Skip to content
View yonatangross's full-sized avatar

Highlights

  • Pro

Block or report yonatangross

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
yonatangross/README.md
yonyon.ai: one engineer, an army of AI agents



One engineer. An army of AI agents.

I build AI systems that run businesses: agents, automations, knowledge bases, custom AI apps.
Founder of yonyon.ai · creator of OrchestKit.

yonyon.ai LinkedIn X Email hi@yonyon.ai Book a 15-min intro


yonyon.ai is a one-engineer AI studio in Tel Aviv. I design, ship and run the whole system myself, with an army of AI agents doing the work around the clock: multi-agent backends, RAG, infrastructure, CI and full-stack product. Every change is reviewed before it ships.

OrchestKit: the AI dev toolkit for Claude Code

Stars Version 106 skills 36 agents 171 hooks


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.

Claude Code

/plugin marketplace add yonatangross/orchestkit
/plugin install ork

Cursor: Settings → marketplaces → yonatangross/orchestkit → enable ork → new chat.

Starter 12 (skills.sh, any agent), not the whole catalog:

npx skills add yonatangross/orchestkit -s doctor -s setup -s explore -s implement -s verify -s review-pr -s commit -s expect -s assess -s brainstorm -s create-pr -s remember

The implement skill is implement, not ork-implement.

Coverage 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.

Repo · Docs · vs Superpowers


What I build

Multi-agent AI platforms

Production LangGraph systems: supervisor/worker patterns, RAG over pgvector, real-time WebSocket streaming, and LLM pool failover across providers.

LangGraph pgvector FastAPI

AI operations infrastructure

End-to-end platforms with custom MCP servers, WhatsApp + comms integration, AI command centers, automated content pipelines, and LLM evaluation harnesses.

MCP Claude SDK Langfuse

Full-stack product

React 19 + Next.js front ends on FastAPI / Node back ends. Clean architecture, optimistic updates, TanStack Query, typed end to end with Zod.

React 19 Next.js TypeScript

Infrastructure & DevOps

Terraform-managed infra across Hetzner, Cloudflare, and Vercel. Docker deploys, GitHub Actions CI/CD, and Cloudflare Tunnels for secure ingress.

Terraform Docker Cloudflare


Stack

Python TypeScript C# .NET
FastAPI LangGraph Claude SDK MCP pgvector
React 19 Next.js Docker Terraform Cloudflare Redis

Want an army of AI agents working for your business? → Book a 15-min intro

Pinned Loading

  1. orchestkit orchestkit Public

    The Complete AI Development Toolkit for Claude Code. 106 skills, 36 agents, 171 hooks. Install `ork` for stable (v9.x), or `ork-alpha` for the v10 line, which ships daily.

    TypeScript 286 35