ツール

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.

Frontend design polish skill: one skill with 24 commands such as polish, audit, critique and typeset, plus 61 deterministic rules that catch typical AI-generated UI problems, with live iteration in the browser. Works with Claude Code, Codex, Cursor and others.

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.

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.

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.

MCP server built into the adaptive Python scraping framework Scrapling: supports plain HTTP requests, browser rendering and stealth fetching, and uses CSS selectors to pass only the target content to the AI, saving tokens and filtering out prompt injection.

Adaptive web scraping framework: scrapling extract turns a page into Markdown, text or HTML in one command, with CSS selectors and browser rendering for dynamic pages, plus an MCP server (needs the ai extra). Needs Python 3.10+ and a browser install on first use.

Open-source, LLM-friendly web crawler that turns pages into clean Markdown for RAG and agents. Ships the crwl CLI and supports deep crawling and question-driven data extraction (extraction needs an LLM key). Free to self-host.

Document parser from OpenDataLab that turns PDFs, images and Office files into Markdown or JSON, handling tables, formulas and complex layouts well, with page-by-page reading and citation anchors for agents. Parses locally by default; needs Python 3.10+.

Multi-agent orchestration framework formerly called Claude Flow: ruflo init gives Claude Code nearly 100 specialized subagents, swarm coordination, cross-session vector memory and hooks; add --codex to configure Codex instead. Also works as a standalone MCP server or plugin marketplace.

Multi-agent orchestration framework for Claude Code and Codex, formerly Claude Flow: swarm coordination, self-learning memory and cross-machine federated communication. The marketplace offers 30+ plugins; full features need npx ruflo init.

Job search system that runs in your local AI coding CLI: scans job portals, scores roles with a structured A-H evaluation and a 1-5 rating, flags fake listings, tailors ATS resumes and cover letters, and tracks applications. Never submits for you. Needs Node.js.

Classic open-source OCR engine and CLI that reads text from images and outputs plain text, hOCR, searchable PDF or TSV. Supports 100+ languages; install the language data for each language you need.

All-in-one LLM fine-tuning framework: llamafactory-cli handles pretraining, SFT, PPO/DPO alignment and LoRA/QLoRA training, plus chat inference, weight merging and export, and OpenAI-style API serving for 100+ open models. Has a Web UI; training usually needs a GPU.

Write videos in HTML, CSS and frame-seekable animations, preview them from the CLI and render deterministic MP4s. Comes with agent skills for product launch videos, captions and talking-head re-edits. Maintained by HeyGen; needs Node.js 22+ and FFmpeg.

HeyGen's official HyperFrames skill set: lets agents write deterministic MP4 videos in HTML, CSS and animation, with workflows for promo videos, explainers, captions and beat-synced music. Needs Node.js 22+ and FFmpeg.

Official OpenBB MCP server exposing the OpenBB Platform's equity, ETF, macroeconomic, crypto and news data to agents; enable only the tool categories you need to save context. Needs uv locally; some data sources need your own API keys. Not investment advice.

Command-line edition of the open-source OpenBB investment research platform: query stock prices, financial statements, macroeconomic and other financial data from the terminal, and automate data pulls with Routine scripts. Officially maintained; some sources need API keys.

Runs GitHub Actions workflows locally in Docker, so you can test .github/workflows changes without repeated commits and pushes, or use workflows as a local task runner. Needs Docker installed.

Parses PDF, DOCX, PPTX, XLSX, HTML, images and audio, recovering layout, reading order, tables and formulas, and exports Markdown, HTML or lossless JSON. Started by IBM Research, now hosted by the LF AI & Data Foundation; runs fully locally.

Command-line toolkit for transcoding, cutting, joining, frame extraction and streaming of audio and video, including ffmpeg, ffprobe and ffplay. A core dependency for agents handling media. The GitHub repo is the official mirror.

Generates self-contained HTML+SVG diagrams in an editorial style: architecture, flowcharts, sequence, swimlane, Gantt and dozens more types. Can match brand colors from a website and redraw imported Mermaid, draw.io and Excalidraw sources.

Official MCP for the open-source design tool Penpot: through the Penpot plugin API, agents can query, modify and generate designs, supporting design-to-code and code-to-design. Run npx -y @penpot/mcp@latest first and load the MCP plugin in Penpot to connect.