I built a tiny AI company that runs on my laptop (multi-agent application)
Source: Dev.to
Introduction
Lately I’ve been thinking about what “work” might look like in a world of AI agents. I was talking with my wife about it — maybe in the future, instead of replacing people one by one, it becomes one person managing a small team of AI workers. Tools like Claude Code or OpenClaw felt way too technical for her, so I started wondering: what if this actually felt like working with a team? Not writing code, not wiring workflows, but hiring, managing, and collaborating.
Holons
I built Holons, a desktop‑first system (Tauri + Flask + React) where:
- agents have roles and identities
- a “lead” agent assigns tasks and builds workflows
- multiple agents can collaborate in group chats
- everything runs locally (or self‑hosted)
You can say something like:
“Create a pitch for a B2B AI accountant”
and Holons will:
- propose a workflow
- assign tasks to different agents
- estimate cost
- let you run the whole thing
What surprised me
Visibility
The hardest part wasn’t the agents; it was visibility. Once multiple agents are running, you need to understand:
- what they’re doing
- how much they cost
- how they behave over time
Unified ledger
I made an early design decision: every LLM call writes to a unified ledger. Each call tracks:
- model + provider
- tokens (prompt / completion)
- cost
- latency
- agent + user
That single table powers:
- cost dashboards
- usage quotas
- reports
- audit logs
Key features
- Multi‑provider support: Bedrock, OpenAI, Anthropic, Gemini, MiniMax
- Per‑agent model binding (different agents can use different models)
- pgvector‑based RAG + external knowledge integrations
- MCP‑style tool integration
- IM channels (Telegram / Slack / LINE)
Still early
This is very much an experiment. I’m not sure yet if this is the “right” abstraction for multi‑agent systems—more like managing a team, less like calling an API.
- GitHub: https://github.com/jhk482001/Holons
- Demo: https://x.com/HolonsAgent/status/2048772512394432749?s=20
I’m curious how others are thinking about multi‑agent systems. Are people actually using them in real workflows, or are we still figuring out the right model?