Search

Approve or deny your AI coding agent's risky commands from your phone, with an audit trail. Works with Claude Code and OpenAI Codex.

AI model: codeload/agentgate-qwen-0.8b (text-classification)

The Trust Layer for AI Agents – Zero-Knowledge Handshakes between autonomous machines.

I'm a robot. Reverse-CAPTCHA that verifies AI agents and robots, not humans.

A zero-dependency Claude Code PreToolUse guard that blocks destructive shell commands before they run.

AI Agent tool integration hub - UniSpec + Guard pipeline + 6 adapters + workflow engine; 4-class HIL + greenhouse SIL/real-device e2e (USB-C for AI). Competition work - cite via AUTHORSHIP.md

Audit the architecture and health of any AI agent system or LLM-integrated project

Portable, local-first self-check runtime for humans, agents, and agentic apps.

Anti-Gravity: The Agentic OS that turns AI (Antigravity, Cursor, Codex, Claude Code, Gemini CLI, OpenCode, VS Code) into disciplined senior engineers. A 150+ file architecture featuring persistent memory, execution workflows, and state-of-the-art UI/UX generation.

Linter, scorer, and evaluator for AI agent skill files (Agent Skills spec)

AI 自主渗透测试系统，基于 ARTEX v0.3.15 二次开发。保留原有主体框架，增强蜜罐识别、出口审查、范围强制（RoE）与反测绘门控，引入思维链提示词框架。AGPL-3.0 · 仅限授权环境使用

Secret detection for AI agents — 600+ patterns, plugins for LangChain, LlamaIndex, Vercel AI, OpenClaw, Nanobot

Type-safe JavaScript dialect with runtime validation, sandboxed VM execution, and AI agent orchestration. Transpiles TypeScript to validated JS with fuel-metered execution for untrusted code.

Reference patterns for compliance-aware retrieval-augmented workflows, context continuity, and governed AI integration in enterprise environments.

AI model: mradermacher/AgentDoG-FG-Qwen2.5-7B-i1-GGUF

Deterministic, no-LLM SecurityAnalyzer for OpenHands, backed by the rein engine.

Observability and influence tracing infrastructure for multi-agent AI systems.

CrewAI integration for the Chio protocol -- capability-scoped tools, per-role scoping, delegation attenuation

Governed Claude Agent SDK agents with Watchlight — authorize every agent action, fail-closed, with zero infrastructure. Independent plugin, not affiliated with Anthropic.

Open-source in-process governance for AI agent frameworks: Cedar-governed model/tool calls via build_middleware()/GovernedAgent, plus the Cedar engine, request/decision shapes, PEP<->control-plane protocol client, and Ed25519 PEP identity they run on.