200 open source apps like Tiny TPU, closest match first.
Vui
Vui Nano — a small, context-aware text-to-speech model trained on real
MLX-LoRA-Studio
A native Mac App for LLM fine-tuning on Apple Silicon
MLX Tune
Fine-tune LLMs on your Mac with Apple Silicon
Sayit
Private, local text-to-speech for Apple silicon Macs
SapienAI
Self-hosted academic chatbot, research workspaces and editor
Pipelex
Build AI methods with your coding agent
Texo
A minimalist SOTA LaTeX OCR model with only 20M parameters, running in browser
Minimind V
Train a 65M-parameter VLM from scratch in just 2h!
Lineage Skill
Distill videos, PDFs, transcripts, and notes into source-backed teacher Agent…
Code
Companion code for Machine Learning From Scratch
Parakeet
OpenAI Whisper-compatible ASR server using NVIDIA Parakeet TDT 0.6B (ONNX)
Parakeet.cpp
Ultra fast and portable Parakeet implementation
Minion
A tiny single-file coding agent for self-hosted models
Dectalk
Modern builds for the 90s/00s DECtalk text-to-speech application
AI Agent Camp
Non-engineer-friendly AI agent training curriculum
Versatile-OCR-Program
Multi-modal OCR pipeline optimized for ML training
Neuroarxiv
A skill to kill from-scratch coding
Alpamayo Recipes
Developer Hub for NVIDIA Alpamayo, containing ready-to-use recipes for…
Tetris Game
A Tetris Game with AI
Audio Webui
A webui for different audio related Neural Networks
Google AI Edge Eloquent
Free on-device AI dictation and voice editing from Google
Lucebox
LLM speculative inference server for heterogeneous hardware & consumer GPUs
Qwen Scribe
Private, local transcription and system-wide dictation for Apple Silicon
Qwen3 TTS Apple Silicon
Run Qwen3-TTS text-to-speech locally on Mac (M1/M2/M3/M4)
Piper Plus
Multilingual neural TTS (6 languages: JA/EN/ZH/ES/FR/PT, code supports SV)
TensorSharp
A native .NET LLM inference engine and agent runtime for GGUF models
Kun
Local-first AI agent workspace for coding, writing, design, research
Xybrid
Cross-platform on-device AI toolkit
TVM CN
TVM Documentation in Chinese Simplified / TVM 中文文档
ToshLLM
Run large language models locally on Intel Macs with AMD GPUs
browser-whisper
In-browser Whisper speech-to-text with WebGPU (WASM fallback)
Guaardvark
Self-hosted AI studio on your own GPU: chat with your files
Tern
Local AI search for podcast and video archives on Apple Silicon: Whisper speech
Maths CS AI Compendium
Become a cracked AI/ML researcher/engineer
Streamcore Server
Open-source realtime voice agent server in Go with WebRTC
Tessera
A workspace for organizing AI coding sessions across projects
Claw Compactor
14-stage Fusion Pipeline for LLM token compression
arXivisual
TartanHacks '26 Winner
Tesseract
Tesseract Open Source OCR Engine (main repository)
AgentPipe
High performance multithreaded task execution and optimization engine
KokoroSharp
Fast local TTS inference engine in C# with ONNX runtime
Ccmux
Run all your AI coding agents in tmux: jump to the one
AI Infra Engineer Learning
AI Infrastructure Engineer Learning Track
Omarchy Local AI
Local AI for Omarchy: the model validated for your GPU, one button on the bar
Tensorwatch
Debugging, monitoring and visualization
Audio.cpp-webui
audio.cpp with a full-task WebUI - pure C++ audio-model inference engine…
Onnx Web
web UI for GPU-accelerated ONNX pipelines like Stable Diffusion
Laya Coreml
Local Laya typed decisions on Apple Core ML and Neural Engine
llama.cpp
C/C++ inference engine for large language models, supporting quantization
GPA
[AutoArk] GPA (General Purpose Audio) can do ASR, TTS and voice conversion