LangChain
3 Tools · 60 Intel
LangChain is an AI infrastructure company that builds tools for developing applications powered by large language models. Founded in 2022 by Harrison Chase as an open-source Python framework, the company has since launched LangGraph for agent orchestration and LangSmith for AI observability. It has grown into one of the most widely adopted open-source AI frameworks and was valued at roughly $1.25 billion following a 2025 funding round.
Is this you? Sign in with X to claim this profile.
Tools
Low-level framework for building stateful agent workflows as graphs, with checkpointing and human-in-the-loop.
LangChain's open-source agent harness with built-in filesystem access, subagent delegation, and shared memory.
Tracing, evaluation, and monitoring for LLM apps, framework-agnostic and usable without LangChain.
Intel
LangChain 1.4.9 adds standardized model refusal content blocks in core and raises the minimum langchain-core requirement to 1.7.5, giving agent builders one consistent way to detect refusals across model providers.
Numan describes its eval-first approach for a regulated health-coaching agent on LangGraph and LangSmith: per-category LLM judges, simulated patient conversations, in-graph safety guards, and clinician-authored rubrics that gate safety claims.
OpenWiki extended its coding agent integrations to Cursor, joining Claude Code, Codex and OpenCode. Setup is a global npm install of openwiki@latest followed by openwiki integrations install cursor.
LangChain released Managed Deep Agents 0.9 with a Reactions API for Slack channels. Builders can generate loading indicators and acknowledgment receipts using heuristics, decision models or custom logic.
LangChain core 1.7.0 changes streaming: tool-call arguments are emitted as tool-call-delta slices rather than block-delta snapshots. Final tool_calls and output are unchanged, and pinning below 1.7 preserves the old snapshot behavior.
LangChain launches LangSmith Fine-Tuning in public beta with the smithtune CLI. A coding agent pulls traces, a multi-judge council filters them against a rubric, then the CLI prepares splits, trains on Baseten or Fireworks, evaluates against the base model and deploys.
A LangChain case study describing how Stripe's AI platform team built Kai, an internal 'Knowledge AI Platform' agent used by every employee, on top of LangChain's open-source Deep Agents harness. It details Kai's layered architecture (Deep Agents core, a Stripe-specific security/infra harness, and a configuration layer for custom agent personas) and how it connects to Stripe's data warehouse, Slack, and Google Suite via a library of over 1,000 skills contributed by 100+ teams.
LangChain describes Deep Life Sci, an open source agent harness built on deepagents that pulls from 600k+ clinical trial records and tens of millions of PubMed papers, using sub-agents and sandboxes for pharma R&D tasks.
LangChain ships langchain-typesafe 0.0.1 with TypeSafeClassifier, experimental AutoModeMiddleware and ModelRouterMiddleware, invocation-scoped classifier questions and usage-metadata tracing.
📦 Try Out Kimi K3 in LangSmith LLM Gateway Run agents with Kimi 3 using just your LangSmith API key. LangSmith now provides access to open models out-of-the-box, powered by @FireworksAI_HQ. Get started today → https://t.co/z5wCvrOpua https://t.co/XDJDJuABP0
A production account of why a single agent with a growing toolbelt got worse as it got more capable, and what replaced it: an orchestrator, permission-aware context retrieval across boards and files, specialized subagents with bounded responsibility, and sandboxes for agent-written code.
LangChain ran NVIDIA's Switchyard router through its 145-task Deep Agents eval suite: 93% of turns went to a 30B model and only 7% needed Claude Opus 4.8, cutting total cost about 70% while keeping roughly 90% of Opus's accuracy.