Features

Everything branches. Everything is measured.

Thirteen little scenes, one product: AI work on an infinite canvas that forks instead of piling up — with agents, research fan-outs and a live meter on what every branch costs.

01 · Branching

Every turn drags the whole chat

Left: each new message re-sends every earlier one, so the pile — and the bill — keeps growing. Right: a branch sends only its own short path.

A branch only re-sends its own path — up to ~90% less context re-sent (your dashboard measures the real number).

02 · Context quality

Long threads lose the thread

Left: as the pile grows, older turns fade out of reach and the answer goes dim — while the token bar fills. Right: two messages of clean context, a bright answer, a tenth of the tokens.

Short, clean context = better answers AND fewer tokens.

03 · Orchestration

One goal, workers in parallel

A Project Manager agent breaks the wish into jobs, runs them at once, and assembles the result.

Describe the goal — a Project Manager agent plans, spawns workers in parallel, and assembles the result.

04 · Create app

One sentence to a running app

Plan, build, launch, preview — every stage stays a node you can open and change.

From one sentence to a running app — plan, build, launch, preview, all on the canvas.

05 · Research mode

Five models, one report

Ask once. Answers come back side by side and merge into a single cited document.

Ask once — five models research side by side and merge into one cited PDF report.

06 · Import

Your old chats, untangled

Bring a history export in; it comes out as a tree you can navigate and fork from.

Bring your ChatGPT / Claude history — one import turns the scroll into an organized branch tree.

07 · Model per node

Every node, its own model

Switch on one node without touching the rest of the tree.

Every node can run a different model — pick per task, not per conversation.

08 · Routing

Right model, right step

Auto-pick sends each task where it belongs — and only pays big where big is needed.

Auto-pick routes each task to the right model — big brains for hard steps, cheap ones for easy steps.

09 · Enhance

Rough ask, precise prompt

Enhance rewrites what you typed into role, goal and constraints before it hits the model.

One click rewrites your rough ask into a precise prompt — role, goal, constraints — before it ever hits the model.

10 · Design studio

Design it, then ship the code

Real responsive HTML on the canvas — not a picture of a layout.

Design real, responsive HTML on the canvas — export working code, not a picture.

11 · Memory

What it learns, it keeps

A knowledge graph and an Obsidian vault on your own disk — recalled when it helps.

What your agents learn is kept — as a knowledge graph and an Obsidian vault on your own disk — and recalled when it helps.

12 · Providers

Any provider, your keys

Cloud, local, or anything OpenAI-compatible. Keys stay on your machine.

Bring any provider — cloud keys, local models, or any OpenAI-compatible endpoint. Your keys never leave your machine.

13 · Why branching

Built on published findings

Long single threads drift. Short branches are the documented fix.

The design follows published findings on multi-turn drift — branching is the fix, not a gimmick.

See it with your own work.

The browser playground needs no key and no signup. The desktop app is free and runs everything above.

Try in your browser ⬇ Download for desktop ▶ Watch the tutorials