Showing 100 ai tools sorted by GitHub stars — all open-source with proven community adoption.
Web UI for Stable Diffusion image generation
Run large language models locally on your machine
Cross-platform ChatGPT/Gemini UI with one-click deploy
Run powerful and customized LLMs locally
Robust speech recognition via large-scale weak supervision
Fast LLM inference in C/C++ for local deployment
Original latent diffusion model for photorealistic image synthesis
Converts screenshots to clean HTML/CSS/JS code using AI
Powerful node-based UI for Stable Diffusion
Natural language interface to run code on your computer
Ask questions to your documents with 100% private AI
User-friendly self-hosted web UI for Ollama and LLMs
Modern open-source ChatGPT / LLMs UI framework
Midjourney-style image generation, offline and open-source
Gradio-based web UI for running local LLMs
Your AI second brain for productivity and knowledge
LAION's open-source ChatGPT alternative for everyone
Text-prompted generative audio model with emotion and music
Deep learning toolkit for Text-to-Speech synthesis
Powerful few-shot voice conversion and TTS toolkit
Fine-grained conversational text-to-speech model
Versatile instant voice cloning by MyShell AI
Open-source ChatGPT-style UI for multiple AI providers
HuggingFace library for image, audio and video generation
Practical image/video super-resolution using ESRGAN
All-in-one desktop and Docker AI application
Singing voice conversion based on VITS and SoftVC
Free, open-source alternative to OpenAI API running locally
Open-source framework for augmenting humans using AI
Retrieval-based voice conversion web interface
Browser extension and desktop app for AI translation
Professional creative engine for Stable Diffusion
Self-hosted AI coding assistant, open GitHub Copilot alternative
Open-source ChatGPT alternative that runs offline
Meta's library for audio generation including MusicGen
AI pair programmer in your terminal
Open-source AI code assistant for VS Code and JetBrains
High-quality document parser converting PDFs to Markdown
Build UI components with AI-assisted description
Enhanced ChatGPT clone with multi-model support
Converts PDF, EPUB, MOBI to Markdown accurately
Run LLMs as a single cross-platform executable file
3D visualization of large language model internals
State-of-the-art open image generation models by Black Forest Labs
Apple's ML framework optimized for Apple Silicon
Personal AI assistant that searches your notes and docs
Proxy service for Midjourney API integration
AI tool to remove image backgrounds automatically
React framework for in-app AI copilots and chatbots
Port of OpenAI Whisper in C/C++ for fast local inference
Brand new TTS solution with voice cloning
AI-powered documentation chatbot with RAG
Animate face images with speech audio to create talking portraits
Use AI to generate HTML from hand-drawn UI sketches
Chat with multiple AI bots simultaneously to find the best answer
RNN-based LLM with transformer-level performance
4x faster Whisper transcription with CTranslate2
Identity-preserving personalized image generation
LLM OS with virtual memory and persistent context management
Private enterprise-grade Q&A with local document retrieval
Whisper with word-level timestamps and speaker diarization
AI-powered enterprise search connecting all company data
AI coding engine for complex multi-file tasks in the terminal
Animate your personalized text-to-image diffusion models
Robust face restoration and enhancement using a Transformer
Scripting language for interacting with LLMs like programs
Desktop app for running uncensored LLMs locally
End-to-end RLHF training pipeline for chat models
Databricks' open-source instruction-following LLM
Accurate multilingual document OCR and line detection
AI-powered command-line productivity tool
Open-source video generation model by THUDM
Customizing realistic human photos via stacked ID embedding
Optimized SD WebUI fork with faster generation and lower VRAM
Real-time high-quality virtual avatar with lip sync
Music source separation (vocals, drums, bass, guitar)
NVIDIA's toolkit for optimizing LLM inference performance
Zero-shot text-to-speech with voice cloning
Image prompt adapter for Stable Diffusion models
Neural OCR for academic PDF documents with math support
Multilingual code generation model by THUDM
Fast, local neural text to speech system
Advanced UI for AI roleplay and interactive story writing
Cross-lingual neural codec language model for TTS
Temporally consistent human animation using diffusion
Fundamental end-to-end speech recognition toolkit
Various AI scripts for LoRA and Dreambooth training
Easy-to-use local LLM inference with KoboldAI interface
Generative AI suite for professionals with personas and tools
Community-based approach for LLM alignment and fine-tuning
Automated AI framework for YouTube Shorts / TikTok videos
Command-line interface for LM Studio local LLM app
Efficient inference library for quantized LLMs
CLI utility and Python library for interacting with LLMs
Andrew Ng's simple interface for multiple AI providers
Open-source implementation of ChatGPT code interpreter
Fast LLM inference engine for consumer-grade hardware
iOS app for private AI chat using local Ollama models
An LLM playground to compare multiple models side-by-side
Gradio-based web UI for OpenAI Whisper transcription