Sàn agent

SPEC-First Agentic Development Kit for Claude Code — 24 AI agents + 52 skills with TDD/DDD quality gates, 16-language projects, 4-language docs. Go CLI, zero deps.

Modular Reinforcement Learning (RL) library (implemented in PyTorch, JAX, and NVIDIA Warp) with support for Gymnasium/Gym, NVIDIA Isaac Lab, MuJoCo Playground and other environments

One sentence creates an AI-driven world — generate maps, characters, and watch stories emerge on their own. 一句话生成一个AI自主驱动的世界.

AI coding dream team of agents for VS Code. Claude Code + openai Codex collaborate in brainstorm mode, debate solutions, and synthesize the best approach for your code.

An IOS Simulator Skill for ClaudeCode. Use it to optimise Claude's ability to build, run and interact with your apps. I mainly use it as an xcodebuild wrapper to save context.

Low code tool to rapidly build and coordinate multi-agent teams

First AI Journey for DevOps - with comprehensive learning paths, practical tips, and enterprise guidelines

Portable, vendor-agnostic agent harness for project-specific skills, workflows, and agent teams aligned with your codebase, conventions, and engineering standards.

Resources to learn AI

Open-source AI agent harness in native Rust — GUI, CLI, headless, and webapp from one binary. Multi-provider, MCP, skills, plugins, agent teams.

Independently authored prompt templates for AI coding agents — system prompts, tool prompts, agent delegation, memory management, and multi-agent coordination. Informed by studying Claude Code.

Steno is the AI powered intelligence layer for all your confidential conversations. Capture beautiful notes whilst keeping your data confidential. Perfect for government, defence, legal and CXOs.

Structured deep research skill for Claude Code/Open Code/Codex with human-in-the-loop control

A set of tools that gives agents powerful capabilities.

A Python-based lightweight robot simulator designed for navigation, control, and learning

The collaborative spreadsheet for AI. Chain cells into powerful pipelines, experiment with prompts and models, and evaluate LLM responses in real-time. Work together seamlessly to build and iterate on AI applications.

turns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then runs tree search with parallel subagents.

Agentic desktop GUI client for Elasticsearch, OpenSearch, DynamoDB, MongoDB & EasySearch. Natural language queries, visual management, and monitoring. Privacy-first. Open source.

From Automated Idea Factory to Realization

ToRA is a series of Tool-integrated Reasoning LLM Agents designed to solve challenging mathematical reasoning problems by interacting with tools [ICLR'24].

AWS Skills for Agents

Open-source private logbook with a local agentic layer. Long-living AI agents read what you record and propose what to do next. Hardware permitting, the models runs locally too. Matrix + Vodozemac for end-to-end encrypted sync between your own devices.

Zero, your trustworthy AI teammate for real work.

Open Source ClaudeCode Leaked. Same functionalities as Claude Code by Anthropic. Written in Rust, Ready to use immediately for free.