Local-first MCP and coding-agent reliability harness that captures bounded, sanitized failure evidence and generates deterministic executable regression tests. Capture is opt-in; no API key or hosted service is required.
An MCP server that lets AI models run code in 31 languages, evaluate symbolic math and logic problems, and measure complexity—exposed as 48 tools for execution, session management, translation, optimization, and more.
Runs AI-generated code in secure Firecracker microVMs with opt-in network policy enforcement, PII scanning, prompt injection defense, and audit logging. Exposes MCP tools for running commands, managing files, and the full sandbox lifecycle.