Tools

Makes the agent reply in terse 'caveman' style, compressing only prose while keeping code, commands and errors intact, which cuts output tokens significantly. Comes with skills for short commit messages, code review and memory file compression; supports 30+ agents.

Makes the agent answer in terse 'caveman' style to cut output tokens, compressing only prose while leaving code, commands and errors intact. Includes a local proxy that compresses logs, test output and other input. Works with Claude Code, Codex and 30+ other agents.

Multi-agent investment research framework where fundamental, sentiment, news and technical analysts, bull and bear researchers, a trader and risk managers debate a stock and produce a report and rating. Covers US, Hong Kong and A-shares. Needs Python and an LLM API key; not investment advice.

OpenAI's open-source general-purpose speech recognition model. The whisper command transcribes many languages, translates foreign speech into English and writes subtitle files. Needs FFmpeg; faster with a GPU.

JavaScript, TypeScript and WebAssembly runtime with built-in formatting, linting, testing and compilation. Scripts get no file, network or environment access unless granted with --allow-* flags, making agent-generated scripts safer to run.

Google's official open-source terminal agent using Gemini models with a 1M-token context. Built-in Google Search, file and shell tools, plus MCP support. Personal Google accounts get a free quota.

Engineering skill collection spanning define, plan, build, verify, review and ship, with /spec, /plan, /build, /test, /review and /ship commands, including TDD, code review and web performance audits. By Addy Osmani.

Addy Osmani's production-grade engineering skill pack covering spec, planning, implementation, testing, review and shipping, with commands like /spec, /plan, /build, /test, /review and /ship. Supports both Claude Code and Codex.

For fuzzy requirements: the agent asks one question at a time with its own guess, clarifying users, motivation, success criteria and constraints, and restates the intent for your confirmation before planning. Needs you answering live, so not for unattended runs. From Addy Osmani's agent-skills.

Reviews code changes before merge across five axes: correctness, readability, architecture, security and performance. Works on code and PRs from you, other agents or other people, judged by whether they improve overall code health. Part of Addy Osmani's agent-skills.

Helps agents build frontends that don't look templated: picks a design direction first, then tunes layout variance, motion intensity and information density. Also includes redesign audits, minimalist and brutalist styles, and design reference generation.

Microsoft's cross-browser end-to-end testing framework: one API drives Chromium, Firefox and WebKit, npx playwright test runs tests in parallel and isolation, with auto-waiting and trace replay for debugging failures.

All-in-one JavaScript and TypeScript toolchain: a single bun binary is a Node.js-compatible runtime, package manager, test runner and script runner, with noticeably faster installs and test runs.

High-throughput LLM inference and serving engine: vllm serve starts an OpenAI- and Anthropic-compatible server in one command. Supports 200+ model architectures from Hugging Face, quantization and distributed inference. Aimed mainly at NVIDIA, AMD and other GPUs.

Official Storybook addon that exposes an MCP endpoint on the Storybook dev server so agents can look up component docs and props, write and preview stories, and run component and accessibility tests. Storybook must be running; AI features are in preview.

Official MCP reference server for reading, writing, editing, moving and searching local files within an allowlist of directories, adjustable at runtime through Roots. Handy for organizing documents from a desktop client.

Provides a sequential_thinking tool that guides the model to break complex problems into revisable, branching steps. Good for planning, analysis and tasks that need careful iteration. Official MCP reference server.

Gives agents the current time and IANA time zone conversion, detecting the system time zone automatically. No API key needed. Official MCP reference server, written in Python.

Official MCP reference server that fetches web pages and converts them to Markdown for the model, reading long pages in chunks from a given offset. Zero config, but it can reach internal network addresses, so use it with care.

Official MCP reference server for local Git repos: view status and diffs, stage and commit, create and switch branches, and search the commit log by date. Written in Python and runs with uvx; still in early development.

Baidu PaddlePaddle's official OCR and document parsing tool: the paddleocr command reads text from images and parses PDFs and scans into Markdown or JSON, supporting 100+ languages with models that run locally.

Official PaddleOCR MCP: text recognition and layout parsing for images and PDFs (PP-OCR, PP-StructureV3, PaddleOCR-VL), returning text or Markdown. Runs inference locally, or calls the official API or a self-hosted service.

Astral's extremely fast Python package and project manager written in Rust, replacing pip, pipx, poetry, pyenv and more. Supports lockfiles and multiple Python versions, and uvx runs Python tools without installing them.

Static site generator written in Go that builds Markdown content into docs sites, blogs or landing pages in seconds, with a local preview server and an asset pipeline for images, CSS and JS.