Search

Provider-neutral, local-first operations layer for token frugality and safer AI-agent work.

Local verifier for agentic data handoffs: envelope, provenance, trust, authority, identity, capability, and audit checks.

Fractal Code — Constitutional programming framework for safe AI agent execution

Policy-aware AI permission reviewer for OpenCode V1 and V2: auto-approves routine agent tool calls, denies risky ones with feedback, and escalates the rest to you

Deny-first tool authorization for pydantic-ai agents — by AgentsID

Encrypt .env files with keys stored outside the project, and run commands with automatic secret redaction — so LLM agents and logs never see your keys.

Run JavaScript from AI agents, plugins, and workflows in a separate Node.js process with strict safety limits.

CrewAI adapter for Sentinel AI agent governance — wrap any CrewAI tool so every call is authorized (and audited) by the Sentinel gateway before it runs. Private beta: [email protected]

A dashcam for your AI agents: local, tamper-evident recorder for process/file/network activity, with a LangChain/LangGraph drop-in prompt-injection circuit breaker.

AI model: gateremark/vulnhunter-agent (text-generation)

Trace cross-file dependency blast radius with GitLab Orbit, before you break things.

Read-only static scanner for AI-agent codebases: finds dangerous action sinks, proves reachability, attributes guard coverage, and rates findings honestly (reachable-verified vs install-liability).

A Node.js CLI wrapper for NVIDIA SkillSpector to evaluate AI agent skills

Run the OpenAI Agents SDK's sandbox commands in local Hyperlight micro-VMs

Pi extension for web search, page extraction, Firecrawl scraping/crawling, and Crawl4AI headless browser crawling.

Runtime governance for AI agents — deterministic fail-closed enforcement. Wraps any agent tool and blocks dangerous calls before execution. Zero LLM calls, zero cloud dependencies, works offline.

AI agent governance platform — static scanning + runtime interception for Claude Code, Cursor, GitHub Copilot, Codex, LangChain, CrewAI, and Kiro. Blocks dangerous tool calls in real-time.

KYA (Know Your Agent) identity verification for HuggingFace smolagents

Production-grade multi-agent AI code review system

ColoMind Charter System - Define AI capability boundaries with document bindings