[ICLR 2022 Oral] Official PyTorch Implementation of "Transform2Act: Learning a Transform-and-Control Policy for Efficient Agent Design".

🦞 Production-grade AI Agent design system — 龙虾教练：产品级 AI Agent 设计体系

HumanStudy-Bench: Towards AI Agent Design for Participant Simulation

HumanStudy-Bench: Community Edition — Standardized human study replays for AI agent evaluation

Vendor-neutral agent design skill inspired by Claude Code-class systems.

CrewAIMaster transforms any task description into a fully functional, production-ready multi-agent system, making advanced AI orchestration accessible to everyone.

Enterprise-grade AI Architect for multi-agent system design. Transform natural language into agent blueprints, flowcharts & executive reports. Powered by Gemini 3 Pro. Built for Google Gemini API Developer Competition 2025.

Consultant-grade skills, workflow, and templates for designing, evaluating, launching, and iterating AI Native products.

Simplifying and understanding the various Agent design patterns.

An open-source engineering blueprint for defining and designing the core capabilities, boundaries, and ethics of any AI agent.

Building AI systems from first principles, focusing on retrieval, evaluation, and failure modes rather than demos.

Portfolio case study of Lilo, a conversational AI chatbot supporting college enrollment and reducing summer melt.

A substrate-independent governance pattern for agents operating in imperfect environments. Repo includes formal layer documentation, design rationale, reference library maintenance protocols, and validation cases demonstrating how the architecture functions across diverse failure modes and at system scale in simulated environments.

Optimizing Campus Route — An AI agent-based solution to minimize walking distance and time for completing tasks across university campus locations using search algorithms like A* and Random Restart Hill Climbing.

A reuse-first OpenClaw skill that helps non-technical users turn fuzzy needs into clear solution documents and execution-ready guidance.

Conceptual framework for designing self-aware, evolving partner agents. LLMに依存せず、自己認識と記憶を軸に進化するパートナーAIの概念設計。

A Claude cowork skill for designing AI agent architectures via Socratic deep interviewing. Five-phase pipeline: interview → recommendation → blueprint → modules → prototype. Based on Anthropic's Building Effective Agents framework.