Offline Q&A over Wikipedia ZIM files – full‑text + semantic search using TurboRag. Zero internet required after setup. Run on low‑CPU, low‑RAM devices. using llama.cpp

🐱 Kitten TTS Studio using local onnx models TTS Offline

Claw-skills any thing

Cross‑platform inference engine for huge AI models (1B–397B). Runs on any CPU (x86_64/ARM64) with AVX2/NEON, supports dense & MoE models (Qwen, Llama, Mistral…). GPU backends (Metal, OpenCL, CUDA) coming soon. No Python, no frameworks – pure C with optional PyQt5 GUI.

🦀 Rust port of Claw Code – fast, memory-safe AI agent harness with full offline/Ollama support. No API key. Built‑in tools, MCP, slash commands, plus Python RAG/TTS/sandbox skills.

Offline CRUD + semantic search agent for ZIM archives (Kiwix format). Read, write, edit, delete articles, build vector indexes, and serve via MCP – all offline, low‑resource.

A Desktop app using python PyQt5 for zim-agent Offline CRUD + semantic search agent for ZIM archives (Kiwix format). Read, write, edit, delete articles, build vector indexes, and serve via MCP – all offline, low‑resource.

Run offline RAG engines on CPU and RAM using quantized vector indexing, LLM quantization tools, and multi-language support.