Researcher
Reads the web and brings sources back to the conversation.
Tofi is a self-hosted workspace for persistent AI Bots. Each Bot keeps its memory, schedules and tool connections on a server you own. Give an account its own sandboxed computer. Use the model you choose, including one that runs on your own hardware.
curl -fsSL https://raw.githubusercontent.com/JackZhao98/tofibot/main/install.sh | sudo bash
Ubuntu 22.04/24.04 · Debian 12/13 · x86_64 and aarch64 · Apache-2.0 server
Early beta: updates ship often, sometimes several a week. tofi update backs up first and rolls back if a new version fails.
Hand a task to the crew. A Bot takes over, works it through to the end and hands back the result.
Bots can reach what is on your network: Home Assistant, your NAS, internal tools and local model servers. Nothing is sent to Tofi unless you opt in to the anonymous install report. Model requests go only to the provider you configured.
tofi backup and tofi restore.One microVM per account, with Chrome, a desktop and a terminal. Watch the live view while a Bot works. Open the work trace afterwards. Accounts cannot see each other's computers.
In a group chat the Bot you asked becomes the lead. It assigns parts to the Bots whose roles fit, shows one plan card with each part and its owner, and answers when the parts are done.
Results land right in the conversation, files included. If a message fails to send, you can retry it.
Read all three. Two moved to per-seat pricing this quarter; one dropped its free tier.
RECORDED ON A LIVE INSTALL
No mock-ups: three short clips from a real TOFI server, sped up.

A question in plain words. The answer comes back with its sources.

The Bot opens Hacker News in its own browser. The live view sits in the corner.

In a group, one Bot picks a dashboard and the other writes the install checklist as a file.
Give each Bot a silhouette, a coat, its own tools and memory. They breathe, blink and glance around while they work.
Reads the web and brings sources back to the conversation.
Tails your logs at 3 a.m. and only wakes you when it matters.
Turns scattered notes into a first draft in your voice.
Files, tags and remembers everything you hand it.
Opens the terminal, runs the tests, sends you the diff.
Pick a silhouette, a coat and a job. Plug in MCP tools and Skills.
IN THE APP
Small parts of the Web app that save a step.
Before a severe action you did not ask for, the Bot shows an approval card. It stays at the bottom of the chat. Send a new message and it cancels.
Press ⌘K or Ctrl+K, or the magnifier. Search covers chat titles and message text.
Pin conversations to a dock at the top of the sidebar. The rest sort by their latest message.
The usage panel splits the context by part and shows the cache hit rate and an equivalent cost estimate.
Add MCP servers and Skills, sign in to services with OAuth (Google, Notion and others), and let Bots search and fetch the web from the server.
An admin updates from Settings. Tofi waits for running Bots, backs up first and rolls back if the new version fails.
A new Bot opens on an empty chat with three templates to start from. Pick one, or just type.


The Web app works in a phone browser. Ask a Bot from anywhere and read the answer, sources included.
An optional Bot computer for each account (today a built-in virtual machine), with a desktop, Chrome and a terminal. The Bots in that account share it. Watch them work live, or take the wheel yourself.
Needs KVM on the host. Add it later with sudo tofi computer add kvm.

INSTALL
Tofi runs on a Linux server you control. The Bot computer is optional: a host without KVM gets the server and the web app, and you can add a Bot computer later.
$ curl -fsSL https://raw.githubusercontent.com/JackZhao98/tofibot/main/install.sh | sudo bashOr: Docker Compose (no Bot computer, no KVM).
On your Linux server. It installs Docker if needed, pulls pinned images and starts Tofi.
The installer prints the web addresses and a one-time setup key. Enter the key to create the first admin.
Sign in with ChatGPT, add an OpenAI or Claude API key, or connect Ollama or another OpenAI-compatible server.
TOFI is free to self-host. The server is Apache-2.0. The web app is PolyForm Shield: use it, change it and run it for yourself, but do not sell a competing product built from it.
The server is Apache-2.0. The web app is PolyForm Shield. You pay your own model provider.