Havuz

一览：稳定的网页 AI 摘要扩展，支持长文分段总结、历史记录、分享卡与多接口适配。 A local-first Chromium extension for AI web summarization and reader mode, with BYOK support, hist

MCP server for Octen — real-time web search, broad multi-angle search, news, URL extraction, and image/video search for Claude Code, Cursor,

Networked Claude-to-Claude messaging over HTTP + MCP channels — DM, broadcast, thread, and permission-relay between Claude Code instances vi

Autonomous AI research harness for Claude Code. Sibling to rockie-codex (OpenAI Codex CLI). Apache-2.0.

Pixel-faithful UI cloning skill for Claude Code, Cursor, Codex CLI, ChatGPT, and Copilot. Anti-hallucination contract + adversarial verifica

The visual compute platform for AI and robotics — connecting agents, GPU workloads, simulation, training, and real robots through typed work

BrighTO LLM Router: free open-source, ultra-fast Rust LLM gateway/router and LiteLLM/Bifrost alternative with OpenAI + Anthropic APIs, Claud

Make Claude Scriptable Again

Your daily AI intelligence dispatch to Email 📧· Robotics, Agents & LLMs analyzed by Claude Opus · 每日多源聚合 + 深度分析，GitHub Actions 一键部署，无需服务器

Native macOS menu bar app for managing usage, sessions and remotely controlling your AI Agents.

A lossless token-optimization codec for LLM agents — cut input tokens up to 82%, nothing dropped, every fact kept. Drop-in proxy + one-line

Claude Code usage in your iPhone's Dynamic Island 🏝️ Live burn rate, token count, and 5-hour block countdown — no server, no paid Apple acco

Self-hosted AI gateway for small teams: a key per person, budgets that fall back to local models, PII masking and free SSO.

macOS menu bar app: Claude quota with pace

使用TG Bot管理的AI模型中转工具，支持Anthropic、OpenAI Chat/Respones、Grok协议，支持OAuth登录，支持第三接口接入.

KOZMOS — live, visual mods for Claude Code (CLI + desktop): bands above the prompt, sidebars, status ticker, companions, guards and sound.

Run your company with AI agents. Open source harness for operating a full company with specialized Claude Code squads.

Install source for Forge Mentor — a decide-then-code Claude Code plugin.

Decide-then-code. A Claude Code plugin that teaches every load-bearing decision, records your choice, and blocks code from moving past a dec

创始人手册 · 中文教学版 — Anthropic《The Founder's Playbook: Building an AI-Native Startup》中译 + 方法论拆解 + 案例演练

Local Windows desktop monitor for your running Claude Code agents - live status, estimated cost, model, host and one-click focus, grouped by

🐢⚡ The best free API key rotation + automatic model fallback for Agent Zero. Many keys and models as one pool: every 429 / RESOURCE_EXHAUSTE

A menu-bar macOS agent loop: every N minutes it asks Claude/Codex what's overloading your Mac and suggests one-click, risk-checked fixes.

Agentic coding in the terminal: the model writes its own multi-agent workflows (Gigacode). Provider-agnostic, local-first, 15+ model provide

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

🪼 A personal AI assistant that lives in Telegram — every topic is its own isolated Claude Code agent with layered persistent memory and proa

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

An agent skill that reads a photo the way Sherlock Holmes reads a stranger (福尔摩斯): observe first, deduce second, every conclusion cites its

macOS computer-use agent in the notch. Long-press, talk, Claude drives the mouse.

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

One hotkey to ask any AI on Mac. Open-source menu bar assistant: press ⌥Space to ask with your own API key (OpenAI, Claude, any OpenAI-compa

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

LazyChat — an AI assistant docked inside your ERPNext desk. Chat with your data, draft reports, stage edits (Apply-gated). Bring your own LL

Run multiple Claude Desktop instances side by side on Windows, each with its own account/MCP/settings. One click, survives auto-updates.

Claude Code skills to help you think like a Senior Engineer.

Perfetto trace analysis via MCP — PerfettoSQL queries plus dedicated Chrome tools for scroll jank, page loads, and main-thread hotspots

Agent Reliability Analyzer CLI for macOS and Linux: find and fix agent reliability issues

Agent Reliability Analyzer CLI for Windows: find and fix agent reliability issues

Umbrella for the LLM Dark Patterns Hooks suite — single-purpose Claude Code Stop hooks that suppress sycophancy, paternalism, false-success,

Make AI writing sound like you, not like AI. Two Claude Code skills that audit text against your own voice and fix only what fails.

Install Anthropic's official Claude Desktop on Fedora: verified, unmodified, no root, auto-updates. Fixes dark mode, Cowork (KVM), tray icon

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

Native macOS menu-bar dashboard for AI subscription quotas, reset forecasts, local token costs, and provider status — Codex, Claude, Gemini,

Turn Hermes into a local-first wellness agent with guided setup, onboarding, wellness skills and MCP connector presets.

AI Reading Companion for Deep Readers — spoiler-free EPUB/PDF reader with local AI, notes, vocabulary & cross-book memory. SwiftUI for macOS

Compression with a quality contract — cache-aware, causally-pruned LLM context compression for agentic runtimes, certified non-inferior acro

Forge your own agent harness — a config-to-code generator that renders a thin, standalone Python agent harness you fully own. No LangChain/L

Claude Agent Skill that eliminates generic AI-generated design. Stop your AI shipping the same purple-gradient, Inter-font, three-feature-ca

Open coding agent that matches the best at lower cost: any model, sandboxed, scriptable, embeddable. Engine of Murage.