🪢 Open source AI engineering platform: AI Gateway, agent observability, evals, and prompt/skill management, built on OpenTelemetry. One open platform for every AI call and every agent. Self-host or use Langfuse Cloud.
Scanning GitHub for open-source AI projects that are actually worth running: self-hostable, forkable, with a clear license. Star counts and languages are verified against each repository.
🪢 Open source AI engineering platform: AI Gateway, agent observability, evals, and prompt/skill management, built on OpenTelemetry. One open platform for every AI call and every agent. Self-host or use Langfuse Cloud.
SGLang is a high-performance serving framework for large language models and multimodal models.
AI Observability & Evaluation
Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.
AirLLM 2.8T LLM inference with single 4GB GPU
A hands-on guide to fine-tuning and deploying open LLMs and multimodal models on Linux, covering full-parameter training and LoRA.
This repository contains the Hugging Face Agents Course.
Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.
A full-stack RAG engineering guide: how to build retrieval-augmented LLM applications end to end, with a free online edition.
SOTA Open Source TTS
Distribute and run LLMs with a single file.
This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial.
YuE2: frontier music generation with symbolic planning, zero-shot covers, and agentic music editing.
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
A high-throughput and memory-efficient inference and serving engine for LLMs
LlamaIndex is the document processing platform for AI
LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
Your AI workspace for models, agents, and productivity.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.