Awesome Opensource Ai

21 Lessons, Get Started Building with Generative AI

🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.

📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Language Models (LLMs) or other AI tools like Claude, ChatGPT, DeepSeek, Perplexity, Gemini, Gemma, Llama, Grok, and more.

The AI Toolkit for TypeScript. From the creators of Next.js, the AI SDK is a free open-source library for building AI-powered applications and agents

Universal LLM Deployment Engine with ML Compilation

High-performance In-browser LLM Inference Engine

Private AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research, Document analysis, Multi-model support, and API connectivity for agents.

RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.

An open source implementation of CLIP.

A framework for few-shot evaluation of language models.

Build voice agents with open-source models

💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows

A PyTorch-based Speech Toolkit

Run GGUF models easily with a KoboldAI UI. One File. Zero Install.

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.

An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries

SWE-bench: Can Language Models Resolve Real-world Github Issues?

Harness LLMs with Multi-Agent Programming

This is a Phi Family of SLMs book for getting started with Phi Models. Phi a family of open sourced AI models developed by Microsoft. Phi models are the most capable and cost-effective small language models (SLMs) available, outperforming models of the same size and next size up across a variety of language, reasoning, coding, and math benchmarks

[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments