Let's build AI apps with AI
Oridecon Labs is a one-person AI studio: a human sets the specs, coding agents like Claude Code do the typing. Everything ships on QuadKit — our open-source Python framework built for agents — backed by 40+ in-house packages, ready to power our products.
THE FRAMEWORK
Our tool: the QuadKit framework
QuadKit is our open-source Python framework for AI backends — async-first, contract-driven, and built so a coding agent can operate it end to end: 590+ typed protocols, 240+ error codes, one explicit boot graph.
Every Oridecon Labs project runs on it — it is the foundation under everything you'll see below.
GET STARTED
Two doors into QuadKit
Start from the terminal with your coding agent, or compose visually on the canvas — both produce a real, standalone QuadKit project.
FROM THE TERMINAL
01 Build with your coding agent
A Python backend an LLM can actually operate: 590+ protocols, 240+ error codes, an explicit boot graph, and docs that ship in the format agents already fetch. Not autocomplete — build.
FROM THE CANVAS
02 Drag, wire, start
A visual node-canvas app builder, built with QuadKit itself. Compose QuadKit applications by dragging nodes and wiring typed edges — then generate a real, standalone project with one click.
No signup required. The canvas graph is the source of truth — one-way codegen produces a complete QuadKit project.
I'm building a Python backend with the QuadKit framework. First read https://oridecon.dev/agents.md and follow it as your operating manual, then help me scaffold the project and build my feature.
QuadKit never duplicates its rules. One sentence, one URL: the operating manual is oridecon.dev/agents.md.
FROM OUR LABS
Products ready to scale
Built with Claude Code + QuadKit
One developer, one framework, unlimited possibilities — each proving a real market with QuadKit's composable contracts. Interested in pushing any of these further? Have an MVP in mind? Let's build it.
40+ private in-house packages ready to power every Oridecon Labs project. See their examples in Extended Examples.
Muralla · operator console
Codename: Muralla
AI API Gateway
Every AI team wires providers differently — OpenAI here, Anthropic there, Gemini somewhere else. Each has its own auth, rate limits, error shapes, and billing. Muralla collapses that chaos into one OpenAI-compatible endpoint with intelligent failover across 17 providers, per-model quota enforcement, and a 10-stage relay pipeline that handles governance, cost tracking, and streaming — so your app talks to one API and everything else is the gateway's problem.
What's built
- Byte-exact OpenAI-compatible API — drop-in replacement for any OpenAI SDK client
- 10-stage relay pipeline — guards, governance, channel selection, protocol conversion, cost tracking, billing
- Circuit-breaker failover — 3 retry attempts across priority-weighted channels with health tracking
- Stripe billing — pre-consume quota check, post-relay settlement, subscription and top-up flows
- React 19 operator console — channels, models, users, tokens, governance, playground, audit
What's next
- Public AI-API resale storefront — tiered subscriptions, per-request markup
- Enterprise — dedicated instances, SLA, SSO, RBAC
- Multi-region deployment with cross-region failover
- Model fallback chains with quality scoring
- Provider rate-limit autoscaling
12 in-house QuadKit packages
Cinerama · episode timeline
Codename: Cinerama
AI Continuous Movie Series Production
The hard part of AI video isn't any single model — it's coordinating them. A script needs an LLM, storyboards need diffusion, scenes need video generation, dialogue needs TTS. Cinerama wires these into a DAG workflow: feed it a novel script, and autonomous agents plan episodes, generate keyframes, compose video, and mix neural audio — outputting rendered episodes with cross-episode character and style consistency. The workflow engine IS the product.
What's built
- Full AIGC pipeline — novel script to exported video episode via LLM + diffusion + video + TTS
- Cross-episode character consistency — characters persist across episodes with appearance tracking
- Style lock — visual style enforced per series for continuity
- DAG workflow engine — checkpoint/resume, conditional routing, saga compensation
- 17 media adaptors via Registry — swap image/video/TTS providers without code changes
- All generation delegated to Muralla — single gateway, zero provider SDKs in the app
What's next
- Self-hosted inference — openweight engines for video, audio, and diffusion
- Marketplace for agent workflows and templates
- Cloud rendering with usage-based billing
- White-label licensing for production studios
- API access for third-party integrations
22 in-house QuadKit packages
Piccolina · brand
Codename: Piccolina
AI Pet Wellness
Pet owners Google symptoms at 2am and get conflicting advice from blogs, forums, and AI hallucinations. The real problem is information asymmetry — they don't know what they don't know. Piccolina closes that gap: describe symptoms or snap a photo, get a RAG-backed analysis from a curated veterinary knowledge base with urgency scoring, care plans, and breed-specific warnings — in 30 seconds, not 3 days.
What's built
- 6-stage AI analysis pipeline — intake, parallel RAG retrieval, temporal health context, LLM analysis, enrichment
- Multi-query RAG — symptoms + breed predispositions + urgency + patient history, deduplicated and scored
- PostGIS vet discovery — 673+ Philippine clinics sorted by distance and emergency capability
- Community feed — location-aware posts with AI wellness summaries, rescue alerts, smart matching
- Temporal health context — longitudinal pet health tracking with activity logs, milestones, wellness scores
What's next
- Freemium — basic analysis free, premium per pet/month
- Vet clinic SaaS dashboard — subscription per clinic
- Insurance partner integrations — referral fees
- Telehealth consultations — per-visit billing
- Wearable device partnerships — revenue share
- More country mapping — expanding beyond Philippines
40+ in-house QuadKit packages
...and more projects being tested.
Lab notes
Writing from the studio
How the framework is built, how agents read it, and what is stable in 0.0.x — in the open.
THE VISION
The full AI friendly web stack
Open-core QuadKit framework, in-house packages. Running in production on our own products.
Let's build something together. Get in touch.