7-flash Plus a wave of core reliability fixes from external contributors: 🛠️ Tool calling & structured output: clearer errors, respect for pydantic aliases when validating tool inputs ( 📊 Usage metadata fixes: token usage callback bugs, and cost metadata when streaming OpenRouter ( 🧱 Content & prompt hardening: guard malformed Anthropic content blocks, and preserve non-str/non-dict items in prompt templates for content blocks ( Huge thanks to everyone who contributed! 🙏

.@Toyota builds its manufacturing agents on LangChain, and uses LangSmith to spot failed tool calls, broken pipelines, and frustration signals before they become bigger problems. An inside look at how the two work together to keep production moving.