Starred repositories
TQ1.0 ternary inference engine for BitNet b1.58 on CPU. Pack + run Falcon3-1B/3B/7B/10B, no GPU needed.
The fastest inference framework to run AI on CPUs
NobodyWho is an inference engine that lets you run LLMs locally and efficiently on any device.
Council is an open-source platform for the rapid development and robust deployment of customized generative AI applications
Promptdesk is a tool designed for effectively creating, organizing, and evaluating prompts and large language models (LLMs).
🦁 AI chat & search summaries in Brave Search, powered by the latest LLMs
ComfyUI-QwenVL custom node: Integrates the Qwen-VL series, including Qwen2.5-VL and the latest Qwen3-VL, with GGUF support for advanced multimodal AI in text generation, image understanding, and vi…
huchukato / ComfyUI-QwenVL-Mod
Forked from 1038lab/ComfyUI-QwenVLComfyUI-QwenVL custom node: Integrates the Qwen-VL series, including Qwen2.5-VL and the latest Qwen3-VL, with GGUF support for advanced multimodal AI in text generation, image understanding, and vi…
ComfyUI-QwenVL custom nodes with local model discovery and 3.5 support: Integrates the Qwen-VL series, including Qwen2.5-VL,Qwen3-VL, and Qwen3.5 with GGUF support for advanced multimodal AI in tex…
A pan-and-zoom image slideshow in Python, using Clutter. Integrates nicely with Variety.
Wallpaper downloader and manager for Linux systems
Wallpaper Engine backgrounds for Linux!
1M+ downloads Linux reference app with basics, tips and formatted man pages
Container runtimes on macOS (and Linux) with minimal setup
The official repository for ERNIE 4.5 and ERNIEKit – its industrial-grade development toolkit based on PaddlePaddle.
Open-source private logbook with a local agentic layer. Long-living AI agents read what you record and propose what to do next. Hardware permitting, the models runs locally too. Matrix + Vodozemac …
🎨 Multiplatform AI image generation app powered by Stable Diffusion • Built with Kotlin Multiplatform & Compose • Supports SDXL, FLUX, SD3 & more • Native performance via C++/JNI • Android/iOS & De…
InkArms is your local AI agent with eight arms and zero patience for busywork. It doesn’t chat — it acts, remembers, and leaves records, working from your terminal and across Telegram, Discord, Sla…
An Open Source implementation of Notebook LM with more flexibility and features
AI superpowers you own. Sila is an open alternative to ChatGPT where you own AI assistants, chats and data.
A friendly, human-like AI chatbot powered by Gemini.
A ~9M parameter LLM that talks like a small fish.
Desktop pets for AI coding agents. Install pets, connect Claude Code via MCP, and see live coding status on your desktop.
Hierarchical Agent Memory with Git-Like Version Control
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.
A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.