Most AI “apps” these days aren’t really apps. They’re wrappers.
A thin UI. A subscription. A cloud call. A monthly fee. And your data quietly piped off to a server farm you’ll never see.
I didn’t want to build another one of those. I didn’t want to use another one of those. So, I built something different.
I built Bob’s Bar — the first Collaborative Multi-Persona Sandbox (CMPS).
Let's be honest, every AI chat feels the same. You ask a question, it answers, repeat. Useful? Yes. Alive? No.
I kept thinking: “Why does every AI tool assume I want a one-on-one conversation? Why can’t multiple AIs talk to each other while I watch?” That question became the seed. I wanted a space where multiple personas could exist together, talk to me and each other, and run entirely on my own hardware.
I’m an indie dev. I don’t have a server farm, and I don’t want to pay AWS just to host my own brainstorming sessions. So the architecture is 100% local-first:
-Engine: Ollama (raw LLM inference)
-UI: Python + Gradio (Blocks API for stateful UI)
-Distribution: PyInstaller → standalone .exe
-Licensing: Lemon Squeezy API (so I could actually sell the damn thing)
No cloud. No subscriptions. No data scraping. Just your machine doing the work.
But getting four local models to talk to each other without hallucinating is absolute chaos.
At first, they spoke twice in a row. They impersonated each other. They put words in the user’s mouth. They derailed into movie scripts. Vane pitched a heist film, and Bob started giving stage directions like “I polish a glass and chuckle.”
I had to build what I now call The Bouncer — a regex-powered clean_reply() function that physically chops off AI responses the moment they write a script, impersonate another persona, use bullet points, or hijack the conversation. I also added a seen_in_banter set to prevent any persona from dominating the room.
Once the routing was locked down, the magic happened.
Because the AIs share a context window, emergent behaviour happens naturally. One night, a joke about a stone gargoyle turned into a 40-turn spy thriller about a tax-dodging landlord. It was chaotic, hilarious, and it felt alive. That became Pub Mode.
But I also needed it to be useful. So I added Work Mode — a toggle that injects a new rule into the system prompt. The banter drops instantly, and the four personas become a professional focus group. Pub Mode is chaos. Work Mode is clarity. Both matter.
Running locally via Ollama changed everything. Instant responses. Absolute privacy. No API limits. No cloud dependency. No tracking.
Local-first isn’t just a technical choice; it’s a philosophy. It’s about ownership. It’s about sovereignty. It’s about making AI feel like a tool you own, not a service you rent.
That’s why Bob’s Bar is £29 lifetime. No subscriptions, no cloud, no scraping. Just a .exe and your imagination. You can even save and swap Persona Sets — turn the pub into a sci-fi crew or a corporate boardroom in one click.
If you had a local-first sandbox with multiple personas that could talk to each other, what world would you build? What personas would you create? What chaos (or order) would you unleash? I’d genuinely love to hear it.
If you want to check it out, Bob's Bar is live on Product Hunt today and available as a £29 lifetime .exe.
👉 Product Hunt
🍺 Buy directly on Lemon Squeezy
🌐 Visit the website