Letting an AI coding agent run commands on your machine is convenient right up until it does something you didn't expect, deletes a file, reads a secret, or reaches out to a server it shouldn't. Grith sits underneath the AI agent at the operating-system level and checks every action before it happens. Grith is an OS-level security supervisor for AI coding agents, including Claude, Codex, Aider, Cursor, Cline, and Copilot, that intercepts Linux system calls, scores each action against 18 built-in security filters covering secret scanning, sensitive-path detection, egress policy, destructive-operation checks, and taint tracking, and automatically allows low-risk actions, queues ambiguous ones for human review, and denies high-risk ones, all through a single wrapper command with no agent-specific integration required. It keeps a hash-chained audit log and can run fully offline. MPL-2.0 licensed, freemium.
| # | Tool | Best for | Price |
|---|---|---|---|
| 1 |  Firejail | Développeurs | — |
| 2 | Développeurs | — | |
| 3 | Développeurs et équipes utilisant Claude Desktop ou Cursor avec des serveurs MCP tiers, soucieux de la sécurité des appels d'outils IA | — | |
| 4 | Site owners and developers managing AI crawler access | — | |
| 5 | Privacy-conscious users wanting model-agnostic AI access from their browser | — | |
| 6 | Developers wanting privacy/consent management integrated into their codebase | — | |
| 7 | IT/DevOps teams replacing corporate VPNs with Zero Trust access | — | |
| 8 | Businesses needing GDPR-compliant, frictionless bot protection | — | |
| 9 | Organisations d'ingénierie, équipes sécurité/conformité adoptant des agents de code IA | — | |
| 10 | Équipes MCP/API et sécurité déployant des agents IA | — | |
| 11 | Équipes DevOps/SRE et administrateurs système voulant un moniteur d'expiration de certificat sans dépendance pour cron/CI | — | |
| 12 | Équipes construisant des applications LLM soumises à des exigences de conformité (RGPD, AI Act) et de protection des données | — |
macOS app that intercepts and audits MCP server traffic between Claude Desktop or Cursor and connected tools for security oversight.
Free, in-browser generator for robots.txt and llms.txt files that control which AI crawlers can access your site.
Privacy-first browser side panel AI assistant that works with any model or agent and anonymizes sensitive data before it leaves your browser.
Open-source, developer-first privacy and cookie-consent infrastructure with headless consent flows and version-controlled policies.
Open-source WireGuard-based mesh VPN that replaces traditional VPNs with Zero Trust, identity-based device access.
Invisible, privacy-first bot protection using proof-of-work instead of visual puzzles.
Enterprise policy-enforcement layer that watches what coding agents do — prompts, commands, file changes — and blocks or alerts on sensitive data exposure.
Authorization layer that checks every AI agent action against a policy before it runs, with per-action revocation and a full audit trail.
A free Python command-line tool that checks a website's HTTPS certificate and tells you exactly what's wrong with it — expired, untrusted, wrong hostname — instead of a generic connection error.
An open-source trust-boundary gateway that sits in front of OpenAI, Anthropic and Gemini API traffic to redact PII, enforce rate limits, and track usage without touching your app code.
