Showcase

myAI

An AI brain you drop into any codebase. It crawls the repo, learns the architecture, and works like an employee — multi-agent, autonomous, mobile-controllable.

Generic AI assistants forget everything each session. myAI gives them persistent memory, cross-repo awareness, scheduled autonomous work, and human oversight from your phone.

64

Specialist agents

auto-discovered

137

Skill playbooks

trigger keywords

44

MCP gateway tools

shared fleet-wide

60

Managed repos

one hub

24/7

Off-hours runner

free-window work

The autonomous loop

One continuous cycle — from a sentence to a shipped, supported app.

1Idea

Describe an app in plain English

2App

Blueprint scaffolds a full prod-ready repo

3Schedule

Queue work for the off-hours runner

4Automate

Agents build & ship autonomously

5Remote

Drive it all from your phone

6Support

Health alerts + bug/feature triage

What it can do

Capabilities shipping today — counts are live where the gateway and database are reachable.

Multi-agent specialists

64 agents

Domain-owning agents auto-discovered by Claude Code — architecture, frontend, API, DB, security, ops, swarm coordination and more. Parallel lanes prevent collisions.

Skill playbooks

137 skills

Repeatable, named procedures with trigger keywords — code review, OWASP audit, blueprint scaffold, productionise. Loaded on demand, zero idle token cost.

MCP gateway

44 tools

A local gateway exposing tools for memory, scheduling, repo orchestration, routing and recall — shared by every repo on the machine.

Mission Control

live

This dashboard: what is running, what needs you, what is next — live across the whole fleet. Installable PWA, mobile-first.

Scheduling platform

0 scheduled

A work queue an off-hours autonomous runner drains on the free model window — schedule a task, walk away, review the diff in the morning.

Blueprint

idea→prod

One keyword scaffolds a full Next.js + TypeScript + Tailwind + Mongo + Sentry repo wired to the framework — idea to production app.

Remote control

mobile

Drive sessions from your phone — Telegram alerts and a CLI-mobile branch bridge keep CLI and mobile sessions perfectly in sync.

Multi-org orchestration

60 repos

A single hub managing 60 repos — per-repo state, handoffs, health cards and READMEs, all self-contained and portable.

Cost routing

tiered

Tier-aware model routing maps each agent/task to the right model, prefers the free Fable window for batch work, and meters real token spend.

The platform

myAI is the first of three products. The others get their own showcase, done right.

agentFlow

live

The idea→app generation pipeline built on this framework. An 8-stage agent pipeline turns a plain-English idea into a working, tested application — real codegen, not scaffolding.

1Idea

Describe the app in plain English

2Plan

Solution-architect drafts the approach

3Gap

Gap analysis against the stated goal

4BRD

Business requirements captured

5TRD

Technical requirements + contracts

6Design

UI/UX + architecture design pass

7Build

Real codegen — files land in the repo

8Ship

Reviewed, tested, deployable

AI PM vs Human PM mode

Run the pipeline fully autonomous with an AI project manager driving each stage, or take the wheel yourself and approve every stage transition.

Real codegen

Not scaffolding-only — the Build stage writes actual, working code into the generated project, not just planning documents.

Background generation

Long-running stages execute as background jobs, so a generation run survives a closed tab and picks up where it left off.

Artifact viewer

A browsable, tree-view artifact viewer across every stage — inspect and download generated files without leaving the workspace.

connect

live

The bug & feature intake hub for shipped apps. A closed loop turns a user report into a deployed fix — AI-triaged, AI-drafted, human-reviewed.

1Report

A bug or feature request lands via the widget or portal

2Triage

AI classifies severity, dedupes, and routes it

3Fix

Fix-engine drafts a patch against the target repo

4PR

Change opens as a reviewable pull request

5Deploy

Merged fix ships to the reporting app

Auto-triage

Incoming reports are classified, deduplicated, and prioritized by AI before a human ever looks at the queue.

Fix-engine

Drafts a real patch against the target repo for qualifying bugs — not just a ticket, a candidate fix.

Admin cockpit

A single dashboard for operators to review reports, approve fixes, and track the loop from intake to deploy.

Test coverage

180+ tests back the support→triage→fix→PR→deploy loop, so the automation is verified, not vibes-based.

Full capability reference

The master SHOWCASE.md, rendered live.

SHOWCASE.md not found

Could not read SHOWCASE.md. The dashboard reads it from the master repo mounted read-only at AI_ROOT — verify the volume mount in docker-compose.yml.