Stars
AI enabled pair programmer for Claude, GPT, O Series, Grok, Deepseek, Gemini and 300+ models
Memory library for building stateful agents
STAR: Similarity-guided Teacher-Assisted Refinement for Super-Tiny Function Calling Models
Vali-98 / cui-llama.rn
Forked from mybigday/llama.rnReact Native binding of llama.cpp
CorbeauSplat is an all-in-one Gaussian Splatting automation tool designed specifically for macOS Silicon. It streamlines the entire workflow from raw video/images to a fully trained and viewable 3D…
Lightpanda: the headless browser designed for AI and automation
AI agents running research on single-GPU nanochat training automatically
Fullstack app framework for web, desktop, and mobile.
A lightweight self-hosted bot in a single binary, written in Go.
LiteRT, successor to TensorFlow Lite. is Google's On-device framework for high-performance ML & GenAI deployment on edge platforms, via efficient conversion, runtime, and optimization
Lightning-Fast, On-Device, Multilingual TTS — running natively via ONNX.
On-device AI for Android — LLM chat (GGUF/llama.cpp), vision models (VLM), image generation (Stable Diffusion), tool calling, AI personas, RAG knowledge packs, TTS/STT. Fully offline, zero subscrip…
Lisa plans. Ralph does. Interactive specification interview workflow for Claude Code that conducts in-depth feature interviews and generates comprehensive specs.
omo; the best agent harness - previously oh-my-opencode
Qwen Multi Angle UI powered by fal.ai API
Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc.
Connect Google ADK TypeScript to Vercel AI Gateway and 100+ LLM models
🤖 AI-powered ADR generation - Automatically capture and document architectural decisions as you code
📐⚙ 2D vector line drawing and shape modeling for CNC and laser cutters.
[CVPR2026] Long-horizon, spatially consistent video generation enabled by persistent 3D scene point clouds and dynamic-static disentanglement.
Z80-μLM is a 2-bit quantized language model small enough to run on an 8-bit Z80 processor. Train conversational models in Python, export them as CP/M .COM binaries, and chat with your vintage compu…
Official implementation of "Depth Any Panoramas: A Foundation Model for Panoramic Depth Estimation".
[WACV'26] Inpaint360GS: Efficient Object-Aware 3D Inpainting via Gaussian Splatting for 360° Scenes