sglang
SGLang is a high-performance serving framework for large language models and multimodal models.
HYSEN LABS DIRECTORY
Platform tag · curated repositories and deep analysis.
SGLang is a high-performance serving framework for large language models and multimodal models.
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more.
NVR with realtime local object detection for IP cameras. Frigate NVR - Realtime Object Detection for IP Cameras \[English\] | 简体中文 A complete and local NVR designed for Home Assistant with AI object detection.
AI Website Cloner Template guides coding agents through recreating a reference site as a structured Next.js project.
Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.
Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/
Vibe-Trading is a research framework that coordinates agents for market data collection, analysis, strategy testing, and trading reports.
Industrial-strength Natural Language Processing (NLP) in Python. spaCy: Industrial-strength NLP spaCy is a library for **advanced Natural Language Processing** in Python and Cython.
Apache Kafka - A distributed event streaming platform. We build and test Apache Kafka with Java versions 17 and 25.
This plugin lets Claude Code send repository tasks to Codex for implementation or a second code review.
You like pytorch? You like micrograd? You love tinygrad. Neural networks As it turns out, 90% of what you need for neural networks are a decent autograd/tensor library.
Visualizer for neural network, deep learning and machine learning models
Algorithm powering the For You feed on X. **Note:** The transformer implementation is ported from the Grok-1 open source release by xAI, adapted for recommendation system use cases.
go-zero is a cloud-native Go web and RPC microservices framework with built-in resilience design and goctl, a CLI that generates multi-language code from .api files.
The open agent skills tool - npx skills. Supports **OpenCode**, **Claude Code**, **Codex**, **Cursor**, and 70 more.
Project brief: Linux /Lora LLM / MLLM. "Open Source Large Model Eating Guide" is a tutorial for rapid fine-tuning (full parameters/Lora) and deployment of domestic and foreign open source large models (LLM)/multimodal large models (MLLM) based on Linux environment tailored for Chinese babies.
Fincept Terminal is a native C++20/Qt6 desktop finance application with embedded Python analytics for market analysis, investment research, and economic data tools.
Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.
Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.
gbrain adds searchable long-term notes to OpenClaw, Hermes Agent, Claude Code, and Codex so earlier work can be retrieved in later sessions.