Stars
A Python port of Pi’s minimalist coding agent.
Fast and memory-efficient exact attention
A high-throughput and memory-efficient inference and serving engine for LLMs
Train the smallest LM you can that fits in 16MB. Best model wins!
100M tokens. Infinite compute. Lowest val loss wins.
AI agents running research on single-GPU nanochat training automatically
omo/lazycodex: The coding agent for tokenmaxxers;the one and only agent harness for complex codebases. For your Codex, for your OpenCode
Build Real-Time Knowledge Graphs for AI Agents
An Open Source implementation of Notebook LM with more flexibility and features
Welcome to the Storm Cookbook! This is your go to guide for Building with STORM Solution.
Open-Source Chrome extension for AI-powered web automation. Run multi-agent workflows using your own LLM API key. Alternative to OpenAI Operator.
a free and opensource app that lets you gain an unfair advantage
OpenHealth, AI Health Assistant | Powered by Your Data
Data and docs for Deep Funding's dependency graph
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.
Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.
Video+code lecture on building nanoGPT from scratch
llama3.cuda is a pure C/CUDA implementation for Llama 3 model.
AutoRAG: Now your agent can find anything in your computer. It gets smarter if you are using it frequently.
The simplest, fastest repository for training/finetuning medium-sized GPTs.
Superagent protects your AI applications against prompt injections, data leaks, and harmful outputs. Embed safety directly into your app and prove compliance to your customers.