Skip to content
Andrew Van DykeAndrew Van Dyke
Live demo

2026 · Design, architecture & implementation

Agent World — Emberwick

Three agent frameworks orchestrated from one Basilisp Polylith monorepo, behind a hard fail-before-spend cost cap — shipped as a zero-backend static replay anyone can watch.

  • LangGraph
  • AutoGen
  • CrewAI
  • Basilisp
  • Polylith
  • OpenRouter
  • FastAPI
  • Canvas
Live demo Source

Problem

"Multi-agent" demos usually mean one framework doing framework tourism — and an API bill nobody watched. I wanted a system that uses LangGraph, AutoGen, and CrewAI together, each doing the one job it's actually shaped for, with LLM spend capped before the call is made, and an artifact a hiring client can open in a browser with zero backend.

What I built

Emberwick: six LLM-powered villagers live in a 2D pixel town. Each framework owns the seam it was designed for:

  • LangGraph runs per-agent cognition — every decision is a compiled StateGraph (perceive → decide → conditional route → set-target / idle), with the LLM node swappable so the whole graph tests offline.
  • AutoGen handles proximity conversations — when two villagers meet, a RoundRobinGroupChat of two persona-primed agents talks (≤ 6 messages, 80 max tokens each).
  • CrewAI writes the Town Chronicle — every two sim-minutes a chronicler → editor crew rewrites the running narrative from the raw event log.

All of it is orchestrated from a Basilisp (Clojure-on-Python) Polylith monorepo: nine single-purpose components (world, persona, memory, cognition, conversation, chronicle, inference, engine, recorder) and two bases — a FastAPI server with a live WebSocket viewer, and a headless CLI that renders sanitized replay JSONL. One shared inference component fronts OpenRouter with a reserve → call → settle cost guard that fails before it spends.

Outcome

The live demo is a fully static replay — the plain-canvas viewer plus a recorded JSONL file on Vercel, no backend, no keys, no cold starts. The same renderer drives live WebSocket mode and replay mode, and the cost cap held for the entire recorded run. It's the flagship proof that I can make three agent frameworks cooperate instead of collide.