Semantic grep with local embeddings
Local LLM runners, AI code assistants, inference engines, and RAG pipelines.
Semantic grep with local embeddings
A UI for Claude Code
A character-level text diffusion model from scratch
Let's Build AI
OCR pipeline for ML training (tables, diagrams, math, multilingual)
AI Image Generator with Consistent Visuals
Open-source framework for production-grade RAG
Local voice assistant using Ollama, transformers and Coqui TTS toolkit
A copilot for your command line
AI powered Real-time voice changer
We made glhf.chat – run almost any open-source LLM, including 405B
AI game animation sprite generator
I built a more productive way to manage AI chats
HTTP API for Claude Code, Goose, Aider, and Codex
A SOTA foundation model for small tabular data
I added local LLM support to Apple Notes (through Ollama)
Convince our voice AI to give you the secret code
AI fine-tuning platform to create custom LLMs
I made a tiny book using a pen-plotter and AI
AI toy I worked on is in stores
local LLM Chrome extension
Using LLama2 to Correct OCR Errors
Benchmarking VLMs vs. Traditional OCR
open-source RAG framework for modular applications
Open-source load balancer for llama.cpp
I generated 70k audiobooks with OpenAI Text-to-Speech
We made an MCP server so Cursor can debug Node.js on its own
Create your own finetuned AI model using Google Sheets
Offline AI transcription for macOS
Experimental website combining computer vision and web design