cpu-only

Minimal CPU-only Ollama Docker Image

Local agentic AI runtime optimized for CPU-only consumer hardware, tool use and efficient local inference.

CPU-only LLM inference engine in pure Rust — 4-bit quantized models, hand-written AVX2 kernels, speculative decoding, and a local HTTP/MCP server. No GPU, no Python runtime.

CPU-only ONNX Runtime export and runtime workspace for VoxCPM2

An LLM-based content moderator. Firefox extension to block webpages unrelated to work, based on page title and URL. Local LLMs with Ollama and Langchain to ensure your browsing history never leaves your device, for complete privacy. Google Gemini also supported.

🦙 chat-o-llama: A lightweight, modern web interface for AI conversations with support for both Ollama and llama.cpp backends. Features persistent conversation management, real-time backend switching, intelligent context compression, and a clean responsive UI.

Deterministic logical reasoning engine using Vector Symbolic Architectures. 100% ProofWriter. CPU-only. No backprop.

A high-performance Python library for extracting structured content from PDF documents with layout-aware text extraction. pdf_to_json preserves document structure including headings (H1-H6) and body text, outputting clean JSON format.

No-GPU 3D scanning from phone rotation videos — pure geometry, no neural networks, no cloud

Self-hosted, model-free knowledge base for GitHub and GitLab repositories, with group imports, cross-repository search and read-only MCP.

LCM-LoRA Studio - Create a high-quality image, in an average of ONLY 4 STEPS, using just a low-end CPU or a Raspberry Pi 5.

Lightweight, efficient, optimized CPU-only webcam face, body and hand tracker that drives VRM 1.0 avatars. Rust, ONNX Runtime, Bevy.

Fast CPU-only ROI detection library for real-time pipelines

A self-hosted, fully autonomous, CPU-only poker-bot fleet for openpoker.ai — Rust workspace and React control room, every artifact machine-generated.

Probabilistic Signed Distance Fusion with View Planning on CPU

Adds deploy-ready FastAPI backend package with CPU model layout, docs, env examples, and tests.

Offline lightweight singing synthesizer — independent per-track parameters, no pretraining, UTAU voicebank support

Cascade MoE: a CPU-only expert system that turns plain-language sysadmin and networking questions into shell commands. No GPU, no cloud, no external model weights. Russian-first: 80% of held-out Russian queries answered with a working command, 38% in English. Patent pending. The benchmark that measures it ships with the source.

Zero-memory, multi-core-CPU local AI training for ordinary laptops.