Awesome Opensource Ai

Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience

《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码

The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, Phi4, ...) (AAAI 2025).

Deeplake is AI Data Runtime for Agents. It provides serverless postgres with a multimodal datalake, enabling scalable retrieval and training.

The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!

Open-source framework for building agentic apps in JavaScript, Go, Dart, and Python, built and used in production by Google

A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines

A Next-Generation Training Engine Built for Ultra-Large MoE Models

Align Anything: Training All-modality Model with Feedback

The Ruby-native AI framework. Chats, agents, tools, images, audio, and video through one consistent API, in plain Ruby or Rails.

One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks

An open-source model family for long-form speech, dialogue synthesis, voice design, sound effects, and real-time streaming TTS

Open-source multimodal retrieval engine (Morphik Core)

MTEB: State-of-the-art evaluation of embeddings across languages and modalities

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

[ICLR & NeurIPS 2025] Repository for Show-o series, One Single Transformer to Unify Multimodal Understanding and Generation.

Fast Multimodal LLM on Mobile Devices