The interface protocol for AI agents. 8 kernel primitives + 16 stdlib operations to operate any interface. Forge once, run forever — zero AI at runtime. 81 skills across 41 sites.
Enables AI agents to fork plans into counterfactual worlds, score them with rubrics and simulations, detect contradictions, measure regret, and merge a winner with a full audit trail.
Audits AI agent skills for safety using static, semantic, adversarial, and supply-chain analysis, providing scores and risk flags. Can be run via CLI, CI, or as an MCP tool from Claude Code, Cursor, and Codex.
Score your agent's governance (0-100), lint MCP tool definitions, and estimate costs across all major models. Free diagnostic tools with no API key needed. Expert skill files on governance, economics, and system architecture available with free tier.
AI agent provenance, trust, and auditability layer. VERITAS multi-gate scoring, Cortex approval gates, S.E.A.L. hash-chain audit ledger, and semantic RAG with cryptographic provenance tracking for every decision an agent makes.