JarvisTown
Autonomous AI Developer Colony Simulation
A Rust-based simulation where AI agents with distinct roles autonomously collaborate on software development. Built with Bevy game engine and Dioxus desktop UI.
// the problem
Challenge
Creating autonomous AI agents that collaborate meaningfully without scripted workflows is an open research problem. The simulation must give each agent distinct perception, reasoning, and action capabilities while allowing emergent collaboration. Single-binary deployment with no external services requires careful architecture.
// what we built
Solution
JarvisTown uses Bevy ECS for entity-component-system architecture where agents are entities with AI "brains". Each agent has perception (what is happening), reasoning (LLM calls with role context), and action capabilities. Agents live in a 2D office environment and collaborate organically when they notice tasks relevant to their role.
// shipped
Key features
- Multiple AI agents with distinct specializations
- Role-based personalities and reasoning
- 2D office environment simulation
- Task board with emergent workflow
- Artifact generation (code, tests, docs)
- Single binary deployment
- Pathfinding and movement
- Memory of recent events
// stack.json
Tech stack
The exact tools shipping this product in production.
- Rust
- Bevy
- Dioxus
- AI/ML
- Tokio
// system.diagram()
Architecture
AI colony simulation with autonomous agents collaborating on software development
- frontend
- backend
- ai
- service
- external
- database
// receipts
Results
- Single Rust binary - no external services
- 5 distinct AI agents with unique personalities
- Emergent collaboration without scripted workflows
- Bevy ECS game engine integration
- Dioxus desktop UI shell
- Leading AI model integration
// next()
Have a project like this?
We build production systems with the same engineering rigor you see here. Let's talk.