The platform is a full-stack AI product: a Django/DRF backend hosting eleven domain apps (multi-LLM via OpenRouter, coding assistant, sandboxed code execution, pgvector RAG, MCP connectors, AI voice rooms, Stripe billing, GDPR/rate-limiting hardening) paired with a React 19 + TypeScript frontend. The entire codebase was driven by an autonomous Claude Code task-runner that enforced per-task quality gates, gate-repair loops, and structured failure records, making the development process itself a case study in agentic software engineering.
Multi-Model AI Platform
11 domain apps
React 19 + TypeScript frontend
01What it is
A production-grade, multi-model AI chat and agent platform with sandboxed code execution, a RAG knowledge base, MCP integrations, and Stripe billing, built autonomously by a homegrown Claude Code orchestrator.
02Engineering
03 Architecture
Frontend
React 19TypeScript
Backend
Django/DRF
Domain apps
OpenRouter multi-LLMcoding assistantsandboxed code executionMCP connectorsAI voice rooms
RAG and billing
pgvector RAGStripe billingGDPR / rate-limiting hardening
Agentic build process
Claude Code task-runnerper-task quality gatesgate-repair loopsstructured failure records
04 Highlights
- Django/DRF backend hosting eleven domain apps, from multi-LLM via OpenRouter to Stripe billing
- React 19 + TypeScript frontend paired with the backend for a full-stack AI product
- pgvector RAG, sandboxed code execution, MCP connectors, and AI voice rooms among the domain apps
- Entire codebase driven by an autonomous Claude Code task-runner with per-task quality gates and gate-repair loops
05Stack
PythonDjangoReactOpenRouterpgvectorKubernetesCloudflare
06Status
pre-launch