pruna
Pruna is a model optimization framework built for developers, enabling you to deliver faster, more efficient models with minimal overhead.
HYSEN LABS DIRECTORY
Curated repositories with precise taxonomy, verified metadata and practical context.
Pruna is a model optimization framework built for developers, enabling you to deliver faster, more efficient models with minimal overhead.
A visual tool to edit HTML and Markdown files, leave comments like a Google Doc, and send feedback to your AI agent. Works inside your favorite AI harness.
An open-source personal learning agent with three-layer memory (learner profile / wiki knowledge base / cross-conversation recall), a proactive scheduler, personal IM channels, and a workspace-scoped Practice Lab — built on the Pi SDK.
Autoprompt is a coding-agent skill that cuts failures by 45% on agentic coding tasks.
🪐 🔧 Model Context Protocol (MCP) Server for Jupyter.
Destiny 2 Offline Exploration Mod
Review code 100X faster. Lens draws every PR as animated architecture and data-flow walkthroughs, inside the pull request itself. Use it as a GitHub App, GitHub Action, CLI, or a skill for your coding agent
OpenWrt 一体化透明代理方案:一条命令装完 sing-box 内核 + 管理面板,浏览器打开即用
The Open-Source Data Annotation Platform
BaseAI — The Web AI Framework. The easiest way to build serverless autonomous AI agents with memory. Start building local-first, agentic pipes, tools, and memory. Deploy serverless with one command.
Transformers4Rec is a flexible and efficient library for sequential and session-based recommendation and works with PyTorch.
OpenCode plugin that uses your existing Claude Code credentials — no separate login needed.
Multi-OS sandbox to run AI agents with better constraints (it is not 100% secure, but enough)
Continuously sync your AI setups with one command. Codebase tailor suited agent skills, MCPs and config files for Claude Code, Cursor, and Codex.
Instructional notebooks on music information retrieval.
Scalable machine 🤖 learning for time series forecasting.
javascript for 's, a tiny runtime with big ambitions. Each runtime loads the same bench-coldstart.js script from examples/npm/hono/ that creates a Hono app with two routes, prints "ready", and calls process.exit(0).
NobodyWho is an inference engine that lets you run LLMs locally and efficiently on any device.
Embeddable JSON form builder for React, Angular, Vue, and plain JavaScript. Drag-and-drop UI, your backend.
一个轻量高性能的内网穿透,二进制体积大约5MB ,支持 TCP、QUIC、KCP、WebSocket 传输协议,支持 TCP、UDP、HTTP、HTTPS、SOCKS5 协议代理,提供纯Rust原生跨平台桌面客户端和服务端 Web 界面