Give AI a place.
Vancetope gives AI a place — and with it, an application: a workspace of documents, sheets, canvas and boards where the AI sits with your data and doesn’t chat on the side, it does the work. The thing you open first in the morning, for work and for life, kept apart.
Or run it on your own machine in a couple of minutes — self-host →
Why it exists
AI had no application.
Someone once told me AI chats have no application — you open ChatGPT and there’s just a text box; what are you supposed to do with it? It stuck with me. Vancetope is my answer: give AI a place — somewhere it lives, right next to your data — and with a place it finally has an application, something real to do.
Real surfaces
Real apps — AI-made and connected.
Not a chat window, but the tools you actually work in — all AI-native: have them created, filled, reshaped and linked. Because everything is a document, it all hangs together, and it’s shared live — people and agents at once.
Sheet
Spreadsheets with functions — pipe the results onward.
Canvas
Think spatially: nodes, links and groups on an open plane.
Workbook
Notes and pages in a block editor.
Kanban & Issues
Plan work and track it through.
Finance
Structure money decisions.
Cortex
Chat, document and execute on one surface.
…and more kinds — mindmap, calendar, slides, diagrams, checklists.
See it in action
What people get done with it.
Real walk-throughs — one request grows into research, charts, documents and decks. Each is a slideshow you can follow step by step.
Research a topic, end to end
Deep-research with Marvin, reshape it into a mindmap, illustrate it, compile a document — and export a PDF. All in one conversation.
Size up a stock with live data
Pull a stock's prices off the web, chart them as candlesticks, and get an assessment that cites the numbers it stands on.
Stress-test an idea with a panel
Stand up a reusable council of AI personas, throw a pitch at it, and get one synthesised verdict — the disagreement kept intact.
What makes it tick
A few ideas do most of the work.
Everything else is a consequence of these.
Everything is a document
Recipes, prompts, schedulers, hooks, manuals, settings — all stored in MongoDB. A new automation is a new document. The system reshapes itself from its own data, and so can agents.
Agents drive (almost) everything
Nearly every capability is a tool: write documents, spawn processes, set triggers, research, delegate. You give the direction and step in whenever you want — the flow stays visible.
Projects draw the boundaries
A project is a bounded area with its own documents, config and agents. Different setups live side by side. Memory and permissions inherit down a scope cascade.
Built to work in, together
Cortex unites chat, documents and execute on one surface — live-edited with other people and with agents in the same session. Presence, merge and versioning included.
Memory that carries over
Work doesn’t vanish when a session ends — it compacts into summaries and stays retrievable. Scope-aware recall (RAG) walks the cascade, so a process draws on what its project and tenant already know.
It runs itself
Schedulers, lifecycle hooks and webhooks fire recipes, scripts or workflows. Agents act on a timer or an event — not only when you’re there to chat.
Work and life
One place for whatever you’re working on.
Work or personal — Vancetope holds both, kept apart in separate tenants. A five-minute question or a project that runs for weeks; something off the web, a document to reshape, files right there on your machine. It’s open-ended on purpose: the stuff you’d otherwise scatter across a dozen apps tends to just fit here.
Project kits
Start a project ready to work.
A kit is a git bundle of skills, recipes, tools and settings. Install one and a project arrives preconfigured — thinking patterns, worker recipes, tool packs, defaults. And kits inherit, so they compose:
The interesting part isn’t the bundled ones — it’s that a kit is just a git repo. Point a project at yours and it’s productive from the first message.
Under the hood
A handful of engines, many recipes.
An approachable surface, but no power lost underneath. The work is run by engines — Java algorithms with a lifecycle, where code drives the flow, not the LLM (a recipe picks which one). And Vancetope keeps the raw power too: a CLI agent that works on your own machine, MCP in both directions — it speaks it and serves it — and real integrations.
One brain, many ways in
Meet it where you work.
The Brain is the single source of truth. Clients are different entry points into the same project — not views on the same thing.
Terminal
Work right at the command line, with local tools (shell, files, git) — but always inside a project, with everything stored in it.
Web
The working environment in the browser: chat, live documents in many kinds, and apps built on top of them.
Mobile
On the go — a wrapper around the deployed Web UI, with an isolated WebView per account.
The proof is the product
Written by agents. On purpose.
Every line of Vancetope is AI-written — directed, reviewed and shaped by one human. That’s not a confession, it’s the whole point: Vancetope is what working with agents over months actually builds — a large, coherent system you can run, read and change. The tool and the demo are the same thing.
Honest bit
It’s a personal project.
I built Vancetope to develop LLM agents and shape them until I could actually work productively with them. Over time everything I found interesting went in — plus a few things I think others might get something out of.
No support contract and no roadmap promises — it’s a project, not a product. The source is public: read it, run it, take it for a spin. It’s source-available rather than classic open source, and where it goes from here I’m keeping open.
— Mike Hummel