Discover
Every project in the index. Underrated first: good projects that haven’t been noticed yet.
- Hitoshi Togasaki740
Karukan
Japanese input method with neural kana-kanji conversion
- 2.1k
transcribe.cpp
C/C++ library for running many speech recognition models on ggml
- Harry (J.X.) C.1.8k
Spirula Studio
Gaussian splatting trainer that turns photos or video into splats and meshes
- Antoine2.3k
forge
Reliability layer that makes local LLM tool calls succeed more often
- 3.4k
SIE
Self-hosted inference server running many open models behind one API
AI models and runtimesAgent frameworks and toolsServers and infrastructure
3.4k
- 3.5k
LiteRT
On-device runtime for running ML and generative AI models on edge hardware
- 3.4k
Switchyard
Per-request model routing for AI agents across cheap and capable LLMs
- 5.6k
Weave Router
Prompt-level model router with an OpenAI-compatible endpoint
- Maziyar Panahi5.7k
OpenMed
Clinical entity extraction and PII de-identification on local hardware
AI models and runtimesHealth and fitnessPrivacy and security
- 5.8k
Newton
GPU-accelerated, differentiable physics engine for robotics research
6.2k
- Arthur Brussee5.2k
Brush
Gaussian splatting trainer and viewer that runs on desktop, Android, and web
6.7k
Prince Canuma5.6k
- 7.1k
Plano
Envoy-based proxy that routes, traces, and guards LLM and agent traffic
Agent frameworks and toolsAI models and runtimesServers and infrastructure
7.3k
- 7.6k
ODS
Installer that sets up a complete private local AI stack on your own machine
- Prince Canuma8.1k
MLX-Audio
Speech synthesis, transcription and voice conversion on Apple Silicon
- andy6.8k
whichllm
Command-line tool that ranks local LLMs that will run on your hardware
- leejet7.7k
stable-diffusion.cpp
C/C++ inference engine for diffusion image and video models
Alpamys Makazhan9.5k
Manjeet Singh7.3k
- 10k
Pocket TTS
Small CPU-only text-to-speech model with voice cloning and streaming