Cloud — your own private cell Self-hosted AI workspace
Open Fork
Yours for the voyage.

The AI workspace you own.

Chat and agents, a vibe-coding studio, parallel job orchestration, deep research, local model serving, email, documents. One workspace you own — in your own private cell in our cloud, on your desktop, or on your servers. Your models, your hardware, your data.

$ download for Windows →
The workspace

Started as an AI chat. Became a workspace.

Open Fork puts an entire AI-native toolkit behind one sign-in. Every part shares the same models, memory, tools, and crew — and every part runs where you decide.

open fork · gallery
The Open Fork gallery app showing a grid of generated images inside the dark workspace UI The Open Fork gallery app on a phone-sized screen

open fork · gallery — one of fifteen built-in apps

Flagship

Six reasons it replaces a browser full of tabs.

01 · Chat + agent loop

A chat that does the work.

Streaming responses, slash commands, and tool calls you can watch happen. The agent loop plans, executes, and reports back — it answers questions, and it also finishes tasks.

chat
02 · Crew

Hire a crew, not a chatbot.

Create named crew members, each with their own persona, provider, and toolset. Put them to work in chat, inside the Builder, on scheduled tasks — even over WhatsApp.

crew/
03 · Builder

Describe the app. Watch it ship.

A vibe-coding studio: say what you want and the agent scaffolds it, iterates with you, and renders a live preview beside a real terminal. Publish to an isolated hostname in one click — and roll back just as fast.

builder
04 · Loom

Five jobs in parallel. Zero surprise merges.

A conversational orchestrator that fans work out to parallel agents — each in its own isolated git worktree with a live terminal and a hard budget cap. Every merge is held for your approval. Always.

loom
05 · Deep Research

Hours of reading, returned as a report.

Kick off a multi-step research run and keep working. Open Fork gathers sources in the background, reads them, and delivers a cited, visual report — not a wall of links.

research
06 · Cookbook

The right model for the hardware you have.

Cookbook scans your machine and recommends models that actually fit your VRAM — from a catalogue of 270+ — then serves them in one click with vLLM or llama.cpp. On this box, or on a remote GPU over SSH.

cookbook
The full deck

One sign-in. Fifteen apps.

Everything below ships in the box — no add-ons, no marketplace tiers.

Documents

Living documents you write with the model — then hit Run to preview sandboxed HTML apps and games inline.

Compare

One prompt, several models, blind voting. Let the answers compete before you commit.

Brains, Memory & Skills

Private knowledge containers for RAG, persistent memory across conversations, and skills the assistant writes for itself.

Email

Your real inbox over IMAP/SMTP, with AI triage and drafts in your voice.

Scheduled tasks & notes

Recurring agent runs, reminders, and notes that file themselves.

Tools & MCP

Built-in tools plus any MCP server you connect. Toggle each one, per chat.

Gallery & image editor

Generate images, then finish them in a full editor — no round-trips.

Video

Generate video, then let AI edit it: transcribe, cut, subtitle.

Calendar & contacts

CalDAV and CardDAV, beside your email, visible to your agents.

Make it yours.

Themes, density, layout — the workspace bends to you, not the reverse. This page is wearing the default One-Dark theme; it isn't the only one.

Run it anywhere

Three ways to run. The same workspace.

Cloud · admin-provisioned

A private cell at ofork.dev.

  • Single-tenant: your own container and row-level-secured database
  • Isolated at cell-yourname.ofork.dev
  • No public signup — accounts are provisioned for you
Desktop

Windows, from a ZIP.

  • Portable ZIP — unzip and run, no installer
  • Postgres bundled, WebView2 shell
  • Everything stays on your machine

macOS and Linux run via self-host today — instructions on the download page.

Self-host

Docker or bare metal.

  • Docker Compose or native install
  • GPU overlays for NVIDIA; Metal on Apple Silicon
  • Your box, your rules, your data
Every model, one roof

Frontier APIs, local weights, or both.

Connect OpenAI, Anthropic, xAI Grok, and Z.ai through a credential-isolating broker — your keys stay inside the boundary you run. Route to OpenRouter or Groq directly. Or skip APIs entirely and serve vLLM, llama.cpp, or Ollama on your own silicon. Mix and match per chat, per crew member, per task.

Honest billing

Prepaid credits. Nothing else.

no subscriptions
You top up a credit balance when you choose. There is no plan to forget and no renewal to catch you.
no card on file
We don't store a payment method. During early access, top-ups are handled directly by your operator.
local is free
Models served on your own hardware are never metered. What runs on your silicon is yours, full stop.

Yours for the voyage.

Sign in if you have a cell. Ask us for one if you don't. Or take the desktop build and run it tonight.

$ download for Windows →