finetrainers
Scalable and memory-optimized training of diffusion models
HYSEN LABS DIRECTORY
License tag · curated repositories and deep analysis.
Scalable and memory-optimized training of diffusion models
RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.
TokenHub gives enterprises a private gateway to unify AI model access and governance, making every request controllable, traceable, and attributable.
Extension for Scikit-learn is a seamless way to speed up your Scikit-learn application
Infinispan is an open source data grid platform and highly scalable NoSQL cloud data store.
A 3B-active-parameter native unified multimodal model for image and video understanding, generation, and editing.
Building LLM-Enabled Multi Agent Applications from Scratch
Install our local first extensions for your favorite AI IDE or Terminal Agent. Process your histories into reusable skills with Lore. Sync your conversations to the cloud. File issues and requests.
Build, train, optimize, and run computer vision models locally, from raw images to live inference. Open source, optimized for Intel XPU (CPU-only and CUDA also supported).
AI-powered tool for efficient abstract and PDF screening in systematic reviews.
High performance, easy-to-use, and scalable package for learning large-scale knowledge graph embeddings.
Wenyan MCP Server lets AI automatically format Markdown articles and publish them to WeChat Official Accounts.
Bernini is a unified framework for video generation and editing that combines an MLLM-based semantic planner with a DiT-based renderer.
Shevery - Modernized Android manager with Jetpack Compose, Material 3, and compatibility enhancements.
AI-first 3D & AR SDK for Android (Jetpack Compose + Filament), Apple (SwiftUI + RealityKit) and the web. Opens glTF/GLB, 3MF, STL, OBJ and PLY on Android and USDZ on Apple, at real size in AR. An assistant reads llms.txt and writes code that compiles first try; also an MCP server and a ChatGPT/Codex plugin.
Open-source semantic layer: one cube for Excel (MDX/XMLA), dashboards, and AI agents (MCP). Mondrian + Apache Calcite.
CLI runbook for agent long run.
SGLang-Omni is a high-performance serving framework for audio models (TTS, ASR) and unified multimodal models.
AgentSociety 2 is a modern, LLM-native agent simulation platform designed for social science research and experimental design. It provides a flexible framework for creating and managing intelligent agents in simulated environments.
ApeRAG: Production-ready GraphRAG with multi-modal indexing, AI agents, MCP support, and scalable K8s deployment