Havuz

302API 开发者资料与接入示例：Python / Node.js / cURL、客户端配置、前端组件与本地账单验算器。Apache-2.0 开源，再分发请保留 NOTICE 署名。

OpenCode 2 plugin that uses your existing Claude Code credentials — no separate login needed.

Turn any course PDF into an interactive 3D pop-up textbook with your own AI (Claude, OpenAI, Gemini, Ollama or Claude Code). Runs locally, o

Fixes prompt cache regression in Claude Code that causes up to 20x cost increase on resumed sessions

Local, zero-dependency dashboard for Claude Code: live token usage and context, lost-session recovery, full-text search, and approve tool ca

Always-on durable pi agent on your server that you talk to in Telegram. Survives crashes and restarts, keeps history in SQLite. pi-durable T

Run Claude Code natively on Android via Termux or AVF (Android Virtualization Framework) -- no desktop, no SSH, no root required.

A loop engineering framework — state a Goal; Rounds run until a skeptical, read-only Verify agent settles it.

Infinite, 100% Free, Zero-latency Multi-provider AI Router for Claude Code CLI & Desktop with real-time SSE streaming, auto-failover across

Turn WorkBuddy / CodeBuddy (Tencent) quota into a local OpenAI + Anthropic compatible API. Zero-dependency Node.js, multi-account pool with

A local web panel for managing Claude Code skills — paste a GitHub URL to install, symlink-hosted with zero copies, plus a daily feed of new

Auto AI improver. Cost and token burn reducer, turn saver, and focus keeper for Claude Code, Codex, Copilot, Gemini, and more: surgical read

Proxy patch for Google Antigravity that intercepts internal Cloud Code API and adds support for OpenAI, Claude, Ollama, Gemini and any custo

Your AI usage, quota, and balance — as a desk pet. 🐾 A local companion service that normalizes every AI provider into one LAN feed, plus ESP

A feature-rich, dependency-free Node.js statusline for Claude Code with model, task, git state, context window, rate limits, and Anthropic p

Let an LLM write its own tools at runtime: parsed with acorn, versioned in SQLite, run in a supervised worker process

One command to install, heal & prove ruflo (claude-flow) + agentic-qe + RuvNet Brain — plus ambidextrous Claude/Codex/OpenCode host routing,

Self-hosted mobile web chat UI for Claude Code — drive your real local claude CLI from your phone. Same CLAUDE.md, MCP, skills, login; any g

Local multi-provider proxy for Claude Code — automatic failover, priority routing, auto-recovery, usage analytics, and a provider catalog

A TypeScript framework for building WhatsApp agents. Pluggable transports (Baileys, Cloud API, Twilio), a tool-calling agent core, and multi

Apple Icon Composer CLI & MCP server: create and manipulate .icon bundles and images with Liquid Glass rendering

AI coding runtime hygiene for Codex, Claude Code, Cursor, Windsurf, MCP servers, and safe workspace caches. Try: npx z-clean audit

Bring your own key (BYOK) relay to enable lightweight frontend-only apps to use LLMs using the user's API keys without hitting CORS.

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

Watch your Claude Code subagents work as a pixel-art office. Rewind any second, see what every agent cost, and turn any session into a timel

MCP server for Asterisk and FreeSWITCH. Lets AI assistants inspect channels, SIP registrations, trunk status and dialplan on a live PBX.

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）。

Minimal surface, complete architecture: a small, local-first coding-agent harness that re-derives the invariants of DeepSeek Harness with fe

Open-source LLM control plane: observe every call, recommend savings, then apply only human-approved, reversible routing.

Diff your AI agent's behavior between two runs. See exactly which tool calls, args, costs and outputs changed when you swap models or edit p

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

Lightweight cost observability for every API call in your stack. Track LLM tokens, database ops, and external services from your terminal.

Round-robin proxy for multiple Claude Max subscriptions — multiply your Claude Code throughput with automatic OAuth token rotation and trans

Discord Rich Presence (RPC) for Claude Code — live model, project, tokens, and lifetime stats in your Discord profile. Driven by Claude Code

Self-aware cognitive AI agent with a persistent soul: reads, modifies & verifies its own code, plans autonomously, dreams in idle time, reme

Local control plane for Claude Code on Windows and macOS: switch LLM gateways in one click behind a fixed endpoint, SSE keepalive proxies, k

Turn Claude Code into a plan-execute-validate loop with parallel work, intelligent retry, and memory

Turn your Mac/Linux into a remote Claude Code terminal via Telegram. Spawns real CLI — sessions, streaming, approvals, voice, git panel, 30+

Drop-in replacement for Claude Code's built-in WebSearch and WebFetch. DuckDuckGo-powered, no API keys, works on every provider.

Claude Code CLI — original source code snapshot for research. Property of Anthropic.

Humanize browser automation for AI agents, QA tests, and demos. Playwright-first — record sessions to video or runnable tests, and drive it

Run Claude Code agents on a schedule. They stay silent unless there's something worth telling you — a quiet day costs zero tokens.

Claude Code skill for building Ableton Live extensions with @ableton-extensions/sdk — API & concept references, project templates, a with-sk

Ben — an autonomous digital entity that lives on Crustocean

Windows computer-use MCP server: drive any desktop app via semantic discover-then-act targeting (entities + leases, not pixel coordinates),

AI agent toolkit for coding agents, unified LLM APIs, agentic workflows, tool harness and more.

Prismatic — a highly customizable, zero-dependency status line for Claude Code. Truecolor gradient model pills, a color-coded context bar, a

Structured output generation for LLMs in Node.js — token-level constraints for local models, native JSON modes for cloud APIs