AI Coding Live News

LangChain Raises $300M Series C at a $3B Valuation Led by CapitalG, Betting on LangSmith to Run, Improve and Govern Agents, With New Features Due November 20

LangChain co-founder and CEO Harrison Chase announced on November 13, on the company blog and on X, that LangChain has raised a $300 million Series C at a $3 billion valuation. Existing investor CapitalG led the round, with new investors GIC and DFJ Growth and existing investors IVP and Sapphire Ventures, bringing total funding to $460 million. The money backs LangSmith, its framework-agnostic agent platform, which the company says more than 7,000 organizations use; new LangSmith capabilities will be shown at a release event on November 20.

Key Takeaways

  • The numbers: a $300M Series C at a $3B valuation, bringing total funding to $460M (LangChain blog, Business Wire release)
  • Investors: CapitalG led, with new investors GIC and DFJ Growth and existing investors IVP and Sapphire Ventures; Salesforce Ventures, Insight, MongoDB Ventures and others joined, and Sequoia and Benchmark doubled down
  • LangSmith is pitched as a framework-agnostic platform with three pillars, Agent Runtime, Agent Improvement and Agent Governance, running in LangChain's cloud, self-hosted, or in a customer's own AWS, Azure or Google Cloud account
  • Scale figures are company-reported: more than 7,000 organizations use LangSmith, and CapitalG says the open-source projects have passed 1 billion downloads and now see more than 350 million a month
  • Next up: a special release event on Friday, November 20 (US time) with several new LangSmith capabilities; the features have not been disclosed in advance
Read full story
Linked Models & Agents:

ScaleDown ships Constrained Decoding Models: 1M-token task models for summarize, compress, extract and classify, with LangChain Deep Agents middleware

On Oct 13 ScaleDown launched Constrained Decoding Models (CDMs): each model is trained for a single task and only returns answers that task allows (a label or spans of the input) instead of free-form token-by-token generation. LangChain shipped a langchain-scaledown integration and LangSmith LLM Gateway support the same day, with middleware for history summarization, tool-result compression and structured extraction. ScaleDown claims 200x faster and 467x cheaper than frontier models on these narrow tasks; Extract and Summarize are on OpenRouter at $0.04 per million input tokens.

ScaleDown ships Constrained Decoding Models: 1M-token task models for summarize, compress, extract and classify, with LangChain Deep Agents middleware

Key Takeaways

  • Four single-task models (Summarize, Compress, Extract, Classify), each taking up to 1M input tokens; Extract, Summarize and Classify accept images and scanned PDFs
  • Vendor-reported: vs the average of GPT-5.5, GPT-5.4 Mini and GPT-5.4 Nano, Summarize is 41x cheaper and 2.7x faster, Compress 138x cheaper and 1.8x faster, both with higher accuracy
  • Classify vs Jev: Jev is text-only with 32K tokens of state per question; Classify takes 1M tokens plus images and adds a one-sentence reason per decision
  • LangChain's trace example compresses a docs page from 18,402 to 3,110 characters; if a ScaleDown call fails the middleware leaves history untouched and the agent keeps running
  • On OpenRouter, Extract and Summarize cost $0.04/M input tokens with 1M context; Summarize caps output at 4,000 tokens and neither supports tools or response_format
Read full story
Linked Models & Agents:
⚡ ScaleDown Classify-1⚡ ScaleDown Extract⚡ ScaleDown Summarize⚡ ScaleDown Compress🤖 LangChain Deep Agents🌐 ScaleDown🌐 LangChain🌐 OpenRouter
L
LangChain@langchain-ai·
👀47
🔥88

LangSmith SDK 0.14.2: Python ls.address agent handle, JS OTel tool fields, primary replica keeps original run ids

LangSmith SDK v0.14.2 (2026-09-30): Python ls.address (#3581), JS OTel tool fields (#3592), primary replica keeps original run ids (#3623).

LangSmith SDK 0.14.2: Python ls.address agent handle, JS OTel tool fields, primary replica keeps original run ids

Key Takeaways

  • Release v0.14.2 at 2026-09-30T14:41:07Z; PyPI langsmith 0.14.2
  • Python ls.address agent addressing (#3581)
  • JS OTel tool name/call_id/definitions (#3592)
  • Only primary write replica keeps original run ids (#3623)
  • Compare ahead_by 8; docs https://docs.smith.langchain.com/
Read full story
Linked Models & Agents:

LangSmith SDK 0.14.1: address runs/feedback by agent, sandbox delegated login, Claude SDK + OTel trace fields

LangChain shipped LangSmith Python SDK 0.14.1 on 2026-09-25 (rolling in 0.14.0): address runs and feedback by agent rather than only by project; sandboxes can receive delegated LangSmith access and login service URLs (JS too); ClaudeSDKClient.receive_messages() is traced with stop_reason plus tool/response IDs; OTel exports add tool_call_id, tool_definitions, and finish_reasons. JS package moves to 0.10.5.

LangSmith SDK 0.14.1: address runs/feedback by agent, sandbox delegated login, Claude SDK + OTel trace fields

Key Takeaways

  • Shipped: Python 0.14.1 / JS 0.10.5 — pip install -U langsmith
  • Address runs and feedback by agent, not only by project
  • Sandboxes get delegated LangSmith access + login/service URLs
  • ClaudeSDKClient.receive_messages() traced with stop_reason and tool/response IDs
  • OTel exports tool_call_id, tool_definitions, finish_reasons; list_runs can return s3_urls attachments
Read full story
ADSponsored

LangChain Launches Managed Deep Agents Public Beta with Scaffold CLI, Hosted Infra, and Harbor Evals

LangChain opened the public beta for Managed Deep Agents, providing CLI scaffolding, LangSmith-managed infrastructure sandboxes, and integrated Harbor behavioral evaluations.

Key Takeaways

  • Agent PaaS model matures: packages scaffolding, isolated sandboxes, and behavioral evals into a unified deployment flow;
  • LangSmith expands into the production control plane managing long-horizon agent runtimes and state;
  • Harbor evaluation suite embeds into CI/CD pipelines to enforce automated behavioral quality gates before release.
Read full story