Claude
Tools

Release binaries for Verbative — voice control and a fully-local memory engine for the Claude Code CLI in VS Code. Hosts the on-device artifacts the extension and the verbative-memory packages install; no source code here.

metahub is building the missing infrastructure for AI tools, in the open — a registry that installs skills, MCP servers, agents and plugins into any harness, free publisher observability, and an eval framework going open source.

A grid of real, simultaneously visible terminal panes across projects, with a focus-following file explorer — VS Code extension

An extension of the UX+AI MCP. It makes the 101 methods easy to find and run with / commands.

A governed AI tool hub that removes the prompt — 16 cited-or-abstain tools across 4 platforms on one no-prompt shell, safe on sensitive data (PII/PHI sanitized before egress), with a measured 20/20 trust eval (0 hallucinations). Live demo included.

A Codex-native version of Anthropic's Claude PR Review Toolkit.

A belt of unrelated Claude Code plugins: guided branch review, context hygiene, and session status in the terminal tab or by ear.

Curated, continuously verified index of Claude Code and Agent Skills tooling. Every entry re-checked daily; anything archived, deleted or 90 days quiet is flagged and delisted.

A minimal but real LLM agent runtime — the core of a coding-agent harness (agent loop, typed tool protocol, provider abstraction, context management, permissions, and deterministic record/replay) in ~1.5k readable lines of Python.

Self-hosted AI assistant platform — chat, image gen, voice, RAG & tools, all running on your own GPU with Ollama.

The browser that writes its own extensions.

based on claude code

An Agent Skill that applies Anthropic's documented best practices for building with Claude: model and effort selection, prompt construction, subagent delegation, tool design, evaluation and guardrails.

Seedance 2.5 prompt optimizer and Agent Skill for Dreamina—write, audit, and repair text-to-video, reference-video, editing, extension, and multimodal prompts.

🧩Tracker-Free Drop-In Replacement for Claude Code: Decompose Claude Code's Harness into Open Source Extensions of Pi Agent.

Crea tu primera extensión de Chrome con ayuda de IA. No necesitas saber programar. AgentKit para Claude Code, OpenAI Codex y OpenCode.

Debug and fault-test any WebRTC session — Chrome extension, MCP server for AI coding agents, npm library, and Playwright plugin. Live RTCPeerConnection/WebSocket inspection, reconnect testing, network-loss simulation.

Local-first analytics for AI coding agents. Reads the session logs already on your disk — cost, cache efficiency, and tool-call effectiveness across Claude Code, Codex and more. No server, no account.

Human-approved bridge between AI agents and your database through Beekeeper Studio.

OmniProxy — Multi-provider gateway for Claude CLI & AI coding tools. Routes requests across Kiro (AWS), Codex (ChatGPT subscription), and external OpenAI-compatible providers with load balancing, token usage tracking, and a web admin dashboard.

Apple Ads Platform API MCP server. All 99 operations (Apple Search Ads + Apple Maps brand ads) exposed to Claude, Cursor and any MCP client through 4 token-efficient tools.

Hand your coding agent's context to the ChatGPT Web session already logged in in your Chrome — and pull a structured verdict back. Raw CDP, no extension, stdlib-only. 把编码 agent 的上下文交接给已登录的 ChatGPT Web 做独立审查。

A Diet Coke can that drains as you use your Claude limits — Claude Code status line, a live can in the terminal, and a floating macOS overlay. Unofficial CLI port of the Diet Claude extension.

Security-first, self-hosted MCP server for Firefly III — 152 operations behind 5 scoped tools, with stdio and authenticated HTTP.