Agent Beacon is the world's first open-source telemetry layer for AI agents wherever they run: locally, in CI, in the browser, or in the cloud.

Let AI agents investigate and operate infrastructure through declared actions, bounded by policy and host-side checks. Approvals when required, with an audit trail. By Protectorate.

Evidence-grounded repository audit CLI - deterministic scanner, MCP server, live dashboard, and a GitHub Action that posts PR diffs.

Mantis Hack

Headless IDA Pro MCP Server

Local-first MCP gateway. One port for every tool and every AI client: lazy discovery (~90% token savings), tool integrity + quarantine, secrets in the OS keychain.

Deterministic safety solutions for probabilistic AI agents

Collection of agent skills to find vulnerabilities inside your web/mobile apps.

Kubernetes Skill for Claude Code and Codex. LLMs hallucinate a lot with K8s - KubeShark fixes this. It eliminates hallucinations and grounds your Kubernetes, Helm etc official best practices.

More than a skill manager — manage skills, MCP servers, plugins, hooks, CLIs, configs, memory & rules across every AI coding agent. 🌟 Star if you like it!

Playwright for coding agents. Benchmark Claude Code, Codex, Gemini, and OpenCode on your own tasks - and test that your skills, MCP servers, and CLIs work when an agent uses them. Sandboxed YAML suites, activation checks, A/B experiments, CI gates.

A browser runtime that lets AI agents control your real Chrome browser via MCP. Agents can explore websites, generate operation manuals, and reuse them to save tokens. AI操控你的真实浏览器。

SAIL V2 (Secure AI Lifecycle) as an agent skill — the full 91-risk catalog for AI/agent gap assessments, security roadmaps, and compliance checklists. Installs on Claude Code, Codex, ChatGPT, Antigravity, and any SKILL.md-compatible agent.

GitX is a portable AI-agent skill for creating clean Git commits, tagged branches, and safe pushes across Codex, Claude Code, Cursor, and other skills-compatible agents.

Cross-Code Organizer (formerly Claude Code Organizer): cross-harness config dashboard for Claude Code, Codex CLI, MCP servers, skills, memories, agents, sessions, security scanning, context budget, and backups.

Official command-line tool for Reolink IP cameras, doorbells and NVRs — LAN only, no cloud. Snapshots, PTZ, RTSP/RTMP stream URLs, two-way audio (talkback/TTS), motion and AI detection, event monitoring, VOD download. JSON output and a built-in MCP server. Works with Home Assistant, Frigate and go2rtc.

🌊 Lagune is your security copilot as you build, your Blue Team when you audit, whether you're a developer or not (no API key needed).

Local-first telemetry collector for AI coding agents — unified OpenTelemetry events for Claude Code, Codex, Cursor and more. Token usage, cost, traces and security audit, exported anywhere.

The full featured self-hosted Codex gateway, for teams, agents and you

Wassette: A security-oriented runtime that runs WebAssembly Components via MCP

Catch dangerous AI agent skills before they catch you. Zero-dependency security scanner for Agent Skills, SKILL.md and MCP configs.

Our agent harness: Skills, plugins, hooks, and utilities to improve the quality of your agent.

Self-hosted runtime control plane for AI agents. Observe or HITL approve or Block rogue tool calls before it executes: secret leaks, prompt injection, supply chain etc in a local dashboard. Agent agnostic (Claude, codex, langchain etc.)

An instruction layer for AI coding agent