Skip to content
View joy7758's full-sized avatar
3 followers · 9 following

Achievements

Achievement: QuickdrawAchievement: Pull SharkAchievement: Pair Extraordinaire

Achievements

Achievement: QuickdrawAchievement: Pull SharkAchievement: Pair Extraordinaire

Highlights

Block or report joy7758

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 supported. This note will be visible to only you.
Report abuse

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

Report abuse
joy7758/README.md

Bin Zhang

Independent researcher exploring governance infrastructure for AI agents.

My work focuses on how autonomous AI systems can become:

  • Identifiable (persona layer)
  • Observable (execution trace)
  • Auditable (evidence records)
  • Governable (runtime control)

AI Agent Governance Stack

Minimal research architecture for auditable AI agents.

flowchart TD

A[Persona Layer<br>POP] --> B[Agent Runtime]

B --> C[Execution Trace]

C --> D[Audit Evidence<br>ARO]

D --> E[Governance Controls<br>Token Governor]
Loading

Core Projects

Persona Object Protocol (POP)

Portable persona layer for AI agents.

https://github.com/joy7758/persona-object-protocol

ARO Audit

Evidence generation and audit records for agent execution.

https://github.com/joy7758/aro-audit

Token Governor

Runtime token cost and policy control for AI agents.

https://github.com/joy7758/token-governor

Verifiable Agent Demo

Minimal end-to-end governance pipeline demo.

https://github.com/joy7758/verifiable-agent-demo

Research Direction

Current focus:

  • AI Agent Observability
  • Agent Governance Architecture
  • Verifiable Agent Execution
  • Digital Object Infrastructure (FDO)

Contact

GitHub discussions and issues welcome.

Pinned Loading

  1. persona-object-protocol persona-object-protocol Public

    A lightweight public draft protocol for portable persona objects in multimodal AI systems.

    Python 1

  2. aro-audit aro-audit Public

    A lightweight audit and provenance layer for AI execution integrity.

    Python 1

  3. token-governor token-governor Public

    天将｜LLM 智能体运行时资源控制引擎：Token 预算控制、成本优化、稳定性 Guard、多工具 Agent 调度

    Python 1

  4. verifiable-agent-demo verifiable-agent-demo Public

    Python