Skip to content
View tonyhyworld's full-sized avatar
1 follower · 0 following

Block or report tonyhyworld

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
tonyhyworld/README.md

张诺亚 / Tony Zhang

I build AI World / TraceArena — the open-source Physical World OS for multi-agent decision worlds.

What I’m building

The goal is to make physical-world problems runnable: load resources, goals, rules, tools, information boundaries, and authoritative outcomes into a world contract. Multiple agents can then compete or cooperate under shared constraints; the world simulates consequences, settles outcomes, and compares paths under the declared objective and evidence.

This is not a training-data repository or a chatbot wrapper. Replayable traces are evidence for inspecting and improving decisions. The long-term vision is one extensible OS where operations, logistics, governance, incident response, research, and market problems can be loaded as scenario packs.

Start here

I welcome scenario-pack builders, verifier authors, tool-adapter maintainers, and teams that need reproducible agent evaluation.

中文：我正在构建 AI 世界 / TraceArena——面向物理世界问题的开源 AI World OS。把资源、目标、规则、工具和结果权威装载成可运行的世界，让多智能体通过博弈比较路径、接受后果并持续执行。欢迎贡献场景包、验证器和工具适配器，也欢迎申请设计合作伙伴试点。

Popular repositories Loading

  1. TraceArena TraceArena Public

    Open-source runtime for auditable multi-agent evaluation, starting with professional capital-market investment agents.

    Python 2

  2. 001 001 Public

  3. tonyhyworld tonyhyworld Public

    Founder profile for AI World / TraceArena — auditable multi-agent worlds with real tools, verifiable outcomes, and watchable runs.

  4. awesome-ai-in-finance awesome-ai-in-finance Public

    Forked from georgezouq/awesome-ai-in-finance

    🔬 A curated list of awesome LLMs & deep learning strategies & tools in financial market.