인기 순위

Open-source browser agent project. Its browser-use CLI lets Claude Code, Codex and other agents drive your logged-in local Chrome with Python snippets, or connect to a cloud browser; also ships a Python agent library. The cloud browser needs an API key.

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.

A CLI and Python library by Simon Willison: imports JSON and CSV straight into SQLite with automatic table creation, runs in-memory SQL queries over files, and supports full-text search and table transformations.

Posit's open-source scientific and technical publishing system built on Pandoc: embed Python, R or Julia code in Markdown or Jupyter notebooks, then quarto render produces HTML, PDF, Word, slides, websites and books.

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.

Converts PDF, Word, Excel, PowerPoint, HTML, images, audio and more into Markdown that keeps headings, lists and tables, ready for LLMs to read and analyze. Maintained by Microsoft; requires Python 3.10+.

Microsoft's open-source AI quant investment research platform: the qrun command runs dataset building, model training, backtesting and evaluation from a YAML config, with many benchmark models. The official dataset is paused, so prepare market data per the README first.

Simon Willison's LLM CLI and Python library: call OpenAI, Claude, Gemini and local models from the terminal, with conversations logged to SQLite automatically, plus embeddings, structured extraction, tool calling and a plugin system.

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.

In-process analytical SQL database. Its CLI queries CSV, Parquet and JSON files directly with SQL, no import or server needed, so agents can sample and aggregate large files. Officially maintained.

Adds a searchable, copyable text layer to scanned PDFs, with automatic deskew, rotation and size optimization, outputting PDF/A by default. Built on Tesseract, supports 100+ languages and runs fully locally.

One CLI for Gmail, Drive, Calendar, Docs, Sheets and other Google Workspace APIs, with commands generated from the Discovery service, JSON output and 100+ Agent Skills. From the googleworkspace org but not officially supported; needs OAuth via a Google Cloud project.

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.

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.

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.

Write videos in React and render them from the command line with npx remotion render, letting agents batch-produce data-driven videos. Free for individuals, nonprofits and companies of up to 3 people; larger for-profit companies need a license.

Universal document converter between dozens of formats including Markdown, Word, HTML, LaTeX and EPUB, with templates, citations and Lua filters. PDF output uses LaTeX by default, which you install separately.

Microsoft Playwright's official browser CLI for coding agents: open pages, click and type, take screenshots and manage sessions, and install the companion skills in one step. Uses fewer tokens than Playwright MCP. Needs Node.js 18+.

Community CLI for Feishu (Lark) focused on two-way conversion between Markdown and Feishu docs; also works with wikis, sheets, Bitable, messages, calendar, tasks and meeting notes, and ships 9 agent skills. Setup creates an app via QR scan; search and mail need extra user authorization.

Firecrawl's official CLI: scrape, search, map and crawl sites and interact with pages in a browser from the terminal, with Markdown output; can also install companion skills for coding agents. Needs a Firecrawl account or API key, or point it at a self-hosted instance.

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.

GitHub's official CLI: manage pull requests, issues, releases and Actions workflows from the terminal. Most commands support --json output that agents can parse, and an official agent skill is available. Run gh auth login first.

Office command-line tool built for AI agents: a single binary that creates, reads and edits Word, Excel and PowerPoint files without Office installed, and renders them to HTML or PNG so agents can check the layout.

CLI and library for evaluating and red-teaming LLM apps: compare prompts and model outputs in bulk, scan for security vulnerabilities and plug into CI/CD, with evals running locally. Now part of OpenAI and still open source under MIT.

The official MCP debugging tool: connect to any MCP server through a web UI, CLI or terminal UI to list and call its tools, resources and prompts. CLI mode outputs JSON, suited to scripts and CI smoke tests.

Open-source research agent: one command runs literature reviews, deep research, paper reviews, paper-code consistency checks and replication plans, searching arXiv, PubMed and more with sources recorded. Good for grad students writing reviews. Run feynman setup to sign in to a model provider.

High-accuracy retrieval-augmented Q&A over paper PDFs, text and Office documents, filling in citation metadata, checking retractions and attaching traceable sources to answers. Provides the pqa CLI and a Python library. Needs an LLM API key by default; local models can be configured.

Open-source PDF table extraction with a camelot CLI: exports tables from financial reports, bank statements and statistical reports to Excel, CSV or Markdown, with an accuracy score. Needs Python 3.10+; handles text-based PDFs by default, scans need the ml and ocr extras. Double-check results.

GitHub's official spec-driven development toolkit: the specify CLI sets up spec, plan and task workflows for Copilot, Claude Code, Codex and other agents so the spec comes before the code, plus bug-fix and idea-evaluation flows. Needs Python 3.11+ and uv.

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.

General-purpose AI agent that runs on your machine, with a desktop app, CLI and API. Written in Rust, works with 15+ model providers and connects to 70+ extensions via MCP. Originally from Block, now part of the Linux Foundation's AAIF.

Official web auditing tool from the Google Chrome team: score pages on performance, accessibility, best practices and SEO from the command line and get HTML, JSON or CSV reports, so agents can iterate on a page. Needs Node 22+ and Chrome.

Fast speech transcription built on faster-whisper, with word-level timestamps and speaker diarization, suited to meeting notes and subtitles. Diarization needs a Hugging Face token; GPU acceleration needs CUDA.

Anthropic's official OS-level sandbox CLI: restricts file and network access for agents, MCP servers and any command without containers, using sandbox-exec on macOS and bubblewrap on Linux. Currently a research preview.

Converts PDFs to editable Word files, keeping paragraphs, tables, images and layout as closely as possible, and can extract tables alone, handy when a contract or exam only exists as PDF. Needs Python; digital PDFs only, OCR scans first. No longer actively maintained by Artifex.

Replaces arXiv preprint entries in your .bib file with the official published versions from DBLP and ACL Anthology, keeping citation keys, to tidy references before camera-ready. Overwrites the file by default, so preview with --dry-run. Mainly covers CS venues; needs Python 3.10+.

ComfyUI's official CLI: install and launch ComfyUI in one step, manage custom nodes and model downloads, and run image and video workflows, with --json output on every command for agents. Can also submit jobs to paid Comfy Cloud.

SEO CLI and MCP server for agents: crawls your site for technical issues, uses Search Console data to rank fixes, and compares before and after. Needs Node.js 22+ and Google sign-in; keyword and competitor research needs paid data (DataForSEO, Semrush or Ahrefs).

HeyGen's official CLI, built for agents like Claude Code and Codex: generate avatar presenter videos from a prompt or template, translate and dub videos, and synthesize speech, with JSON output. Good for batch training and product videos. Needs a HeyGen API key (usage-billed) or a Pro/Max plan.

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.

Lightweight spec-driven development CLI: after initializing a project, commands such as /opsx:propose let humans and agents agree on change proposals and specs before coding. Supports Claude Code, Codex and 30+ other tools. Needs Node.js 20.19+.

Open-source crypto trading framework: download market data, backtest and optimize strategies, and paper trade from the CLI while agents iterate on strategies. Docker recommended; strategies need Python and live trading needs exchange API keys. Backtests don't guarantee returns.

Astral's extremely fast Python linter and formatter written in Rust, replacing Flake8, isort and Black, with 900+ built-in rules and auto-fix.

Browser automation CLI built for AI agents in native Rust: open pages, click and fill forms by refs from accessibility tree snapshots, read text and take screenshots, with compact snapshots and output limits to save context. From Vercel Labs; reuses local Chrome or installs one.

Lightweight multi-protocol command-line downloader that fetches in parallel segments from multiple sources over HTTP(S), FTP, SFTP, BitTorrent and Metalink. Resumes downloads, reads URLs in bulk from text files and offers a JSON-RPC interface for scripts or agents.

Personalized tutoring system from HKU's HKUDS: build a knowledge base from textbooks for Q&A, step-by-step solutions and quizzes, for teachers and self-learners. The deeptutor command outputs JSON for agents like Claude Code. Needs Python 3.11+, Node.js 20+ and an LLM API key.

Translates full PDF papers while preserving formulas, charts and layout (command pdf2zh), outputting monolingual and side-by-side bilingual PDFs. Uses Google Translate by default and can switch to DeepL, OpenAI and others; also runs as an MCP server.

Headless browser written from scratch in Zig for AI agents and automation, using less memory and running faster than headless Chrome in official benchmarks. fetch turns pages into Markdown, and it can serve CDP or MCP. Telemetry is on by default (an env var disables it); Windows needs WSL.

From Firecrawl: converts Word, PowerPoint, Excel, PDF, EPUB, RTF and more into clean Markdown locally in milliseconds, keeping headings, tables, footnotes and formulas so agents can read attachments. Needs Node.js; optional Firecrawl cloud OCR for scans uploads the whole file.

MySQL terminal client with smart autocompletion and syntax highlighting, also compatible with MariaDB and TiDB. Supports --execute and batch mode with CSV or table output, so agents can run SQL directly.