LLMs & Machine Learning
Language models, training, inference, RAG and ML frameworks. ยท 116 repositories
Automation foundation model for tiny devices: 2-bit, 8-29 MB, tool calls, ASR, structured extraction and embeddings on phones, wearables, smart homes, robots, cars and microcontrollers.
Graph-Native Infrastructure for Context and Accountable AI Systems
Personal AI, On Personal Devices
[MLsys2026 Best Paper]: https://arxiv.org/abs/2506.08276. RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.
๐ก All-in-one AI framework for semantic search, LLM orchestration and language model workflows
A straightforward method for training your LLM, from downloading data to generating text.
๐ Geometric Computer Vision Library for Spatial AI
Your personal intelligence agent. Watches the world from multiple data sources and pings you when something changes.
LIBERATED AI CHAT
https://arxiv.org/abs/2606.28344. The end of web parsing. The beginning of scalable pixel-native search. link: https://pixelrag.ai/
Voice-to-text dictation app with local (Nvidia Parakeet/Whisper) and cloud models (BYOK). Privacy-first and available cross-platform.
Official Python inference and LoRA trainer package for the LTX-2 audioโvideo generative model.
Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.
~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & Encrypted.
An AI-powered search engine with a generative UI
A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.
A Smart, Automatic, Fast and Lightweight Web Scraper for Python
ODS V3 Pre-Release: Public testing and refinement ahead of the official V3 launch. Turn your PC, Mac, or Linux box into a private AI server.
Gemma 4 26B-A4B inference in ~2 GB of RAM on any M-series MacBook
Send a phone call from AI agent, in an API call. Or, directly call the bot from the configured phone number!
Building AI agents, atomically
Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks including CrewAI, Agno, OpenAI Agents SDK, Langchain, Autogen, AG2, and CamelAI
Your always-on AI coworkers that move between text, calls, and Slack.
AI-powered virtual executive team โ a single coherent executive persona backed by 8 specialist agents (FastAPI + Next.js).