Skip to content
View EauDoon's full-sized avatar

Achievements

Achievement: Pull Sharkx4Achievement: QuickdrawAchievement: Pair ExtraordinaireAchievement: YOLO

Achievements

Achievement: Pull Sharkx4Achievement: QuickdrawAchievement: Pair ExtraordinaireAchievement: YOLO

Block or report EauDoon

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.

Content in all repositories owned by your account will be closed.
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
EauDoon/README.md
Daniel Oon. Decision infrastructure for agent systems and operators.

Website  ·  LinkedIn  ·  @EauDoon

I build tools for agent systems and business decisions, with explicit rules, recoverable actions, and evidence you can inspect.

A constellation of fourteen catalogued projects and Scout (private), grouped into speed launches, agent systems, decision tools, and practical experiments, with Scout alongside Blitz. Open the project catalog for catalogued project links.

Scout (private) provides optional investigation and comparison within Thor, alongside Blitz.

Selected work

Blitz. Minimum Viable Company kit. Four evidence gates take one bounded offer through a real test to an accepted result and a feasible next cycle.

Repository  ·  Worked example


Gauntlet Verify. Eval the evals, two modes. Blind judges hold a build to a shipped reference, and isolated verifiers label each claim verified, reported, or unverified.

Repository


Decision Labs. Four local browser workbenches for partnerships, pooled buying, structured agreements, and weekend liquidity.

Repository  ·  Worked example


Agent Team OS. A wire format and tool pack for multi-role agent work. Local checks catch missing brief fields, dependency cycles, unsourced claims, and stale audit rechecks.

Repository  ·  Worked example

Experimental software and synthetic worked cases. These checks do not establish customer adoption, production reliability, or business impact.


Browse the project index

Agent infrastructure

  • Agent Action Stack connects policy checks, action recovery, and dispute evidence in a runnable synthetic reference path.
  • Consequence Rail provides recourse-gated execution, recovery preflight, and signed settlement receipts.
  • Constitutional Agent Testbench checks structured agent responses against policy rules with deterministic precedence traces.
  • MandateBound is experimental evidence review for agentic commerce; its synthetic example distinguishes a complete case, missing evidence, and tampering.
  • Hermes Parallel Follow-ups carries reversible patches for a documented source revision, with bounded concurrency and cancellation tests.

Decision methods

  • Unconventional Moves is a decision skill for comparing practical approaches and planning reversible experiments.
  • Crypto Research Desk combines research-only workflows with a browser workbench for evidence packets and independent risk review.

Experiments and examples

  • Operator Labs contains two offline Python tools for synthetic payment-route comparison and OTLP privacy-regression checks.
  • llms-txt-personal-site is a static-site template with Markdown, llms.txt, JSON-LD, and reproducible build checks.
  • connect.md supports local Markdown profile and resume drafting, preview, session recovery, and exports. Optional network services require separate deployment.
  • Stable Desk is a browser-local stablecoin research workbench with a synthetic baseline and human-reviewed decisions. Exported files are its backups; hosted source identity is unverified. No license has been selected, so public visibility does not grant reuse permission.

Fork contribution

Reflection Engine adds a bounded prompt and offline source-preparation and review tools to Kevin Rose's original. The original prompt and attribution are preserved. Other assessed forks are labeled separately in the catalog.

Full project catalog  ·  Search and setup  ·  Review workflows

The catalog is a dated source snapshot. Repository licenses and upstream attribution define reuse.

Pinned Loading

  1. agent-action-stack agent-action-stack Public

    Decide with Constitutional Agent Testbench, act with Consequence Rail, prove disputes with MandateBound.

    JavaScript

  2. consequence-rail consequence-rail Public

    Recourse-gated execution, recovery preflight, and signed settlement receipts for autonomous actions.

    JavaScript

  3. decision-labs decision-labs Public

    Four independent, local-first browser workbenches for partnership thresholds, pooled buying, structured agreements, and weekend liquidity.

    JavaScript

  4. hermes-parallel-followups hermes-parallel-followups Public

    Two MIT patches for Nous Research Hermes: stop busy-queue messages merging into one jumbled turn, and optionally run self-contained follow-ups in parallel.

    Python

  5. llms-txt-personal-site llms-txt-personal-site Public

    A forkable template for a personal website whose primary audience is an AI assistant. Markdown pages, llms.txt, JSON-LD, and a quality gate.

    Python

  6. mandatebound mandatebound Public

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

    TypeScript 1