Action Control for autonomous agents. Check posture. Gate risky actions. Prove execution. Fits your existing agent stack.
🛩️ Git-native workflow control for coding agents: approved plans, verification, and reviewable evidence for Claude Code, Codex, Cursor, and Aider.
AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.
🛡️Decision infrastructure for AI agents. Intercept actions, enforce guard policies, require approvals, and produce audit-ready decision trails.
LLM guardrails & prompt injection detection for Python. Auto-instruments LangChain, CrewAI, OpenAI, LiteLLM + 8 more frameworks. PII masking, toxicity detection, policy CI/CD. One line, zero code changes.
AgentGraph: Trust and identity layer for the agent internet
The open agent control plane. Govern autonomous AI agents with pre-execution policy enforcement, approval gates, and audit trails. Works with LangChain, CrewAI, MCP, and any framework.
4 captures since 2026-05-22
AI agent config detected
Key config paths
AGENTS.md
CLAUDE.md