
LangChain
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.
Notable people
People map
Current peopleNotable public-facing people we cover. Grouped by public roles, not reporting lines; this is not a complete staff directory.
Leadership
- Harrison Chase
Co-founder and chief executive officer · 2023 – Present
- Ankush Gola
Co-founder and chief technology officer
Research
- Vivek Trivedy
Leading Applied Research
Other public roles
- Brace Sproul
Head of Applied AI · Mar 2025 – Present
Tools
- Deep Agentsdocs.langchain.com
LangChain's open-source agent harness with built-in filesystem access, subagent delegation, and shared memory.
- LangSmithlangchain.com
Tracing, evaluation, and monitoring for LLM apps, framework-agnostic and usable without LangChain.
freemiumOriginal source - LangGraphlangchain-ai.github.io
Low-level framework for building stateful agent workflows as graphs, with checkpointing and human-in-the-loop.
Writing, research & talks
Prime Intellect's Will Brown argues continual learning will become routine software lifecycle work. He covers evals as production metrics, choosing between SFT, on-policy distillation and RL, using RL for harness drift and routing, and when specialized models beat frontier ones.
- langchain langchain-core==1.7.0
github.comLangChain 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.
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.
LangChain's October roundup covers what shipped at Interrupt: LangSmith AI Search, Engine v2 with red teaming, Trajectories, Fine-Tuning via Baseten or Fireworks, Managed Deep Agents v0.9, and FastMCP support in LangChain 1.4.0.
- Nemotron 3.5 Super VL plugs into Deep Agents with LangChain benchmarksdocs.langchain.com
LangChain reports Nemotron 3.5 Super VL, NVIDIA's open-weight 120B model (12B active), averages 87% on its Deep Agents behavioral suite and finishes Harbor-lite tasks in 55% less time than DeepSeek V4.1 Flash. Integration docs show setup via ChatNVIDIA with thinking mode and image input.
LangChain announces that Claude Platform traces, including Managed Agents, Messages API and SDK calls with native OpenTelemetry support, can now flow into LangSmith in public beta for step-level agent debugging.
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 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.
LangChain's Managed Deep Agents 0.8 adds HTTP channels for any JSON webhook, user-scoped memory and credentials, Slack file transfer, and built-in Parallel web search. A walkthrough builds a receipt-logging agent reachable by text message.
LangSmith's new judge feature scores every production trace rather than a sample, checks more criteria per trace without cost scaling linearly, and can flag safety or security issues fast enough to trigger automated responses.
LangChain is turning decision models into a first-class LangSmith Gateway feature, starting with SemIf, an open-source decision model, free for a week and drop-in compatible with the TypeSafe SDK.
LangChain tests TypeSafe AI's Jev, a typed 'System One' classifier, against GPT-5.6 and Claude Sonnet LLM judges on a shared Deep Agents weather-task dataset. Jev showed 92-913x lower quality-score variance and ran at $0.00035/call versus $28 total for Claude, suggesting a new evaluator category for
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 positions its Deep Agents framework around built-in context engineering: filesystems, subagents, and skills wired up specifically to keep long-running agent tasks from overloading the context window.
LangChain details building its own paid-media marketing agent on Deep Agents: treating the agent as a knowledge worker with a sandboxed computer, using code for calculations and models for judgment, which grew paid pipeline from 0-20% and cut reporting costs 40x.
- Container-Based Regression Evals for Managed Deep Agentsvideo.twimg.com
LangChain's walkthrough of regression evals for Managed Deep Agents using Harbor. Each eval pairs an environment, an instruction and a pytest verifier, runs in a fresh container, and logs to LangSmith. Claude Code can scaffold the suite, and it can run nightly in CI.
LangChain has released Deep Agents Code (dcode), an open-source, model-agnostic coding agent, alongside a new LangChain Academy course covering installation and enterprise-oriented usage controls.
LangChain revamped its MCP integration: support for the new stateless MCP spec, the integration folded into the main langchain package, elicitation delivered through interrupts, cacheable list endpoints, and a new adapter built on FastMCP. Expect import path and adapter changes.
LangChain and Nevermined published a cookbook for letting an agent transact mid-task without a human in the loop. It covers delegating payment credentials under explicit limits, having the agent buy credits and top itself up to pay providers, and tracing each purchase in LangSmith.
LangChain's MCP integration picks up the updated spec's stateless transport, along with elicitation support. The linked writeup also puts numbers on MCP adoption: Tier 1 SDKs approaching half a billion monthly downloads, and MCP tool calls from ChatGPT up 98x across 2026.
- Do not grade a GPT agent with a GPT judgevideo.twimg.com
Unify's Connor Heggie, speaking on LangChain's Max Agency podcast, says the LLM judge should come from a different model family than the agent it grades. Same-family pairs share distributions and blind spots, so evals drift toward groupthink. This is practitioner advice without measured data.
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.
A Unify engineer explains why OpenAI's default prompt cache routing breaks down past roughly 15 requests per second per key, and how custom routing across keys kept cache hit rates near 95%. Based on a short podcast clip; implementation details are not shown.
OpenWiki 0.4.0 adds OKF v0.2 support and a claims runtime that keeps a persistent source of truth behind generated pages, surfacing which sources built a page, whether it is fully verified, and what produced it.



