#policy-engine

Spending controls for AI agents paying online. Policy-gated x402 payments with audit log.

The trust control plane for enterprise AI agents — real-time policy verdicts in under 800ms and litigation-grade evidence of every decision. Pharos decides. Pharos proves.

Evidence router & policy engine for coding agents — enforces source choice and proof-of-use through Claude Code hooks, including routes to MCP tools. Local-first; no LLM in the hook loop.

AI-native Linux cognitive shell with typed actions, policy kernel, semantic runtime, and unified KDE/Web UX.

Local-first AgentOps control plane prototype for safe AI-to-agent command validation, policy evaluation, and redacted audit logging.

🐌 SlimyOS Habitat — A supervised autonomous Linux control plane. Policy engine, tool broker, proof packs, panic stop, failure memory. Agents can't misbehave.

Autonomous local SRE agent — ingests logs, detects anomalies, and routes all remediation actions through a policy webhook before execution. TDD-built, fail-closed, no cloud dependency.

Open-source trust layer for autonomous AI — gate agent, robot, smart home, and industrial actions before they run. Policies, HITL, Ollama/OpenAI, audit. MIT. npm @sanctum-runtime/sdk