Havuz

给 DeepSeek 装上眼睛 — MCP Server + 通义千问VL, 剪贴板图片→视觉模型→文字描述 / Give DeepSeek the ability to see images via clipboard + Qwen-VL

Web UI for remote control of Claude Code and Codex across multiple machines and nodes.

MOM is a persistent memory for AI agents — she remembers, so you don't have to_

Orquestrador de 5 agentes IA especializados para analise 360 de features com Claude Code. 1 comando, 5 perspectivas, 1 relatorio executivo.

Claude Code skill for using Codex CLI as an execution specialist for implementation-heavy coding work, multi-file refactors, and wrapper-bas

Finds the claims in your CLAUDE.md / AGENTS.md / skills that your code no longer supports. Zero-config, no API key.

Premortem skill for Claude Code — finds the concrete ways a plan could fail before commitment. Multi-agent silent scan, mitigation triplets,

15 executable skills that walk you through your first open source contribution. Works in Claude Code, Cursor, Codex, Copilot, Windsurf, Zed

Carves your agent's tool outputs down to what matters. Never cuts what doesn't come back.

AI agent (Claude Code + Codex) & system monitor for the Thermalright 9.16 LCD — native macOS

Idea-to-store autonomous harness for Flutter/Flame games across Claude Code, Antigravity, and Codex. Automates research, planning, design, g

MIT-licensed, backend-agnostic AI agent orchestration loop in Python: orchestrator→worker→reviewer as a deterministic harness. Drive coding-

The open-source marketing agent workspace for Claude Code. 42 commands, 12 hooks, 4 industry starters.

Multi-agent codebase review for PRs, CI, and downstream fork syncs.

Outsource your understanding. Capture every human-AI decision as a step in a trajectory; grade trajectories retroactively when outcomes land

Open-source cross-provider AI dev team for solopreneurs, built on Claude Code + Codex CLI. Claude plans and reviews what GPT builds; a zero-

A traceable personal memory layer that carries verified state across apps, models, and AI agents.

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

Yazilim projenize AI-driven gelistirme workflow'u kuran template sistemi. Bootstrap ile projenizi analiz eder, 40+ proje-spesifik dosya uret

A dual-path memory system for proactive agents. Facts and procedures in a local knowledge graph, exposed as a CLI, MCP tools and skills. No

Agent-native Stata CLI for AI coding agents (Codex, Claude Code, Cursor). Run .do files, inspect data, and return econometric results as JSO

AutoResearch + PromptFoo = AutoPrompter. Run it with Neo AI Engineer

💎 LaPis — Local AI memory for coding agents. Persistent SQLite memory for Pi, Claude Code, Hermes & MCP.

意图放大与 Goal Contract 协议，面向 Codex 和 Claude Code 的 goal Skill

Turn a one-line idea into a branch with tested, reviewed, committed code. The brainstorm-to-commit pipeline for Claude Code.

AI-powered architecture analysis plugin for Claude Code. Generates diagrams, detects anti-patterns, and scores your codebase 0-100.

SUPERCHARGE AI-assisted development by using Git. Cross-model review gates, evidence-linked closure, verification profiles, model-tier routi

A Claude Code skill that scaffolds ready-to-run LangChain Deep Agents and dcode CLI agents into any project.

Decoding Claude Code's leaked 512K-line source — hidden features, 43 tool definitions, system prompts, architecture patterns

RunAPI MCP server for model discovery, pricing lookup, media task creation, and balance checks.

A tool to monitor Claude Code and CodeX usage limits, quota, and token consumption — with both CLI and GUI | 实时监控 Claude Code 与 Codex 的用量、配额

Anthropic API reverse proxy with prompt-cache injection and request body transforms

Make your AI think like Munger, Feynman, or Paul Graham — load real mental models, not personas.

Claude Code plugin for autonomous AI research — multi-agent loops take a bare topic all the way to running experiments, with no human-writte

Architecture-aware code search, dependency graphs, and impact analysis for Python, TypeScript, Rust, C#, Java, Go, Ruby, Rails, Free Pascal,

Six Claude Code skills that harden Opus 4.8 toward frontier behavior. Written by Fable 5, pressure-tested on the target model with transcrip

Clyro is a governance platform for AI agents. While most tools let you watch agents fail, Clyro stops failures before they happen, catching

Claude Code skills that make Claude (Fable) the conductor of AI worker fleets: many parallel OpenAI Codex workers plus Opus design agents, o

On-demand design systems from any URL. Five surfaces, one agent: web, API, CLI, TypeScript SDK, and a portable agent skill that runs inside

A Claude Code skill that consolidates scattered project markdown files into a single canonical CLAUDE.md, with a pinned PROGRESS block at th

Local-first MCP server that gives coding agents structured context packets, code/schema facts, and diagnostics - backed by a local SQLite st

Open source Enterprise AI Gateway for API, MCP and agent, and AI model traffic. One Apache-2.0 binary: 72 native providers behind an OpenAI-

A blank, working source of truth for Claude Code and Codex across macOS and Linux.

Skill Claude Code de veille tech francophone. Agrège les flux RSS (Journal du Hacker, Human Coders News…) et produit un récap trié par jour.

The complete AI video-editing skill: from raw footage and creative direction to one verified final film.

Run a 28.9M-parameter TinyLM on ESP32-S3 with an RP2040 OLED display node for fully local embedded AI inference.

Minimal Cloudflare Worker that routes Claude Desktop/Cowork to OpenCode Zen and Go models

Your coding agents get an agreed plan, a check after each round of changes and a handover to the next session. Workflow plugin for Claude Co

Get Claude Code and other AI agents approved for use at work — deterministic guardrails on every tool call, tamper-evident audit logs, and a

Turn Claude Code into an autonomous software development team — 16 specialized agents, documentation-first pipeline, TDD slices in parallel