A free OCR inference toolkit for developers who need to turn images into text, bounding boxes and confidence scores. RapidOCR packages recognition models with several runtime options and can run locally inside document-processing applications.
An open-source academic workspace for paper reading, translation, polishing and code explanation. GPT Academic combines configurable model connections with task-specific plugins, including PDF and LaTeX workflows, instead of relying only on a blank chat box.
A free offline desktop OCR application for screenshots, batches of images and scanned documents. Umi-OCR brings recognition engines into a practical interface with editable results, layout handling and searchable PDF workflows.
Baidu’s Chinese-language assistant for questions, writing and study tasks. The current Wenxin interface combines chat with work-oriented entry points; free consumer access should be distinguished from feature-specific services and paid developer APIs.
A free, open-source subtitle editor combining precise timing tools with optional AI transcription and proofreading. The current cross-platform project supports local model routes, making it useful for creators who want editable subtitles rather than only burned-in captions.
An open-source inference runtime that serves local models through familiar API interfaces. It supports multiple model backends and modalities, making it useful for developers building self-managed AI services rather than relying on a single hosted provider.
An open-source PDF translation project focused on scientific documents and bilingual comparison while preserving layout elements. The current next branch uses BabelDOC and supports local interfaces plus configurable translation services.
A local-first AI workspace for chatting with documents, organizing knowledge and connecting model-backed agents. The free desktop app and MIT-licensed self-hosted project can use local models, while external providers and hosted services are optional costs.
A desktop route to downloading and running local language models, chatting with documents and serving a local API. Free for personal and work use; hardware requirements, model licenses and optional cloud services should be evaluated separately.
The current desktop coding environment reached from the former Windsurf routes. It combines editor completions, inline changes and a local agent workflow. The Free plan offers unlimited Tab and inline edits plus a limited agent allowance.
A browser-based AI builder that turns a written brief into websites and applications, with code, preview and hosting in one workflow. The ongoing free plan is useful for small prototypes within daily and monthly token limits.
A browser-based image toolkit for removing backgrounds, cleaning unwanted objects, enlarging images and changing lighting. Several editing tools have recurring free daily limits, making it useful for occasional product and social-media visuals.
