
あらゆる文書をAI対応のMarkdownや構造化JSONに変換
459 種類のワークフローで、アクセス推計・機能・代替製品を比較できます。
“JSON server” · 画像認識・解析·28 件
最初から
あらゆる文書をAI対応のMarkdownや構造化JSONに変換
メール・PDF・各種ドキュメントを構造化JSONに変換するLLMベースのパーサー
メール・PDF・各種ドキュメントを構造化JSONに変換するLLMベースのパーサー

写真1枚から120犬種を照合する無料のAI犬種判定ツール

LocalMode UI is an open-source shadcn registry of copy-owned, composable AI interface components plus installable blocks that run real models directly in the browser. It ships 100+ React components and 36 blocks covering chat, RAG knowledge bases, vision, audio, photo editing, agents and privacy tooling, all designed to be local-first by default and cloud-compatible when you want it.
LocalMode UI is an open-source shadcn registry of copy-owned, composable AI interface components plus installable blocks that run real models directly in the browser. It ships 100+ React components and 36 blocks covering chat, RAG knowledge bases, vision, audio, photo editing, agents and privacy tooling, all designed to be local-first by default and cloud-compatible when you want it.


KYC・入退室管理・不正防止のためのオフライン生体認証と本人確認SDK

自分の資料から作るAI学習プラン、クイズ、間隔反復

オンプレミス型の生体認証SDK

Recipio is a recipe saver that imports recipes from any website, photo, or voice note and uses AI to structure ingredients, steps, cook time, and servings. It adds smart tags, builds merged shopping lists, and lets you publish your collection as a sellable PDF cookbook.
Recipio is a recipe saver that imports recipes from any website, photo, or voice note and uses AI to structure ingredients, steps, cook time, and servings. It adds smart tags, builds merged shopping lists, and lets you publish your collection as a sellable PDF cookbook.
小規模チーム向けの監査対応クラウド文書管理
Screenpipe captures your screen and audio locally to build a searchable memory of your work, then exposes it to AI agents through a local API and MCP server. Ask what you were doing, recover that thing you saw earlier, or turn repeated work into documented workflows.
Screenpipe captures your screen and audio locally to build a searchable memory of your work, then exposes it to AI agents through a local API and MCP server. Ask what you were doing, recover that thing you saw earlier, or turn repeated work into documented workflows.
GPTOCR uses generative AI to read documents and return clean, structured JSON instead of raw text, replacing manual data entry with automated extraction your systems can consume directly.
GPTOCR uses generative AI to read documents and return clean, structured JSON instead of raw text, replacing manual data entry with automated extraction your systems can consume directly.


フィンテックの収入確認とオンボーディングを支えるIRS税務記録の即時検証

PDF・画像・開発・AI ツールを 100 以上そろえたプライバシー重視のブラウザツールキット

AIエージェントにネイティブMCPツールとして持続的メモリと根拠ある知識を提供

個人開発者による小さなAIツールとAPIの工房

idict is a mobile translation app built around voice cloning and speech translation. It covers 137 languages and combines real-time spoken translation with photo text translation, object detection, offline language packs and an AI assistant, so it can serve as a single companion for travel, study and everyday cross-language conversation.
idict is a mobile translation app built around voice cloning and speech translation. It covers 137 languages and combines real-time spoken translation with photo text translation, object detection, offline language packs and an AI assistant, so it can serve as a single companion for travel, study and everyday cross-language conversation.

DocTools Pro is a free, browser-based toolkit for everyday document and image jobs: merging and splitting PDFs, converting between 20+ formats, compressing files, running OCR, removing image backgrounds and password-protecting anything. It is built in Switzerland and designed around local processing — files are handled in your browser's memory and never uploaded to a server, so there is no account, no file-size cap and nothing stored on the provider's side.
DocTools Pro is a free, browser-based toolkit for everyday document and image jobs: merging and splitting PDFs, converting between 20+ formats, compressing files, running OCR, removing image backgrounds and password-protecting anything. It is built in Switzerland and designed around local processing — files are handled in your browser's memory and never uploaded to a server, so there is no account, no file-size cap and nothing stored on the provider's side.

OCR - Image Reader is a Chrome extension from developer brian.girko that adds a toolbar button for on-the-fly optical character recognition. Press the button, drag a selection over any region of the active window, and the extension reads the text inside it using a Tesseract-based engine that supports over 100 languages with automatic orientation and script detection. A second engine option, IBM Granite-Docling, goes further and preserves headings, lists, bold and italic styles, tables and even mathematical equations instead of returning flat text. Everything runs offline in the browser, with no server round trips apart from a one-time download of the language training data.
OCR - Image Reader is a Chrome extension from developer brian.girko that adds a toolbar button for on-the-fly optical character recognition. Press the button, drag a selection over any region of the active window, and the extension reads the text inside it using a Tesseract-based engine that supports over 100 languages with automatic orientation and script detection. A second engine option, IBM Granite-Docling, goes further and preserves headings, lists, bold and italic styles, tables and even mathematical equations instead of returning flat text. Everything runs offline in the browser, with no server round trips apart from a one-time download of the language training data.
サイト内のすべての画像にAIでaltテキストを自動生成——アクセシビリティとSEOを1つのWordPressプラグインで
サイト内のすべての画像にAIでaltテキストを自動生成——アクセシビリティとSEOを1つのWordPressプラグインで