Apps

Browse agent harnesses, automations, creative tools, and experiments from El Oruga. Newest and most agentic first.

AI Education and Community Projects

Courseware, talks, and the 2026 class on loops, workflows and objectives.

Decks, demos, and sample code to teach GenAI fundamentals to the community without the boring corporate vibes. Newest: a non-technical 16-slide class on letting AI work alone (loops, workflows, objectives) compared across Claude Code, claude.ai and ChatGPT + Codex, plus the vibe coding talk deck.

Tech: Python, JS, notebooks, demo backends

Creative GenAI Studio 2026

Image and video booths that route one prompt to the best model.

Orugas Design Studio sends prompts through a serverless proxy to a dozen image models (FLUX 2, Seedream 5, Krea 2, GPT Image 2 and more); the Video Booth drives Seedance 2.0 and Nano Banana 2 with every real parameter exposed; the rest are click-and-done prompt writers and product visualizers.

Tech: TypeScript, Next.js, Replicate, Seedance 2.0, Nano Banana 2, Groq

NimbusOS - A Browser OS in One HTML File

Window manager, 8 apps and two from-scratch 3D games, zero dependencies.

Open a single index.html and get a desktop: draggable windows, taskbar and start menu, Notes, Paint, a real Terminal, a wallpaper engine, a GTA-style open-world driver and a first-person space shooter rendered by a hand-written software 3D engine, plus Chronos, the time machine.

Tech: Vanilla JS, Canvas, software 3D engine

Fun, Games & Experimental Apps

Vibe coding experiments mixing CV, games, and playful interfaces.

Sandbox for ideas that do not fit the roadmap: CV tricks, indie games, and weird interfaces just to see what happens. Newest: Bluejay Over Toronto, a chiptune flap-and-shoot run across the 6ix with a boss fight at the CN Tower.

Tech: Python, OpenCV, JS, game engines, YOLO

ElevenLabs Voice Agents - Conversational AI Stack

Generators, templates, and demos for voice-native agents.

Everything needed to spin up ElevenLabs voices powered by OpenAI reasoning models, from config generators to ready to embed demos.

Tech: ElevenLabs, OpenAI o3, Python, JS

Luna Transcribe & Research - Voice to Workflow Automations

Turn voice into structured notes, research, and follow ups.

Windows, macOS, Linux, and web tools that capture voice, run Whisper style models, call Sonar, and output summaries ready for action.

Tech: Python, Whisper style models, ElevenLabs, Perplexity Sonar

The Agora / Agent Hub - B2B AI Agents Platform

Agent hub where Morgan, MiniMorgan and friends negotiate and collaborate on deals.

Multi agent B2B workflows, routing layers, and negotiation UX to keep company agents talking without humans babysitting.

Tech: OpenAI API, Realtime API, Python, React, agent frameworks

Data Science and Forecasting Apps

Classic ML for churn, segmentation, and sales forecasting.

Small but sharp apps that bridge traditional ML and newer GenAI workflows, used when a quick analytic read is faster than training a model from scratch.

Tech: Python, scikit-learn, statsmodels, ARIMA, K-means

Luna - Personal AI Assistant Ecosystem

Suite of agents that read email, touch Salesforce, watch Jira, and talk back.

Luna stitches voice, Salesforce, Jira, Outlook, and automation glue so one assistant can cover daily work, experiments, and weird workflows.

Tech: Python, OpenAI API, ElevenLabs, Gradio, Salesforce APIs, Jira APIs

Most of what I build these days ships inside companies, under NDA and their IP. No repos, no screenshots, no client names. What I can tell you is what each agent does, how it is built, and whether it is live. Ask Neo-Oruga (red pill) if you want the longer story.

Agents built for clients

NDA · IP protected

Classified Project 01 · Code: Greek God 001

An AI agent that uses Slack as its UI.

Persistent memory per person, so it remembers what you talked about weeks ago. A personal assistant that summarizes your inbox, briefs you before meetings and keeps reminders. Deep search across the company’s Google Workspace (Drive, Gmail, Calendar) with per-user isolation, so everyone only sees what they already have access to. Writes only behind approval gates.

Tech: Claude Code harness, Vertex AI, Slack, Google Workspace APIs, GCP

Status: In production for a client, under NDA.

NDA · IP protected

Classified Project 02 · Code: Greek God 002

The general company agent, top tier, single door into a fleet of agents.

A control plane that decides who may do what, a data plane that executes, and a web UI. Trusts everyone only up to their clearance and fails closed. Other agents plug in as vassals: they keep their own code and runtime, it becomes the one entry point and the one place where access is decided.

Tech: TypeScript, Claude on Vertex AI, GCP, capability tokens

Status: Code complete, deployment gated. Under NDA.

NDA · IP protected

Classified Project 03 · Code: Greek God 003

Autonomous employee onboarding and lifecycle automation.

When someone joins, the agent provisions the accounts, writes them a personalized welcome, walks them through role-specific onboarding in Slack and follows up until each step is done. Covers IT, pipeline and business operations, and the same rails handle role changes and offboarding.

Tech: Python, Claude on Vertex AI, Google Workspace admin APIs, Slack, GCP

Status: In production for a client, under NDA.

NDA · IP protected

Classified Project 04 · Code: Greek God 004

Compliance agent for access and policy hygiene, not surveillance.

Audits the state of access and policy (who has what, which rules are stale), never the content people produce. Report-only by design: findings land as a Slack digest and an HTML dashboard, with any enforcement deferred behind dry runs, a double key and an undo. Reads the onboarding agent’s memory through a one-way wall.

Tech: Claude Code harness, Python, Slack, Google Drive (create-only)

Status: Designed and documented (PRD + solution design). Under NDA.

NDA · IP protected

Classified Project 05 · Code: Greek God 005

Requests and approvals platform: request, approve, purchase.

A small internal platform where teams file requirements and authorizations flow to the right approver, with dashboards and an action assistant that drafts and explains but never writes on its own. Deliberately a platform, not an autonomous agent.

Tech: Next.js, TypeScript, SQL, Claude on Vertex AI, Cloud Run behind identity-aware proxy

Status: In production for a client, under NDA.

NDA · IP protected

Classified Project 06 · Code: Greek God 006

Mines a project’s Slack and email into an executive dashboard.

Reads the channels and the related inbox for a production, extracts decisions, risks, blockers and follow-ups, and rebuilds a dashboard on every run with only the delta since the last one. Leadership gets the signal without reading a thousand messages.

Tech: Python, Claude, Slack API, Gmail API, Google Drive, static dashboard

Status: In production for a client, under NDA.

NDA · IP protected

Classified Project 07 · Code: Greek God 007

CRM activity pushed into Slack, on demand or scheduled.

Pulls recent deal and contact activity from the CRM and posts a clean feed into the sales channel, with an on-demand scan command for when someone needs the latest before a call.

Tech: Python, HubSpot API, Slack

Status: In production for a client, under NDA.

NDA · IP protected

Classified Project 08 · Code: Greek God 008

Event-driven agent that turns flagged emails into tracked rows.

A Gmail watch fires a Pub/Sub event, the agent maps the email into a structured row in the team’s tracking base with a small fast model, labels the thread, and never replies, forwards or deletes anything. Built as a skill-per-feature harness so the dev team can add the next feature the same way.

Tech: Claude Haiku via claude -p, Gmail API, Cloud Pub/Sub, AirTable, systemd on a GCP VM

Status: In production for a client, under NDA.

NDA · IP protected

Classified Project 09 · Code: Greek God 009

Audits and aligns a studio pipeline against a naming and structure policy.

A CLI plus dashboard that compares every project’s folders and assets to a policy file, proposes fixes in two lanes (cosmetic labels always safe, path-sensitive slugs guarded), keeps an undo trail, and reports how many releases behind each pipeline addon is with the missing release notes inline.

Tech: Python, Click, official pipeline SDK, GitHub API, Cloud Run

Status: In production for a client, under NDA.

My own harness, a.k.a. the modifications to Claude

Everything above is built by me plus a heavily customized Claude Code. These are the modifications that make it work like a team instead of a chatbot.

Private · not published

ARISE: two-layer memory harness

Every project wakes up knowing what happened last time.

Layer one is a Karpathy-style LLM wiki: curated, interlinked markdown over immutable sources, with ingest, query and lint. Layer two is verbatim recall through a local memory palace that mines the project and past sessions with zero API calls. An awakening protocol runs at every session start and a compact hook files what was learned before context is summarized. Personal, work and harness-only modes.

Tech: Claude Code hooks and skills, MemPalace, markdown

Status: Private. Installed in every project, never published.

Private · not published

Bitacora: a logbook per code file

No edit without a declared why, no why without a verification.

A pre-edit hook blocks any change to a code file until the agent declares what it is about to change and why; a post-edit hook records what actually changed; a stop hook reports every entry left without a reason or a verification. One JSON per file, mirror tree, local only, never committed. Applies to the main agent and to every subagent.

Tech: Node, Claude Code PreToolUse / PostToolUse / Stop hooks

Status: Private. Running on every project on this machine.

Private · not published

Model tunnel for creative and build work

Claude orchestrates, a second model writes the creative prompts.

A sealed subprocess runs an isolated agent against a different model provider with its own empty config, so nothing from the main harness leaks and the main session stays on Anthropic. Claude writes the technical spec, validates the output and operates the generators; the tunnel writes image and video prompts and design-forward frontends. Every run reports real cost.

Tech: Node, claude -p, isolated CLAUDE_CONFIG_DIR, Kimi K3

Status: Private. Used for the covers on this very page.

Private · patterns public

Autonomous build loops and adversarial review

Goal, boundaries, verifier, evolve cadence. Then let it run.

A loop contract per project (state, logs, backlog, gates) that an agent reads top to bottom, takes the next unblocked item, ships it with tests, and updates its own state before ending the run. Paired with an adversarial review skill that spawns one refuter per claim, each trying to kill it with reproducible evidence, and only lets through what survives. The Orugas game on this page came out of 43 runs of this loop.

Tech: Claude Code skills, Agent Teams, Workflow scripts, git worktrees

Status: Private, patterns published in claude-skills.

Private · not published

Oasis: an autonomous ticket office

Jira-grade tickets that Claude Code desks pick up and drain on their own.

Multi-project ticket board with epics, acceptance criteria and per-project keys, where each desk is a Claude Code skill running as a real headless agent. A scheduled drainer works the queue, a planner must write acceptance criteria before anything ships, and a big red emergency stop halts the office from any page.

Tech: Next.js, Postgres, Drizzle, claude -p, Windows Task Scheduler, Vercel

Status: Private repo, live for personal use.

Private · not published

Voice, presence and small rituals

A doorbell with context, not a screen reader.

When a turn ends, a one-line spoken summary in first person tells me whether something got done or the agent is waiting, only in the session that asked for it and only if the webcam confirms I am at the desk. Plus a general brain that remembers across every project, and a mesh where each laptop’s Claude Code is an agent that wakes up when mentioned in a channel.

Tech: ElevenLabs, Claude Haiku, Claude Code UserPromptSubmit and Stop hooks, Buzz relay

Status: Private. Running daily.