anomalyco/hex๐ฅ active
โฒ +1K โ this week
Local voice dictation for mac, windows and linux
โฆ updated daily โฆ
Open source text mining and NLP projects gaining the most GitHub stars right now.
star gains from Nov 8, 2026 to Nov 15, 2026 ยท top 30 gained +10.1K โ
โฒ +1K โ this week
Local voice dictation for mac, windows and linux
โฒ +701 โ this week
ใๆทฑๅ ฅ็่งฃ AI Agent๏ผ่ฎพ่ฎกๅ็ไธๅทฅ็จๅฎ่ทตใ๏ผๆๅๆฐ ่๏ผๅผๆบไธปไปๅบ๏ผๅ จไนฆๆญฃๆใ็ผ่ฏ็ PDF ไธๆ็ซ ้ ๅฅไปฃ็
โฒ +656 โ this week
Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.
โฒ +499 โ this week
็ฅไบ Cicada ยท ไปปไฝไผ่ฎฎๅ็ดๆญ็ๅฎๆถๅญๅนใๅๅฃฐไผ ่ฏใAI ไผ่ฎฎ็บช่ฆ๏ผMacใWindowsใLinuxใAndroid ๅ ่ดนๅผๆบใLive subtitles, interpreting and meeting notes for any call or stream, on Mac, Windows, Linux and Android.
โฒ +446 โ this week
21 Lessons, Get Started Building with Generative AI
โฒ +436 โ this week
Build and run agents you can see, understand and trust.
โฒ +429 โ this week
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
โฒ +418 โ this week
Search inside documents, code, and even screenshots - instantly and locally. A free, open-source file launcher with OCR, semantic search, and MCP agent access.
โฒ +392 โ this week
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
โฒ +363 โ this week
AI็ๆใฎๆฅๆฌ่ชใ่ช็ถใชๆฅๆฌ่ชใธๆจๆฒใใAgent Skill / Agent Skill for Refining AI-Generated Japanese into Natural Japanese
โฒ +351 โ this week
Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.
โฒ +339 โ this week
๐ค Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
โฒ +307 โ this week
Snow Shot is free, open-source screenshot software and a screen recording tool for Windows and macOS, with annotation, scrolling screenshots, offline OCR and image pinning. ๅ ่ดนๅผๆบๆชๅพ่ฝฏไปถ๏ผๆฏๆๆชๅพๆ ๆณจใๆปๅจ้ฟๆชๅพใ็ฆป็บฟ OCRใ่ดดๅพไธๅฝๅฑใ
โฒ +306 โ this week
๐ชข Open source AI engineering platform: AI Gateway, agent observability, evals, and prompt/skill management, built on OpenTelemetry. One open platform for every AI call and every agent. Self-host or use Langfuse Cloud.
โฒ +292 โ this week
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
โฒ +270 โ this week
๐ก All-in-one AI framework for semantic search, LLM orchestration and language model workflows
โฒ +264 โ this week
A community-supported supercharged document management system: scan, index and archive all your documents
โฒ +241 โ this week
๐ PageIndex: Document Index for Vectorless, Reasoning-based RAG
โฒ +237 โ this week
ShareX is a free and open-source application that enables users to capture or record any area of their screen with a single keystroke. It also supports uploading images, text, and various file types to a wide range of destinations.
โฒ +232 โ this week
PDF craft can convert PDF files into various other formats. This project will focus on processing PDF files of scanned books.
โฒ +228 โ this week
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
โฒ +201 โ this week
Port of OpenAI's Whisper model in C/C++
โฒ +195 โ this week
OCR software, free and offline. ๅผๆบใๅ ่ดน็็ฆป็บฟOCR่ฝฏไปถใๆฏๆๆชๅฑ/ๆน้ๅฏผๅ ฅๅพ็๏ผPDFๆๆกฃ่ฏๅซ๏ผๆ้คๆฐดๅฐ/้กต็้กต่๏ผๆซๆ/็ๆไบ็ปด็ ใๅ ็ฝฎๅคๅฝ่ฏญ่จๅบใ
โฒ +194 โ this week
ใๅจๆๅญฆๆทฑๅบฆๅญฆไน ใ๏ผ้ขๅไธญๆ่ฏป่ ใ่ฝ่ฟ่กใๅฏ่ฎจ่ฎบใไธญ่ฑๆ็่ขซ70ๅคไธชๅฝๅฎถ็500ๅคๆๅคงๅญฆ็จไบๆๅญฆใ
โฒ +182 โ this week
Faster Whisper transcription with CTranslate2
โฒ +176 โ this week
๐ Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.
โฒ +174 โ this week
้็ฎ Qingjian๏ผ็จ Rust ๅ็ๆผ้ณ่พๅ ฅๆณ๏ผๅ้่ฏๆๅคไธๆกๆญฃๅจๅญฆ็่ฏญ่จ็่ฏ่ฏ
โฒ +171 โ this week
12 Weeks, 24 Lessons, AI for All!
โฒ +170 โ this week
The AI Toolkit for TypeScript. From the creators of Next.js, the AI SDK is a free open-source library for building AI-powered applications and agents
โฒ +169 โ this week
WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)
โฒ +6.4K โ this month
Local voice dictation for mac, windows and linux
โฒ +3.6K โ this month
ใๆทฑๅ ฅ็่งฃ AI Agent๏ผ่ฎพ่ฎกๅ็ไธๅทฅ็จๅฎ่ทตใ๏ผๆๅๆฐ ่๏ผๅผๆบไธปไปๅบ๏ผๅ จไนฆๆญฃๆใ็ผ่ฏ็ PDF ไธๆ็ซ ้ ๅฅไปฃ็
โฒ +3.1K โ this month
Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.
โฒ +2.4K โ this month
Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.
โฒ +2.2K โ this month
Search your computer by what's in your files: photos, PDFs, documents, recordings, videos and code. On-device on Mac, Windows and Linux, built on Google DeepMind's EmbeddingGemma 2.
โฒ +2.1K โ this month
21 Lessons, Get Started Building with Generative AI
โฒ +1.8K โ this month
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
โฒ +1.8K โ this month
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
โฒ +1.5K โ this month
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
โฒ +1.5K โ this month
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
โฒ +1.5K โ this month
Covers pre-training data, Tokenizer, Transformer, MoE,distributed training, Scaling Laws, inference & alignment .6 progressive code assignments for full-stack LLM learning | ๆถต็้ข่ฎญ็ปๆฐๆฎใๅ่ฏๅจใTransformerใMoEใๅๅธๅผ่ฎญ็ปใ็ผฉๆพๅฎๅพใๆจ็ไธๅฏน้ฝ๏ผ6 ้กนๆธ่ฟไปฃ็ ไฝไธ๏ผๆๆก LLM ๅ จๆ ็ฅ่ฏ
โฒ +1.4K โ this month
1M param OCR model - runs on CPU, 15x faster than tesseract, close to 1B+ param models in accuracy