Agents, RAG, infrastructure, full-stack — the work that used to need a team, run solo.
Building yonyon.ai in public · creator of OrchestKit.
I run a one-person AI software studio out of Tel Aviv. The pitch is simple: the systems a startup used to staff a team for — multi-agent backends, RAG, infra, CI, full-stack product — I design, ship, and operate solo, end to end. yonyon.ai is where I do it in public.
Stop explaining your stack. Start shipping. OrchestKit encodes production patterns — backend, frontend, AI/LLM, security, DevOps, testing, product — so Claude Code already knows your architecture before you type a word.
/plugin install orkCoverage spans backend (FastAPI, PostgreSQL, REST/GraphQL), AI/LLM (LangGraph, RAG, evals, prompt engineering), frontend (React 19, Next.js, TypeScript), workflows (PR review, implementation, brainstorming), testing, DevOps (CI/CD, Docker, Terraform), product, and security.
|
Production LangGraph systems — supervisor/worker patterns, RAG over pgvector, real-time WebSocket streaming, and LLM pool failover across providers.
|
End-to-end platforms with custom MCP servers, WhatsApp + comms integration, AI command centers, automated content pipelines, and LLM evaluation harnesses.
|
|
React 19 + Next.js front ends on FastAPI / Node back ends. Clean architecture, optimistic updates, TanStack Query, typed end to end with Zod.
|
Terraform-managed infra across Hetzner, Cloudflare, and Vercel. Docker deploys, GitHub Actions CI/CD, and Cloudflare Tunnels for secure ingress.
|
Need a system that runs itself? → yonyon.ai