Инструменты

From Microsoft: converts PDF, Word, Excel, PowerPoint, HTML and other files or URLs to Markdown so agents can read and search them. A single convert_to_markdown tool over STDIO or local HTTP.

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+.

Extracts text and tables from PDFs; merges, splits and rotates pages, adds watermarks, fills forms and OCRs scanned documents. The official Anthropic skill behind Claude's document features; source-available, not open source.

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.

Local MCP server built into Browser Use: lets agents navigate, click, type and extract page content, or hand multi-step tasks to the built-in browser agent. Bring your own OpenAI or Anthropic API key.

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 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.

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.

Generates natively editable PPTX from PDFs, Word files, web pages and other sources, with native shapes, data charts and master layouts. Can also fill your own template and add animations and narration to finished decks. Needs Python 3.10+ and its dependencies.

Converts PDFs, images, PPTX, DOCX, XLSX, EPUB and more into Markdown, JSON or HTML, preserving tables, formulas and layout, with optional LLM help for higher accuracy. Needs Python 3.10+ and PyTorch; large-scale commercial use of the model weights needs a paid license.

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.

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.

Industrial-grade open-source speech recognition toolkit from Alibaba's ModelScope, with an agent-friendly funasr command that turns audio into text, JSON or SRT subtitles in one step, with speaker diarization and timestamps. Strong on Chinese. Requires PyTorch.

Unofficial Python library and CLI for driving Google NotebookLM (now Gemini Notebook): bulk-import sources, ask cited questions, and generate and download podcasts, videos, slides, quizzes and flashcards. Ships an agent skill. Relies on undocumented APIs and needs a Google sign-in.

Browser control from the browser-use team: an editable CDP connection lets agents drive the Chrome you are already using, writing missing helper functions as they go and keeping them for reuse. Also offers an MCP server. Allow remote debugging in Chrome on first use.

Write your resume in YAML and render a cleanly typeset PDF from the command line: multiple themes, fine control of margins, colors and fonts, strict field validation and multi-language support. A companion agent skill is available. Needs Python 3.12+.

Reads the exact position of every character, line and table cell in digital PDFs: the CLI exports layout-preserving text or CSV/JSON details, and the Python API extracts tables and form fields, ideal for invoices, statements and reports. Runs locally with Python; scans need OCR first.

PDF translation CLI for research papers that preserves formulas and layout as much as possible, producing bilingual side-by-side or translation-only PDFs. Needs an OpenAI-compatible API (local Ollama works too); currently focused on English to Chinese.

Rendering engine that lays out HTML and CSS and exports PDF, supporting paged media and other print style standards, ideal for generating reports, invoices and receipts in bulk. Written in Python; depends on the system Pango library.

NetEase's open-source cross-platform UI automation framework: locates elements by image recognition to automate games and apps on Android, iOS and Windows without touching their code. airtest run executes cases and airtest report builds HTML reports.

Lightweight OCR built on PaddleOCR models converted to ONNX, recognizing Chinese and English by default on CPU alone. The rapidocr CLI reads text from screenshots, photos and scanned page images. Needs Python; downloads models on first run, then works offline. Convert PDFs to images first.

Offline speech toolkit for Apple Silicon Macs: CLI text-to-speech (including Chinese and voice cloning) and speech-to-text, for voicing lessons and explainer videos or transcribing lectures and interviews, with data staying local. Needs an M-series Mac and Python 3.10+; MP3 export needs ffmpeg.

Open-source offline machine translation built on OpenNMT, usable as a CLI, Python library or GUI. Download language packages as needed; when no direct model exists it pivots through an intermediate language. Suits text you would rather not upload to the cloud.

Community-maintained MCP for Jira and Confluence: search with JQL/CQL and create or update issues, pages and comments. Supports both Cloud and Server/Data Center deployments; needs an API token or personal access token.