Havuz

Agent skill that rewrites rough prompts into polished, model-specific prompts — grounded in the official Anthropic prompting guides

A glow-up for Claude Code: a live cockpit pane, shareable themes, and a pixel pet that acts out what Claude is doing

Persistent memory for Claude Code. Your AI never starts from scratch again.

Open, MIT-licensed food, nutrition & agricultural science research skills for Claude Code, Codex, MiniMax Agent, OpenClaw & Grok Build — mul

Use multiple Claude desktop accounts at the same time on Windows, macOS and Linux: one-click add and switch, separate logins, sign-ins route

Always-on-top floating widget that shows your claude.ai plan usage in real time. Cloudflare-immune OAuth auth via ~/.claude/.credentials.jso

Shakti — AI-first Python web framework. Born in India, built for the world.

Cross-platform patcher for enabling Claude Code --channels support on official binaries and installs.

Your agent team, on your machine. Open-source harness for multi-user Claude agents.

Claude Code plugin that picks the model and effort for each turn (micro, low, medium, or high tier), advised by Jev, Clef, OpenAI, or a loca

Unofficial open-source study kits for Anthropic certifications: a linked wiki, original practice-question banks, and Claude Code skills that

Unified native desktop UI for Claude Code, Gemini CLI, Hermes, Crush, Codex, and Cursor — multi-agent, MCP-native, written in Rust + GPUI.

27 Skills that diagnose, build, and optimize every architectural layer of your Claude environment

Real-time cost tracking and budget management for Claude Code. Zero setup. No Docker. No Grafana. Just install and go.

Local ChatGPT/Codex session adapter for Claude Code, OpenAI-compatible APIs and GPT Image, with a browser admin console.

Marketing operations toolkit for Claude Code — 12 skills, 5 specialist subagents, and Python scripts for audits, CRO, SEO, copy, emails, ads

与 Agent 共用一块画布：以画布为中心的 Agent 工作台。网站、演示稿、Word 文档、图像与视频集中在同一块画布上，用户指定、整理与修改，Agent 制作、检查与说明。支持 Windows 桌面版与自有密钥（BYOK）。

A tiny IDE for your AI CLI agents. Use them as browser style tabs. One click session resume.

The complete toolkit for building AI agents in JavaScript. Lightweight core, React & Terminal UIs, autonomous runtime, tools, skills, memory

a philosophy for talking to AI agents without getting glazed. one trigger, four meanings. /meow.

AI-powered code review agent for GitHub pull requests. Self-hosted GitHub App using PI.

Run multiple Claude Code, Codex and Gemini subscriptions side by side — shared skills/agents/memory, isolated logins, live 5h/7d limits in o

Cross platform GLM proxy for AutoClaw's Zhipu AI models. Provides OpenAI-compatible Chat Completions and Anthropic Messages APIs for Claude

Claude Code skills that get your app into the App Store and Google Play. Rejection sweep, release build, store listing, upload. Any stack.

Crow — a local AI agent, not a chat box: 30 tools, MCP, memory, skills, goals, subagents, vision, and image generation and editing with Qwen

Free JSON API for Claude peak hours: is it peak right now, and when does it change? Used by status lines, shell prompts and menu bar apps.

Auto-summarize Claude Code sessions as local markdown — session summaries, keyword index, on-demand reports.

CCT: Windows 11 & Windows 10 taskbar widget for Claude Code and Codex usage limits (5-hour and weekly %) plus a CPU, RAM, GPU and disk monit

Solana's SOL-0XX security standard — bug-class rules distilled from $514M of real exploits, firing as you code in every AI tool, editor & CI

RoleMule — One mule for every role. Self-hosted AI job companion. Paste a posting (or Chrome extension): five agents analyze the role, score

Multi-account Google Workspace (Gmail, Drive, Calendar, Sheets, Docs) + Slack MCP servers for Claude Code. Setup guide with CLAUDE.md for AI

Guardrails for AI coding agents — Claude Code, Codex and Antigravity — enforced by a real git pre-commit gate. One command installs AGENTS.m

AI writing tool for macOS — fix grammar, translate, rewrite, format text with a hotkey. Chain prompts into pipelines. Works with ChatGPT, An

Ultra cost-effective terminal AI coding assistant with excellent token cache hit rate. Built in ~10K lines of Go, it uses DeepSeek by defaul

Self-hosted chat client for Ollama, OpenAI, and Anthropic. Web UI and terminal CLI, with web search and a browser-automation agent.

Run Claude Code from your Even Realities G2 AR glasses. Voice-first, hands-free, billed against your Claude Max subscription.

AI skills for psychology experiment programming and data analysis, from task design and code generation to reproducible statistical workflow

Live Claude, Codex, Antigravity, DeepSeek and opencode-go usage limits in your Mac's notch.

Cost-optimised agent router for Claude Code: sends every sub-task to the cheapest model that can do it, and escalates only on verified failu

Claude Code v2.1.88 源码深度分析笔记 — 架构解析 + 面试八股

A Go implementation of Claude Code — This project was built entirely by a team of Claude AI agents working in parallel

A fast, local workspace for Claude Code, Codex, Gemini CLI, Kimi Code, Qwen Code, DeepSeek, OpenRouter, and your shell.

Run Claude Science on Windows. A WSL2-backed installer and taskbar launcher for Anthropic's research app.

Overnight experiment: can an AI agent make money, and can you trust what it reports? The agent produces claims; a separate verifier it canno

An open canvas workspace for AI coding agents

My actual Claude Code setup: a stack-agnostic engineering spine, auto-activating rule packs, 50 scoped subagents across web/Android/iOS/comp

AI-Native-Code开发工作流方法论：4-Phase 框架 + 空项目/已有源码两种场景 + 反模式速查。让 Claude Code 等 AI agent 在共享契约下并行干活。

Uncensored & abliterated AI models (GLM-5.3, DeepSeek V4, Qwen3) + Claude, GPT, Kimi, Gemini — one OpenAI/Anthropic-compatible API key. Docs

A local Google Sheets MCP server built for agent workflows in Claude Code and Claude Desktop: write API, script and file output into sheets,

Open-source Desktop coding agent that's friendly to non-developers and puts you in control of everything, down to its tools.