AI for coding: LangSmith releases Sandboxes for running code safely
LangSmith has launched Sandboxes in general availability: an isolated environment built on kernel-isolated micro-VMs for safely running code generated by AI agents. Key features include state snapshots, parallel forks, service URLs and auth proxies. The tool suits coding agents, CI pipelines and data-processing pipelines.
AI-processed from LangChain Blog; edited by Hamidun News
The LangSmith platform has released Sandboxes, a secure environment for AI agents that generate and run code. It physically isolates execution from the main system and from sensitive data.
Why do AI agents need an isolated environment when writing code?
To prevent unauthorized access to sensitive data, host resources and other processes, LangSmith explains. Sandboxes run as kernel-isolated micro virtual machines that physically separate the execution of agent code.
- Nov 1, 2026Local models lose to Opus and Codex: 0.21 on a MacBook versus 1.00 for Codex
- Nov 1, 2026Kimi scores 96.2% on a 1C database analytics test and emerges as a fallback if Claude access is blocked
- Nov 1, 2026OpenAI Rewrites GPT Behavior Rules: Five Values and a Chain of Command
- Oct 31, 2026Author puts his script before an AI jury: the verdict cost 850 thousand tokens
Test Frontier LLMs & Autonomous Agents in One Workspace
Run Claude Opus 5.5, GPT-6, Gemini 3.1, and DeepSeek side-by-side in Nomad AI (nomadnet.ai) — unified model routing, deep research, and multimodal workflows under one subscription.
The AI world, distilled — once a week
Seven stories that actually mattered, hand-picked. No noise, no reposts, no press releases.
Done! Check your inbox for a confirmation.