Skip to content
View oonyl's full-sized avatar

Block or report oonyl

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
oonyl/README.md

Oonyl

AI systems builder from the business side

I turn operational problems into tested agent systems, decision tools, and reusable workflows.

This is my public build record: working artifacts, adversarial evaluations, documented failure cases, and explicit boundaries.

Featured open-source project

Consequence Rail

A reference protocol and zero-dependency runtime for recourse-gated autonomous actions. It binds each action to connector-backed recourse, verifies the resulting world state, and produces a signed settlement receipt.

Open-source projects

Flagship systems

  • MandateBound: Evidence readiness and deterministic dispute replay for UCP/AP2 agentic commerce.

Agent infrastructure

  • Agent Team: A Codex skill for coordinating bounded specialist-agent workflows with independent auditing.
  • Constitutional Agent Testbench: A deterministic Python testbench for evaluating structured responses against declared JSON rules.

Decision methods

  • Unconventional Moves: A Codex skill for practical, non-obvious approaches with reversible 48-hour tests.

How I build

Business problem → specification → implementation → adversarial evaluation → acceptance

Authorship

I direct problem selection, product direction, requirements, business judgment, evaluation, rights review, and final acceptance for the projects published here.

Pinned Loading

  1. consequence-rail consequence-rail Public

    Recourse-gated execution and settlement receipts for autonomous actions.

    JavaScript

  2. mandatebound mandatebound Public

    Evidence readiness and deterministic dispute replay for UCP/AP2 agentic commerce.

    TypeScript

  3. constitutional-agent-testbench constitutional-agent-testbench Public

    A deterministic Python testbench for evaluating structured responses against declared JSON rules.

    Python

  4. agent-team-os agent-team-os Public

    A Codex skill for coordinating bounded specialist-agent workflows with independent auditing.

  5. unconventional-moves unconventional-moves Public

    A Codex skill for practical, non-obvious approaches with reversible 48-hour tests.