sandboxed.sh
Safe runtime for autonomous on-chain AI agents: isolated sandboxes, Library skills, encrypted secrets.
HYSEN LABS DIRECTORY
Capability tag · curated repositories and deep analysis.
Safe runtime for autonomous on-chain AI agents: isolated sandboxes, Library skills, encrypted secrets.
An original single-file Three.js library of seven interactive clothbound hardcovers.
Multi-model orchestration layer for Claude Code — the frontier model plans, cheaper models execute, verification guards quality. One-prompt install.
Autonomous Android and computer use using any LLM (local or remote)
Professional video editing, right in your browser. Made with Rust, WebGPU, WASM, and Tanstack Start.
An automated AI research-paper writer based off Google's PaperOrchestra paper's implementation through a skills - benchmark + autoraters using any coding agent (Claude Code, Cursor, Antigravity, Cline, Aider). No API keys, no LLM SDKs.
CLI, SDK, and IDE plugins for Duel Agents
AI 服务分流规则聚合: 多源合并 | 按 provider 精修 | 每日自动同步. 覆盖 OpenAI / Anthropic / Gemini / Cursor / Copilot 等主流 AI 服务, 适配 Clash / Mihomo / sing-box / Surge 等主流客户端.
Wispr Flow for your lips: hold a key, silently mouth words, and they're typed at your cursor. Runs locally on your Mac.
a project brain for your AI. Give LLMs instant architectural context without burning tokens
Desktop app to control your computer with AI using your terminal, browser, mouse & keyboard
Clone of https://github.com/github/spec-kit but in Chinese
A collection of 265 rules across 26 categories that AI coding agents can use to write idiomatic, fast, and safe Rust.
An interactive app that walks through every stage of the LLM pipeline, from pattern matching to training a transformer from scratch, with working code you can run locally.
A public-opinion analysis assistant combining real-time data from 26 trending lists across 15 major platforms with LLM analysis. Through a front-end page, users can run conversational trending-list queries, topic search, topic clustering and sentiment analysis. Supports hotkey control of crawler start/stop, fast multi-platform data lookup and navigation, accumulates analysis results from news detail pages (including content mined from videos), and pushes hotspot alerts via email, WeChat, WeCom, DingTalk, QQ and Telegram.
Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (LLM).
Frontier Models playing the board game Diplomacy.
Claude Code reference: write in Louis Rossmann's voice, never like AI slop. Portable CLAUDE.md plus skills.
Open-source self-hosted AI agent runtime and multi-agent framework for autonomous agent swarms. Agent memory, MCP tools, schedules, delegation, and 23+ LLM providers (Claude, GPT, Gemini, OpenRouter, Ollama). A practical Claude Code and LangChain alternative.
QuietHarness: a lightweight AI workflow system shared by Claude Code, Codex and Cursor