{"version":1,"type":"story","url":"https://digestai.news/story/anthropic-releases-open-source-sandbox-runtime-claims-84-fewer-permiss","json":"https://digestai.news/story/anthropic-releases-open-source-sandbox-runtime-claims-84-fewer-permiss.json","markdown":"https://digestai.news/story/anthropic-releases-open-source-sandbox-runtime-claims-84-fewer-permiss.md","slug":"anthropic-releases-open-source-sandbox-runtime-claims-84-fewer-permiss","headline":"Anthropic releases open-source sandbox-runtime, claims 84% fewer permission prompts","summary":"Anthropic has open‑sourced its sandbox‑runtime (srt), an OS‑level sandbox that can wrap any process without containers. The npm package @anthropic‑ai/sandbox-runtime v0.0.81 is about 11.4 MB unpacked, licensed under Apache‑2.0 and requires Node.js 22.12+. It runs on macOS (using Seatbelt), Linux (bubblewrap, socat, ripgrep) and an alpha Windows build.\n\nAnthropic says the sandbox cut Claude Code permission prompts by 84 % in internal usage, a self‑reported figure. The tool enforces filesystem and network allowlists for the whole process tree, denying reads and writes unless explicitly permitted and blocking network traffic unless a domain is on an allowlist. Users can configure rules via a JSON file or through the TypeScript library.\n\nThe sandbox is positioned as a research preview; Windows support is still alpha and the performance numbers have not been independently verified. Developers can install it via npm and prefix commands with `srt`, or embed it in custom agents or MCP servers.","keyPoints":["Anthropic open‑sourced sandbox-runtime v0.0.81 (≈11.4 MB) under Apache‑2.0 for macOS, Linux and alpha Windows.","Internal Claude Code tests report an 84 % reduction in permission prompts, according to Anthropic.","srt enforces filesystem and network allowlists for entire process trees without using containers."],"whyItMatters":"Providing OS‑level isolation without containers lets AI agents run safer and with fewer approval prompts, lowering developer fatigue and reducing data‑exfiltration risk for emerging agent applications.","category":{"slug":"agents","name":"Agents & Tools","url":"https://digestai.news/category/agents"},"entities":{"companies":["Anthropic"],"models":["Claude Code"],"people":["Asif Razzaq"]},"firstPublishedAt":"2026-10-24T11:12:27Z","updatedAt":"2026-10-24T11:12:27Z","sourceCount":1,"hasPrimarySource":false,"sources":[{"outlet":"MarkTechPost","title":"Meet Anthropic’s sandbox-runtime: OS-Level Sandboxing for AI Agents, No Containers","url":"https://marktechpost.com/2026/10/24/anthropic-sandbox-runtime-ai-agent-sandbox","publishedAt":"2026-10-24T11:12:27Z","type":"press","primary":false,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"Anthropic releases open-source sandbox-runtime, claims 84% fewer permission prompts\", 24 October 2026, https://digestai.news/story/anthropic-releases-open-source-sandbox-runtime-claims-84-fewer-permiss","publisher":"Digest AI","title":"Anthropic releases open-source sandbox-runtime, claims 84% fewer permission prompts","datePublished":"2026-10-24T11:12:27Z","url":"https://digestai.news/story/anthropic-releases-open-source-sandbox-runtime-claims-84-fewer-permiss"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}