Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"

MiniCPM-V 4.5: A GPT-4o Level MLLM for Single Image, Multi Image and High-FPS Video Understanding on Your Phone

ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型

[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

The Desktop AgentOS.

Klavis AI (YC X25): MCP integration platforms that let AI agents use tools reliably at any scale

The open source platform for AI-native application development.

Nexent is a zero-code platform for auto-generating agents — no orchestration, no complex drag-and-drop required. Nexent also offers powerful capabilities for agent running control, data processing …

[ICLR 2025] Hallo2: Long-Duration and High-Resolution Audio-driven Portrait Image Animation

A Doctor for your data

The next generation deep reinforcement learning tookit

Easiest and laziest way for building multi-agent LLMs applications.

Run AI models end-to-end encrypted.

https://dev.to/answeryt/the-demo-spell-and-production-dilemma-of-ai-agents-how-i-built-a-self-learning-agent-system-4okk

This project is the official implementation of 'DreamOmni2: Multimodal Instruction-based Editing and Generation''

Applications self-hosting and DevOps platform for running open source, web-based linux Panel of lite PaaS

Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities。

【ICML 2025 Spotlight】 Official Repo for Paper ‘’HealthGPT : A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation‘’

Distributed GPU-Accelerated Framework for Evolutionary Computation. Comprehensive Library of Evolutionary Algorithms & Benchmark Problems.

Res-SAM Framework for GPR Underground Hazard Detection

[NeurIPS 2024] DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curation

Video generation from text&image, 1st-gen

Lumina-DiMOO - An Open-Sourced Multi-Modal Large Diffusion Language Model

Unified Multimodal Model for image generation/editing/understanding

Official implementation of OpenWBT.

[ICCV 2025] Region-Aware Text-to-Image Generation via Hard Binding and Soft Refinement 🔥

A blueprint for building production-ready RAG systems that minimize hallucination, featuring switchable 3-step (Speed) and 4-step (Precision) pipelines.