Havuz

Инженерный skill для проектирования, реализации, отладки и оценки AI-агентов в Codex и Claude Code по книге Bojie Li.

Personal AI agent harness powered by Claude Code. Always-on access through Discord, Telegram, or a built-in web UI.

Your app is guilty until proven secure: an agent skill whose /hack-me breaks into your own running app, proves each bug with a real request,

Advertising prompt agent for Image2: turns business briefs and reference images into debranded, production-ready image prompts.

Floating traffic light for AI coding agents (know when your agent is idle, thinking, or writing)

Validate, repair, and retry LLM structured outputs. 13 repair strategies for common JSON malformations, JSON Schema validation, and retry-wi

Browse, search, and export your Antigravity AI conversations — VS Code Extension

弦外之音 —— 微信聊天里的关系进展助手：读屏（无障碍树 / 截屏视觉）→ Jev 判读 + 攻略度 → 聊天模型出 3 条候选回复，攻略度常驻挂在屏幕上。不改微信、不发消息、不注入点击。

Protokół dla polskiej inteligencji.

ACP and MCP adapter that bridges TypeSafe Jev with any LLM — computer use and typed decisions alongside Codex, Claude, Grok, and OpenCode.

LLM terms explained from an engineering perspective with the production implications, not just the definition.

A Socratic supervision layer for AI coding agents.

Give your AI agent eyes and hands on any desktop — cross-platform accessibility API with MCP server

Agent Skills for working UX designers. Challenge ideas, find blind spots, use the real design system, preserve evidence and decisions, and c

Local-first reading workspace for technical papers — select an equation, figure, or passage and get grounded, step-by-step walkthroughs (wit

Open-source Claude Code plugin porting the internal /skillify skill: turn a finished session's repeatable workflow into a reusable SKILL.md

把你的手机变成 AI 手机：一个住在手机里的 Personal Agent，交代一句就替你办好。Turn your phone into an AI phone.

Make your agents learn from experience. One protocol for weights, harness and routing.

CLI output compressor for Claude Code. Reduces token consumption by 50–90% by compressing verbose command output before it enters the con

Offline-first Go CLI for engineering teams to observe AI adoption, compare estimated coding-tool costs and inspect bounded local delivery ev

Token-budget-aware graph navigation for AI coding agents. Serve exactly the noodles your LLM needs. 🍜

AI coding agent with more freedom.

Autonomous AI-powered penetration testing platform. LLM-driven recon, vulnerability analysis, and exploit validation for internal & external

AI Firewall & LLM security toolkit - protect your AI applications from prompt injection, jailbreaks, PII leakage, and adversarial attacks

See how you really use AI — X-ray your AI coding sessions locally

When asked to pick a random number between 1 and 100, ChatGPT does not follow a random uniform distribution

A design-of-experiments platform for evaluating compound AI systems - find which technique drives quality, by how much, and whether the di

Build and supervise scheduled AI workers with an open-source runtime, human approvals, run logs, REST API, and MCP tools.

Give the agent "this" and he gets a real PC.

From Pipeline to Council — A lightweight agentic framework for search & recommendation. 五个 Agent 重构搜广推管线。

LLM Steganography: Hide a meaningful text inside another plausible text of comparable length.

Production-oriented multi-agent course advisor with deterministic action governance, offline regression evaluation, SSE contracts and observ

🏙️ Public GitHub repos become a walkable 3D town. Traffic shapes the buildings, residents live there, and Gitber drives you to the right pro

Find the best AI models you can run

把多模型 Provider、本地密钥和 HeavySkill 讨论统一成 MCP 网关 | Local MCP gateway for multi-provider LLM routing, secrets, and HeavySkill discussions.

Outside-in replication of Anthropic's Mythos Preview / Project Glasswing — open-source agentic vulnerability-discovery scaffold on Claude Op

🚿 Llaminar: an LLM inferencing engine in C++.

Self-hosted meeting transcription portal — speech-to-text, speaker diarization, LLM-corrected transcripts, structured summaries and Word min

C# MCP server for kernel & user-mode Windows debugging — DbgEng COM, KDNET, Frida, dbgsrv, TTD, and integrated VM control. 29 tools for LLM

Persistent memory for Claude Code — 3-5x longer sessions, 60-80% fewer wasted tokens. Branch-aware, self-healing, token-efficient.

System-wide, on-device AI autocomplete for macOS — Copilot-style suggestions in every text field, fully offline and private.

Self-hosted LLM router. Cost effective, deterministic, and fast. Secure and private by default.

Dual-engine (llama.cpp + vLLM) LLM benchmarking pipeline for GGUF & safetensors on NVIDIA GPUs — speed, quality, live dashboard, publishable

Typed judgment tools for MCP agents. TypeSafe's Jev model as verify, screen, find, classify, rerank, decide, compare, extract, review, gate,

250+ real-world TypeScript AI projects: workflows, agents, and multi-agent systems with production-ready architecture, not chatbot demos.

454 standards-grounded Claude Code skills for every PDLC role. 8 roles, 57 plugins, 173 commands. Grounded in SWEBOK, TOGAF, OWASP, ISTQB, N

A collection of public writeups on attacks against AI agents: prompt injection, tool abuse, memory poisoning, and data exfiltration.

Fable-style spec + evidence gate for Claude Code + Codex. Makes Opus/Codex work under Fable-like discipline: blocks every edit until a deter

AI workers that turn GitHub issues into verified bug-fix pull requests: reproduce, fix with a regression test, prove it, open the PR. Runs l

把一批文章样本自动炼化成可复用的写作风格档案，并生成一个按该风格写作的专属 Claude skill。/ A Claude Code skill that distills writing samples into a reusable style profile and for