Code-as-World
Code as World: Agentic Discovery of Executable World Representations for Physical Reasoning
HYSEN LABS DIRECTORY
Language tag · curated repositories and deep analysis.
Code as World: Agentic Discovery of Executable World Representations for Physical Reasoning
🛍️ The TUI app store: browse, search & one-key-install hundreds of terminal apps.
The OKF toolkit for Claude Code — author, maintain, validate & visualize Open Knowledge Format bundles. Plugin, agent skills, and a GitHub Action.
Proxy Checker is a self-hosting-first, free tool for checking, filtering and maintaining proxies: it pulls continuously updated public proxy sources, batch-tests HTTP, HTTPS, SOCKS4, SOCKS5 and SOCKS5H, keeps the working ones in "My Repository", and generates stable TXT/JSON links that scripts, services or other tools can pull directly. Useful if you regularly work with proxies, account farms or API connectivity.
Educational package-manager project for AI agent skills. Not actively maintained.
Douyin Auto Spark Renewal - a GitHub Actions-based tool that automatically keeps Douyin 'sparks' alive, supporting scheduled text and native emoji sending, no server required.
Model Compression Toolkit (MCT) is an open source project for neural network model optimization under efficient, constrained hardware. This project provides researchers, developers, and engineers advanced quantization and compression tools for deploying state-of-the-art neural networks.
Monitor and drive your herdr agents from menu bar, phone, or Telegram. Zero config locally. Free tunnel for remote. No Tailscale needed.
A full-pipeline intelligent bidding agent: tender document generation, bid interpretation, document review, AI-formatted bid documents, and business opportunity discovery, all in one click. 21 compliance checks, multi-model switching, RAG knowledge base, and OCR extraction. Full AI automation from tender announcement to a deliverable docx.
Seeed SenseCraft Model Assistant is an open-source project focused on embedded AI. 🔥🔥🔥
Run Claude agents in secure cloud sandboxes — via API, CLI, or Slack. One call. Full agent. Zero infrastructure.
VexJoy AI Agent with Intelligent Routing - /do routes plain-English requests to the right specialist agent and gates the work with reviews, tests, and a learning loop.
A general-purpose desktop-pet agent framework that supports importing custom character packs, letting characters perceive screen content and system events and react naturally to the user's current context.
Python and TypeScript SDKs for verifiable evidence of AI agent actions. Signed receipts, policy enforcement, audit trails. Works with LangChain, CrewAI, MCP.
[ICML 2026] Let LLMs invent and evolve languages for efficient reasoning.
Job OK: an evidence-driven job-search Agent Skill for Chinese-speaking job seekers, supporting strength discovery, job matching, resume optimization, interview training, and application tracking.
A productivity kit for solo entrepreneurs - automated 58 tasks without employees, releasing 38 ready-to-use AI agent skills (plus 19 execution scripts).
ExploitBench measures how far AI agents climb, from reaching vulnerable code, to triggering the bug, to building exploit primitives, to arbitrary code execution.
Generative AutoML for Tabular Data
The Python toolkit for computing with string diagrams.