Havuz

Public, source-cited Fable 5, Mythos, Claude Code, and agent-operations second brain. Not affiliated with Anthropic.

NewAPI/Sub2API 中转站采集与 AI 模型比价平台，支持全网站点发现、模型价格监控、公告流、官方 API 状态、AI 热点资讯、在线对话和接口可用性检测。

Google Ads Agent Skills for Claude — campaign analysis, account auditing, safe write ops, PPC math, and MCP server integration

Slack-native governance substrate for Claude Code and peer agents: every tool call passes a tiered policy engine and lands in a hash-chained

Self-hostable MCP server with OAuth 2.1 — connect Claude, ChatGPT, or any other MCP-capable AI to your Lexware Office bookkeeping.

Desktop app built on Claude Code harness for proactive engineers.

DergiPark academic search as a Claude-in-Chrome skill (keyword + advanced field search, PDF→text, references) — no CAPTCHA, runs in your own

Claude skill: turn your current conversation into a complete handoff document so any LLM can pick up exactly where you left off

Unofficial study guide for Anthropic's Claude Certified Architect (CCAR-F) certification. Covers agentic loops, multi-agent systems, subagen

A2A protocol wrappers that turn AI backends into interoperable agents. Drop a JSON config, get a spec-compliant A2A server. Supports GitHub

Android SDK and MCP server: 157 tools for calendar, contacts, SMS, files, camera, sensors, notifications and UI automation, for on-device LL

Eco mode for Claude Code. /eco: -31% to -73% output tokens with critical findings intact; /eco-max: up to -75% with lowered effort. Measured

Cloak your Claude. Switch identities in seconds.

Give your CLAUDE.md / AGENTS.md a checkup — audit size vitals, dead references, drifted claims, and backtest every rule against your own ses

我们的港湾

Threat hunting command system for agentic IDEs

Deja de usar Claude Code como venía en la caja. Semáforo de contexto, modo conciso, 4 hooks que bloquean comandos destructivos y secretos, e

⚖️ TecJustiça PJe — extensão gratuita para o Chrome que ajuda a ler, analisar e organizar os processos do PJe: chat com IA sobre os autos (s

Evidence-driven production readiness checklist for shipping web applications with confidence

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

Assistente de IA avançado para a IDE Embarcadero Delphi (usando Open Tools API) com chat acoplável VCL/WebView2, streaming SSE e refatoração

A friendly, native macOS terminal with workspaces, a command palette, and live process icons, built on libghostty and SwiftUI.

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

💻 Keeps your Mac awake while your AI agents work. Built-in detection for Claude Code, Codex, Cline, Copilot plus presets for Gemini CLI, Ope

GJC(Gajae Code) 5구독 멀티벤더 셋업 — 3대 리서치(Codex/LLM Council/Opus ultracode) + 엔진 ground-truth + red-team 통합 가이드

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）。

Cross-vendor agent-to-agent protocol — Claude, Codex, and Gemini communicate via file-based P2P messaging.

BCI-assisted neurodivergent productivity suite — self-reported or EEG-driven cognitive metrics + an agentic AI task planner (Claude) that ad

An agent skill for deploying, operating, and automating workloads on Northflank. Includes guidance and references for services, jobs, addons

A skill that removes common AI writing tells, based on published AI-detection research

930+ AI-powered skills and 31 agent plugins for Claude Code, OpenAI Codex, Gemini CLI, GitHub Copilot, and Perplexity Computer. The largest

Adversarial multi-turn benchmark for LLM debate quality, using side-swapped matchups and multi-model judging to rank models by judged debate

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

Create an AI friend and build things together!

Persistent memory for Claude Code. Local SQLite + MCP + hooks.

🌀 MUSE — Memory-Unified Skills & Execution. A pure-Markdown OS for AI pair programming with lossless cross-conversation context management.

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

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

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

Distributed, objective-led control plane for Lean 4 formalization projects.

Glyph Studio (formerly Prevail): a private, local-first AI harness for your life. Part of the Glyph family.

Memory for AI agents that never leaves your device. Local-first, end-to-end-encrypted, zero-telemetry memory engine (Rust, MCP) — gives Clau

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

🔍 Detect AI-generated text and fingerprint which LLM wrote it. Open-source GPTZero alternative. Zero dependencies, works offline.

A wax-sealed feedback receipt between a human and their AI partner — rate it, seal it, let the agent learn without turning love into a check

Persistent, interactive MCP Apps for any MCP host: the AI builds an app once, you both reuse it — data outlives the conversation. Ships an e

ARC-DRAW is an SAP-aware Model Context Protocol (MCP) server for SAP Solution Architects. You describe an architecture in plain language; th

跨平台 AI 编程助手用量监控桌面应用 | Cross-platform AI coding usage monitor: track Claude / Codex quota, tokens & costs. Data stays local.

The Karpathy LLM Wiki pattern, productionized. MCP server that gives Claude a librarian for your Obsidian vault — graph traversal, auto-wiki