Discover quality open-source projects, submit projects anonymously, and claim and edit your own project.
A little curiosity. A world of open source.
THE FIRST COLLECTIONPowerInfer is a local LLM inference engine that uses activation locality to keep frequently used “hot” neurons on the GPU while computing input-dependent “cold” neurons on the CPU. It supports hybrid or CPU-only inference, serving, batching, perplexity evaluation, INT4 quantization, and PowerInfer GGUF models.
YuE2 is an open music generation model that unifies symbolic planning with audio synthesis: it turns lyrics and a style prompt into an editable melody-and-chord score, then renders a full song with vocals and accompaniment. It also supports zero-shot covers and agentic score editing.
vLLM is a high-throughput, memory-efficient library designed for Large Language Model (LLM) inference and serving.
Repomix packs an entire repository into a single AI-friendly file (XML, Markdown, JSON, or plain text) for feeding codebases into LLMs like Claude, ChatGPT, and Gemini. It offers token counting, security checks, code compression, and remote repository support.
The Chinese-LLaMA-Alpaca project enhances the original LLaMA model for Chinese NLP by expanding its vocabulary, conducting secondary pre-training with Chinese corpora, and fine-tuning with instruction data. It offers instruction-tuned models, LoRA weights, training scripts, and quantization/deployment tools for local CPU/GPU execution, supporting various ecosystem tools.
LocalAI is an open-source, self-hosted AI engine that runs LLMs, vision, voice, image and video models on any hardware, including CPU-only. It offers OpenAI, Anthropic and ElevenLabs-compatible APIs, on-demand modular backends, multi-user auth, and built-in agents with RAG and MCP.
Oumi is an open-source platform for the full foundation-model lifecycle: data preparation, training and fine-tuning (SFT, LoRA, QLoRA, GRPO), evaluation, data synthesis with LLM judges, and deployment via vLLM/SGLang, with a CLI and cloud job launching.
UL-SMF is a KV cache compression framework for long-context Transformer inference, claiming up to 384x compression via FSQ and 16D latent mapping. The core compression logic requires a proprietary closed-source binary.
LlamaFactory is a Python framework for efficient fine-tuning of 100+ large language and multimodal models, offering zero-code CLI, a Gradio Web UI, LoRA/QLoRA, and multiple training algorithms.
AstrBot is an open-source all-in-one agent chatbot platform that connects LLMs and agent frameworks to mainstream instant messaging apps like QQ, Telegram, Slack, and Feishu, with plugin extensions, WebUI, and sandboxed execution.
Langchain-Chatchat is an open-source offline RAG and Agent application based on Langchain and ChatGLM, Qwen, Llama etc., supporting local knowledge base Q&A, multiple model inference frameworks, WebUI and API.
Ollama is a tool that allows users to run, manage, and build with open-source large language models locally on macOS, Windows, and Linux.
A command-line productivity tool powered by AI LLMs. It generates shell commands, code snippets, and documentation, supports chat/REPL modes, custom roles, and function calling. Compatible with Linux, macOS, and Windows.
SGLang is a high-performance serving framework for large language models (LLMs) and multimodal models, designed for low-latency and high-throughput inference.
PocketRisu is a self-hosted AI roleplay chat platform forked from RisuAI, letting you run a personal server accessible from PC, tablet, and smartphone via web browser.
Aider is a terminal-based AI pair programming tool that allows developers to collaborate with LLMs to build new projects or modify existing codebases.
