Now in Deep Agents: Harness Profiles. https://lnkd.in/eCsFUueU ✅ Model-specific profiles to adjust prompts, tools, and middleware. 📦 Profiles for OpenAI, Anthropic, and Google models out of the box. 📈 A 10–20 point jump on a subset of tau2-bench over the default harness.
LangChain OSS
Technology, Information and Internet
Build reliable agents with our open source frameworks – LangChain, LangGraph, and Deep Agents.
About us
LangChain provides the agent engineering platform and open source frameworks developers need to ship reliable agents fast. Our open source frameworks, LangGraph, LangChain, and Deep Agents, help developers build agents with speed and granular control. LangSmith offers observability, evaluation, and deployment for rapid iteration. Our platform is trusted by leading AI teams at Zip, Vanta, Klarna, Workday, Linkedin, Cloudflare, and more.
- Website
-
https://www.langchain.com/
External link for LangChain OSS
- Industry
- Technology, Information and Internet
- Company size
- 51-200 employees
Updates
-
LangChain Community Spotlight: Distributed LangGraph Architecture with RemoteGraph 🔗 Production-ready example for distributed LangGraph apps with HTTP-invoked subgraphs. Key insight: RemoteGraph returns full state, not deltas—parents handle reducers. From Focused.io. 📦 https://lnkd.in/ggPYxyDM
-
-
LangChain Community Spotlight: Token Cost Attribution 💰 Simon Budziak shows how to track costs in multi-model pipelines using LangChain's `UsageMetadataCallbackHandler` and `get_usage_metadata_callback()`, with LangGraph for per-node tracking. Read the full guide: https://lnkd.in/g-q_UbVx
-
-
LangChain Community Spotlight: text2sql 🤖🗄️ An agentic text-to-SQL SDK built on LangChain's Deep Agents that autonomously explores schemas, writes queries, and self-corrects—achieving 100% accuracy on Spider benchmark with no RAG or pre-computed schemas. Check it out: https://lnkd.in/gmVAqvCq
-
-
LangChain Community Spotlight: Deep Agents + ACP Coding Agent 🛠️ Jacob Lee built a custom AI coding agent with Deep Agents and ACP that replaced Claude Code. Features multi-model support, LangSmith observability, and human-in-the-loop safety. Full guide: https://lnkd.in/ezP-2NVf
-
-
LangChain Community Spotlight: LLM-as-Judge in LangSmith 🎯 Simon Budziak published a technical guide on automated evaluation at scale using LangSmith's LLM-as-Judge, with 85% human alignment. Features Align Evals for self-improving calibration. 📖 Read the full guide: https://lnkd.in/gHA6MEHX
-
-
LangChain Community Spotlight: Saving $1M in LLM Costs 💰 Gustaf, an AI Engineer, shows how he reduced a production RAG chatbot's costs by 90% and improved latency by 82% through caching, intelligent routing, and LangGraph-powered context management. 📺 Watch the full breakdown: https://lnkd.in/gvJSAcwa
-
-
LangChain Community Spotlight: LangAlpha 💼 A coding tool built for Wall Street professionals, bringing AI-powered development to financial workflows. Check it out: https://lnkd.in/gTZEFywZ
-
-
🔒 Building in the enterprise? Cisco AI Defense Runtime Protection can integrate into your LangChain agents through middleware and produce a consistent runtime contract. https://lnkd.in/eEp9ymRt Cisco Senior Product Manager Siddhant Dash put together a quick look at why middleware is the right seam for agentic security, how Cisco AI Defense works with LangChain, and how you can get started today. Give it a read above!
-
-
🇮🇳 Hyderabad LangChain Community Meetup Join KnackLabs and Future AGI for a meetup on how scalable AI systems are built using RAG, agentic workflows, and production-ready architectures. What to Expect - RAG & agentic workflow deep dives - Real-world production insights - Architecture & reliability learnings - Networking with AI builders 🗓️ Saturday, April 18th | 🕜 1:30 PM | 📍 Hyderabad Big thanks to LangChain Ambassador Ravi Kiran for organizing! RSVP 👉 https://luma.com/ypzn1pfb