ThoxyWeb
Chat with THOXY AI assistant locally in your browser
At THOX.ai, we build local-first, privacy-first AI that runs where users need it most: on edge devices, workstations, portable hardware, and embedded systems. Our research and engineering focus on making advanced AI practical without requiring cloud infrastructure or sacrificing user ownership of data. Areas of Interest * Edge AI and on-device inference * Local-first LLM deployment * Small Language Models (SLMs) * Efficient transformer architectures * Quantization and model optimization * GGUF, LiteRT, and embedded AI runtimes * AI acceleration on consumer hardware * Mobile and embedded AI systems * Privacy-preserving AI * Offline AI assistants * Agentic AI systems * Multi-agent orchestration * AI operating systems * Retrieval-Augmented Generation (RAG) * Semantic search and knowledge graphs * Memory architectures for AI agents * AI developer tools * AI infrastructure * Open-source AI * Human-AI collaboration * AI for healthcare * AI for education * AI for accessibility * AI for legal and enterprise workflows * Robotics and autonomous systems * Digital humans * Computer vision * Speech and multimodal AI * Federated and distributed AI * Edge-to-edge AI networking * Secure AI deployment * Model benchmarking and evaluation * AI hardware integration * Quantum-inspired optimization * Responsible AI engineering Technologies We Explore * Gemma * LiteRT * llama.cpp * GGUF * ONNX Runtime * TensorFlow Lite * PyTorch * Hugging Face Transformers * Rust * C++ * Python * WebGPU * CUDA * Vulkan * Jetson * Raspberry Pi * Embedded Linux Our Mission THOX.ai develops open, modular AI technologies that help developers, researchers, businesses, and makers deploy powerful AI locally. We believe users should have meaningful control over their models, data, and computing resources while benefiting from modern AI capabilities across desktop, mobile, embedded, and edge environments.
Chat with THOXY AI assistant locally in your browser
Permanent OpenAI-compatible upstream for llm.thox.ai
Generate text responses with ThoxAir offload model
ThoxIntel-27B - THOX flagship reasoning model by Thox.ai
OpenAI-compatible THOX node in the MeshStack mesh
Chat with an uncensored AI assistant for answers and live code
BitNet b1.58 ternary LMs small enough for a microcontroller
Chat with ThoxMini-3B for concise factual answers
125M from-scratch micro LM. Local-first demo.
0.5B on-device edge chat model. Local-first demo.
9M BitNet role model for edge. Local-first demo.
16M BitNet role model for edge. Local-first demo.
9M BitNet role model for edge. Local-first demo.
Preference router LoRA on Qwen2.5-1.5B-Instruct. Local-first
327M from-scratch THOX decoder. Local-first demo.
OpenAI-compatible image generation on ZeroGPU
Keyless multi-provider web search in the SearXNG JSON shape
OpenAI-compatible speech-to-text on faster-whisper
Chat with AI for answers and Rust code help
OpenAI-compatible coding backend for THOX agents
Calculate cosine similarity between two sentences
Registry and router for THOX mesh nodes
On-device agent-teams realtime voice chat, powered by THOX