Loki: Open-source solution designed to automate the process of verifying factuality

🚀 PR-Agent: An AI-Powered 🤖 Tool for Automated Pull Request Analysis, Feedback, Suggestions and More! 💻🔍

Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthr…

A high-throughput and memory-efficient inference and serving engine for LLMs

Use OpenAI GPTs for Free: https://gptcall.net/

An AI developer tool that turns tickets directly into code.

CLI platform to experiment with codegen. Precursor to: https://lovable.dev

Text-To-Speech, RAG, and LLMs. All local!

Build applications that make decisions (chatbots, agents, simulations, etc...). Monitor, trace, persist, and execute on your own infrastructure.

Open source AI coding agent. Designed for large projects and real world tasks.

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

LLM training in simple, raw C/CUDA

A project structure aware autonomous software engineer aiming for autonomous program improvement. Resolved 37.3% tasks (pass@1) in SWE-bench lite and 46.2% tasks (pass@1) in SWE-bench verified with…

Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/

LM Studio JSON configuration file format and a collection of example config files.

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

Numbers every LLM developer should know

A comprehensive guide to building RAG-based LLM applications for production.

RayLLM - LLMs on Ray (Archived). Read README for more info.

LLMPerf is a library for validating and benchmarking LLMs

The official Python client for the Hugging Face Hub.

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

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

🤗 The largest hub of ready-to-use datasets for AI models with fast, easy-to-use and efficient data manipulation tools

Grok open release

Awesome-LLM: a curated list of Large Language Model

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.