decision-making

Structured multi-perspective deliberation for hard decisions. Run full councils, focused triads, or duo debates across Claude Code, Codex, Gemini CLI, and OpenCode.

[ICLR 2023] ReAct: Synergizing Reasoning and Acting in Language Models

A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.

First Principles Framework (FPF): Pattern language and core specification for admissible action in problematic engineering, research, and mixed human/AI work.

Claude Code plugin: universal radial-tree exploration engine. One tree skill + swappable presets (brainstorm / attack / design / code-audit) for divergent ideation, adversarial critique, and design-space exploration. 12 framings × hard-ban-on-incomplete-leaves × stable convergence.

[ICML 2024] The offical Implementation of "DecisionNCE: Embodied Multimodal Representations via Implicit Preference Learning"

Auxiliary code for pulling, loading reinforcement learning models based on DI-engine from the Huggingface Hub, or pushing them onto Huggingface Hub with auto-created model card.

[ICLR 2025] The offical implementation of "PSEC: Skill Expansion and Composition in Parameter Space", a new framework designed to facilitate efficient and flexible skill expansion and composition, iteratively evolve the agents' capabilities and efficiently address new challenges

Make your AI think like Munger, Feynman, or Paul Graham — load real mental models, not personas.

A structured failure-analysis workflow that assumes your plan already failed and works backward to find every reason why. Based on Gary Klein's premortem method (Harvard Business Review), validated by prospective-hindsight research from Wharton and Cornell

A reasoning skill for AI agents to improve complex judgment, premise auditing, counterargument pressure, and verifiable conclusions.