Radar / AI security / Claude-Cage
Claude-Cage: a lightweight VM that stops Claude leaking to the network
A lightweight virtual machine built for Claude that blocks network leaks, with multi-platform support, multi-account management, remote deployment and mobile control.
Why it matters
A sandbox that lets coding agents run with real isolation - no network exfiltration - aimed at users running Claude on machines they also use for sensitive work.
What you could build with it
A freelance developer could run client coding agents inside Claude-Cage on a shared workstation, so an agent working on one client's codebase can never reach another client's files or the network.
Does it hold up?
Too early to judge - the repo is 13 days old, the README is mostly in Chinese, and no independent review or usage report has surfaced yet; the star velocity shows demand for agent sandboxing, not proven reliability.
Built with Claude-Cage
- GitDiscover daily picks - Claude-Cagegitdiscover.org · Listed among GitHub's daily trending picks, gaining about 1,700 stars in 24 hours.
- Claude Cage: VM Sandbox for Claude Codeexplainx.ai · Deep dive on the proxy-only egress, fail-closed isolation checks and multi-account management; warns it is community tooling, not Anthropic-supported.
- Claude Cage: lock Claude Code to one IP, one clock and one browser in a 320 MB VMthe9.pro · Covers the 320 MB Debian guest, 11 startup isolation checks, and managing several Claude Code subscriptions with their usage windows.
Learn more
First spotted on github: source.
More AI security
NVIDIA SkillSpector: security scanner for AI agent skills, trending againNVIDIA's open-source SkillSpector scanner is trending on GitHub today: it audits AI agent skills before installation…security · JEV 0.75Cloudflare security-audit-skill: turn your coding agent into a security auditorA coding-agent skill for multi-phase security audits with independently verified, machine-readable findings.security · JEV 0.72Shannon: open-source AI pentester that reports only vulnerabilities it can actually exploitCLI agent that combines source-code analysis with live exploitation against web apps and APIs under a 'no exploit, no…security · JEV 0.71AiSOC: open-source AI security operations center with agent triageSelf-hosted SOC that fuses alerts into incidents and hands them to LLM agents that record every prompt and tool call…security · JEV 0.71Codex Security 0.10.0: OpenAI's agentic vulnerability scanner adds resumable scans and cost budgetsOpenAI released Codex Security 0.10.0 on 12 Nov 2026: the open-source CLI and TypeScript SDK that builds a threat…security · JEV 0.69iFixAi: independent auditing of AI agents in under 120 secondsiFixAi audits whether an AI agent is doing what it is supposed to do, run by a human or by the agent itself, answering…security · JEV 0.68
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.