{"id":"provos-ironcurtain","name":"ironcurtain","af_score":52.8,"security_score":63.8,"reliability_score":26.2,"what_it_does":"IronCurtain is a TypeScript runtime/CLI for autonomous AI agents that enforces a human-readable “constitution” (policy) compiled into deterministic rules. It mediates all agent tool calls via MCP servers (e.g., filesystem/git/github/workspace) and a policy engine that allows/denies/escalates actions for user approval, with agent code isolated in a V8 sandbox (builtin mode) or an external agent constrained by Docker + network/MCP mediation (docker mode).","best_when":"You want autonomous agent functionality (including mutations) but require a boundary that routes risky actions through explicit policy and interactive approval, with defense-in-depth against prompt injection/drift.","avoid_when":"You need a simple drop-in HTTP API service; IronCurtain is a local runtime/CLI with mediated tool calls and may require setup of multiple external integrations (LLM provider, optional GitHub/Google auth).","last_evaluated":"2026-03-30T13:41:37.708662+00:00","has_mcp":true,"has_api":false,"auth_methods":["LLM provider API keys (Anthropic/Google/OpenAI) via environment variables or config","GitHub Personal Access Token for GitHub MCP server","OAuth setup for Google Workspace MCP server"],"has_free_tier":false,"known_gotchas":["Default policy denies by default unless rules explicitly allow/escalate; agent may require policy compilation/constitution adjustments for desired actions.","Because escalations may be required for mutations, workflows that expect fully autonomous behavior may need auto-approval/whitelisting configuration.","Policy compilation uses an LLM pipeline to compile/verify; if the constitution or dynamic lists are ambiguous, enforcement outcomes may be surprising until revised."],"error_quality":0.0}