BriefsToolAvailable now1 min read

LangChain adds managed sandboxes to LangSmith for AI agents

LangChain released LangSmith Sandboxes, providing dedicated microVMs with kernel-level isolation for running AI agent code securely.

LangChain adds managed sandboxes to LangSmith for AI agents — image from LangChain
Image: LangChain

Summary

LangChain has introduced LangSmith Sandboxes to give developers a secure way to let AI agents write and run code. The sandboxes use dedicated microVMs for kernel-level isolation, include an authorization proxy to keep secrets out of untrusted code, and integrate with LangSmith, LangChain, and LangGraph.

What changed

  • LangChain launched LangSmith Sandboxes as a managed solution inside the LangSmith platform.
  • Each sandbox is backed by a dedicated microVM providing kernel-level isolation from the underlying infrastructure and other sandboxes.
  • An authorization proxy injects secure credentials into outbound traffic after it leaves the sandbox.
  • Developers can manage sandboxes using the same API and authentication used for other LangSmith functionality.

Availability

Available now

“If you are ready to use sandboxes to keep your agents both useful and secure, you can get started with LangSmith Sandboxes today following the documentation here .”

Founder takeaway

If you are building code-execution capabilities into your AI agents, evaluate managed microVM-based sandboxes to isolate agent execution and protect sensitive data from prompt injection risks.

Source

LangChainHow to Choose the Right Sandbox for AI Agents

Announced Checked

Researched and drafted with AI from the official sources above, then checked automatically before publishing. Spotted a mistake? Tell us.

SharePost on XLinkedIn

Related

More briefs

All briefs
  1. LangSmith adds coding agent reporting and outcome tracking — image from LangChain

    ToolBeta

    LangSmith adds coding agent reporting and outcome tracking

    LangChain updates LangSmith with new reporting features that link AI coding agent spend to GitHub pull requests and GitLab merge requests.

    LangChain1 min read

  2. Reson8 releases Rumble-2-Flash as an open 0.5B speech AI model — image from Hugging Face

    ToolAvailable now

    Reson8 releases Rumble-2-Flash as an open 0.5B speech AI model

    Reson8 released Rumble-2-Flash, an open 0.5B-parameter speech recognition AI model supporting over forty languages.

    Hugging Face1 min read

  3. NVIDIA releases RTX Spark compact desktops for local AI — image from NVIDIA

    ToolAvailable now

    NVIDIA releases RTX Spark compact desktops for local AI

    ASUS, Dell, and MSI launched new RTX Spark desktops to run local AI agents, generation, and model fine-tuning on Windows.

    NVIDIA1 min read

One email, every Monday

Briefs are published here through the day. Monday Heist is the email: one useful AI workflow, the files to use it, and the catch. The first issue is being prepared; subscribers get it first. Free, and you can leave in one click.

One email. Every Monday.