Search

Enterprise AI agent governance framework. Hook-based enforcement, compliance packs (SOC 2, HIPAA, GDPR, PCI DSS, DORA, EU AI Act, ISO 27001), audit trails, multi-LLM adapter architecture (Claude production today; additional providers on roadmap).

AI agent governance framework with audit trails, safety checks, and replayable decision making for autonomous systems

Nakagai edge: the connector runtime that holds your broker credentials

Local DeadBolt sidecar client and optional OpenAI Agents SDK function-tool integration

Universal Zero-Trust Gatekeeper for AI Agents (Shell & Web3). Stops prompt injections and wallet drainers.

Interactive terminal UI for exploring AppThreat atom files with AI agent

NotHumanAllowed — 38 AI agents + unified productivity suite. Gmail, Calendar, Drive, Contacts, Tasks, GitHub, Notion, Slack, voice chat, smart scheduler. Zero-dependency CLI.

xShieldAI / AEGIS DAN gate callback for LangChain agents — pre-execution governance via @xshieldai/aegis

Antarraksha AI Agent Enforcement SDK for Autogen

AI agent permission gateway - routes dangerous tool calls from Claude Code/Codex/Antigravity to your phone for approval

KYA (Know Your Agent) identity verification for CrewAI agents

A penetration testing agent powered by local LLMs via Ollama

Cognosys is an advanced AI-driven platform designed to streamline workflows and enhance productivity by automating routine tasks. By leveraging the power of AI Agents, Cognosys allows users to focus on more strategic and high-value activities, rather than getting bogged down with mundane, repetitive tasks. This innovative tool is versatile and integrates seamlessly with popular applications like Gmail and Notion, making it a perfect fit for modern, tech-savvy professionals aiming to optimize the

Keep your secrets on a leash — AI agent skill that catches exposed API keys, tokens, and credentials before they hit your codebase

TypeScript SDK client for the Argentor AI agent framework REST API

A pure, logic-only library for routing context, handling RAG fallacies, and managing context windows. Layer 1 Primitive - no agent dependencies.

Portless MCP server — persistent memory, local inference, and 44 tools for a personal AI agent system

DuckDB multi-org agent swarm with Spec Engine, 175+ SQL macros, meta-learning, MCP Apps, and smart extensions

Agent Policy Engine is an AI agent enforcement runtime (PEP) that prevents untrusted data from becoming executable authority in AI agents

Permission modes and a shell safety floor for opencode: static read rules, credential guards, a classifier consulted only when nobody can be asked, loop detection and secret redaction.