Havuz

Open specs for AI agent credentials: a signed AI Passport carrying business context, and a one-call revocation check any gateway can enforce

r-doc, AI agent’ların bir projenin AGENTS.md ve docs/ dokümantasyonunu yönetmesine yönelik bir skill’dir.

Neden yükseliyor · 14 günlük repo yaşı içinde 40 commit, yeni ve sık güncellenen bir proje olduğunu gösteriyor; AI agent skill’lerine yönelik ilgi de görünürlüğüne katkı sağlamış olabilir. Ancak 43 yıldız ve tek farklı yazar, benimsemenin veya topluluk ilgisinin güçlü olduğuna dair sınırlı kanıt sunuyor; yükselişin kesin nedeni bilinmiyor.

The security-first skill manager for AI agents — every install runs a security scan. Manage skills & MCP servers across 90 agents. Zero-depe

Open-source Agentic workflows built using Rust

A face for AI agents: 30 expressions people read at a glance, lip-synced speech, and the Agent Face Protocol.

An end-to-end encrypted channel between coding agents, anywhere

Run your AI agents on machines you already own, as one private P2P mesh. OpenAI-compatible, sandboxed with Podman, signed reputation, no clo

Local AI multi-agent orchestration desktop app (Tauri · LangGraph)

A visual manager for fleets of Claude Code, Codex and Muse agents — real terminals, agents that message each other, teams that run tickets o

🛡️ Regex catches 0%, Meta's Prompt Guard 2 catches 1% of 629 realistic AgentDojo injection attacks when they're buried in tool output. Repro

Sandbox for running AI coding agents autonomously: isolated, network-restricted, host-safe

Run Claude Fable 5 + OpenAI Codex as co-founders in one Claude Code skill. Fable is the Visionary (plan, standards, review), Codex is the In

Stop debugging the same errors twice. CoMemor equips your AI coding agents with repository-scoped persistent memory, turning past command fa

Continue unfinished work across coding agents with portable handoff bundles.

Give ChatGPT a real terminal on your Mac. Open-source MCP bridge for shell, files, PTY sessions, jobs, and Codex history.

Your coding agent says "done". Orvant asks for proof. A skill for Claude Code, Codex and other file-capable agents, plus a Python engine tha

Version control and two-way sync for your AI coding agent's files: Claude Code's memory, skills and settings, files it edits, and companion

Persistent knowledge-graph memory for AI agents: MCP server on SurrealDB with spreading activation and decay

Policy guardrails for coding agents (Claude Code, Codex, Cursor) — every tool call is checked locally, before it runs.

Claude Code and Codex together: a local desktop app for chat, pair programming, debates, councils, and code reviews.

A local-first grokbot alternative. Imagine a discord pre-loaded with AI agent superpowers for you to manage life or even build a startup!

认识 Agentic AI：从神经网络到智能体

A pure-Python system that automatically discovers, verifies, and applies relevant historical requirements for coding agents — no embeddings,

A scrolling terminal multiplexer that tracks your AI coding agents.

DeepSeek Harness plugin: deterministic data profiling, cleaning, and verification (dsh-data-quality)

All-in-one Docker/Podman image: hermes-agent + hermes-webui + hermes-dashboard in a single container

CLI server for Zotero 7/8/9 — let AI manage your library. 70+ CLI commands for search, import, PDF, BibTeX, notes, and more. Works with Clau

Play three.js games on your retro handheld, and make your own with AI. A launcher, game store and starter kit for ROCKNIX and Android handhe

Claude Code skill + 18 AI agents for Android & iOS mobile app security audits. OWASP MASVS/MASTG-aligned, with adversarial exploitation conf

Omo Space: real AI agents at desks inside Minecraft. Hermes, Claude Code and Codex terminals on the walls, real web pages, agent players tha

Desk traffic light for AI coding agents: menu-bar app, terminal dashboard and DIY ESP32-C3 lamp for Claude Code, Codex, opencode and Copilot

A benchmark of AI QA agents finding real bugs in 4 open-source web apps, with 1,396 labeled bugs.

A local-first coding agent that doesn't take "done" on faith: the engine keeps the run going until the project's own tests pass, and every g

An extremely fast GitHub for pull request review: PRs open in 20 ms. Keyboard-first, macOS and Linux, CLI for coding agents.

Let your AI agent use your passwords and API keys - without ever letting it see them

DeepSeek Harness port of Claude Code Game Studios (CCGS v1.1.2, MIT) — one-package install: hook bridge (9 events), studio status line, self

Agentic development environment for your coding agents, built in public

AI agents worth falling in love with. Built by the community, loved by everyone.❤️

Managed LinkedIn MCP server for AI agents: search, connect, message and enrich on LinkedIn from Claude, ChatGPT or Cursor. 20,000+ accounts

Multi-model delegation for Codex: native and ACP workers, main-session context separation, and a local Dispatch dashboard.

Pitch your idea to a Shark Tank-style panel of Claude sharks who want to say no. A free Claude Code skill.

77+ free, open-source GTM skills for Claude Code, Claude.ai, Codex, Cursor and every AI agent: ICP research, prospecting, buying signals, co

Run your own AI team from your phone. Claude Code, Codex and more on your own server: shared tasks, always-on agents, a small composable bas

Claude Code skill: 5 AI agents analyze crypto, stocks, forex & commodities in parallel, adapt to your risk profile, and render an interactiv

Open-source MCP servers that let AI agents operate real lab instruments, with safety limits, read-only modes, audit trails, and a simulator

从 Java 开发者到 AI Agent 工程师的 30 天实战之路 | Spring Boot + Spring AI + MCP + Multi-Agent

A real Debian Linux terminal and AI coding agents (Claude Code, Codex, Gemini CLI, OpenCode, Cursor, Pi) on Android tablets and phones. No r

Multi-platform automated operation and publishing (Xiaohongshu / Douyin / TikTok / X / YouTube / WeChat Official Accounts) for Muse, Dots, a

A lightweight annotation standard that helps AI agents navigate codebases faster, with fewer file reads and tool calls

Your local-first command center for working with AI agents like a real team.