Starred repositories
Under heavy development - Quant-em is a terminal UI for downloading Hugging Face models, converting safetensors models to GGUF, and quantizing GGUF models with llama.cpp.
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.
The official Python SDK for Model Context Protocol servers and clients
Find the local LLM that actually runs and performs best on your hardware. Ranked by real, recency-aware benchmarks, not parameter count. One command, run it instantly.
Build your own AI SRE agents. The open source toolkit for the AI era.
Remove invisible AI watermarks (SynthID, StableSignature, TreeRing) and strip AI metadata from images. Open-source CLI & Python toolkit.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Adaptive Precision for EXpert Models: MoE-aware mixed-precision quantization
Open Source AI Platform - AI Chat with advanced features that works with every LLM
Make your own story. User-friendly software for LLM roleplaying
Learn it. Build it. Ship it for others.
💖🧸 Self hosted, you-owned Grok Companion, a container of souls of waifu, cyber livings to bring them into our worlds, wishing to achieve Neuro-sama's altitude. Capable of realtime voice chat, Minec…
Curated list of the best truly open-source AI projects, models, tools, and infrastructure.
An all-in-one enhancement suite for Google Gemini & AI Studio - timeline navigation, folder management, prompt library, and chat export in one powerful extension. / Google Gemini & AI Studio 全能增强插件…
Direct3D 9 Fixed-Function Pipeline → WebGL 2.0 wrapper for Emscripten/WASM
REAP: Router-weighted Expert Activation Pruning for SMoE compression
This is a collection of recent papers on reasoning in video generation models.
RuVector is a High Performance, Real-Time, Self-Learning Ai, Vector GNN, Memory DB built in Rust.