Do you offer API access?

In private beta. The Universal Key proxies Anthropic, OpenAI, Google AI, and OpenRouter through a single OpenAI-compatible endpoint, billed against your braincell credits. Ask on Discord for beta access while self-serve keys are being finished.

Can I self-host braincell?

No - braincell is a hosted service. The apps you build with it are a different story: export any project as a complete working codebase and host it on your own infrastructure, no braincell dependency.

Which models can I use?

Claude Opus 4.7 (deep reasoning), Claude Sonnet 4.6 (balanced), Claude Haiku 4.5 (fast tool-calls), GPT-5, Gemini 2.5, Grok 4, DeepSeek, Llama, and more via OpenRouter. Model access depends on plan; you pick the model per project.

Where do I get support?

Everyone gets community support on Discord, where the founder is active daily. Pro plans get priority - your questions jump the queue.

Build, verify, ship. Documented.

Reference for the braincell platform. The agent loop, the sandbox contract, snapshots, Universal Key, project export, and the surface area we expose for power users.

braincell/Docs · Sandboxes

v2.4

Quickstart

Agent loop

Sandboxes

Universal Key

API reference

Boot a fresh microVM

const sandbox = await

braincell.sandbox.create(

{ project: 'pomodoro', persist: true });

Quickstart

From signup to a deployed URL in under 10 minutes. The shortest path through the agent loop.

Start the walkthrough

The agent loop

Five phases the agent owns end to end: describe, design, build, verify, deploy. Read what each one does.

Read the loop

Universal Key

One key, every frontier model. Drop-in compatible with the OpenAI SDK, billed against your braincell credits.

Wire it in

Models

Opus 4.7, Sonnet 4.6, Haiku 4.5, plus GPT-5 and OpenRouter fallbacks. How to pick the right one per turn.

Compare models

By role

Find the page that matches your job.

The agent loop looks different depending on what you ship. Pick your seat at the table.

Product managers

Ship a prototype before the spec doc. Validate ideas with real users on Friday.

PRD to URL in 60 minutes
Share with users in one click
Snapshots as A/B history

Designers

Push your taste straight to production. No handoff to engineering, no half-built mockups.

Engineers

Skip the boilerplate phase. Clone the project locally when you need to take over.

Real Next.js output
Full project export (zip)
Run it locally, no lock-in

Founders

Stop paying for SaaS you barely use. Replace a stack of subscriptions with one tool you own.

The agent loop

Every braincell turn runs five phases: describe, design, build, verify, deploy. The agent owns each phase. You only step in to confirm the result. Five strikes per turn means typecheck, lint, and a real build all pass before any change reaches you.

braincell/Agent · Turn 14

Running

✓Describeprompt parsed

✓Designschema + routes

✓Buildcode generated

4Verifytypecheck + lint

5Deployvercel · prod

Universal Key (private beta)

One key proxies to Anthropic, OpenAI, Google AI, and OpenRouter. Billed against your braincell credits, no separate provider accounts required. Drop-in compatible with the OpenAI SDK, so the migration is a one-line base-URL swap. The endpoint is live; self-serve key creation is in private beta - ask on Discord for access.

braincell/Universal Key

OpenAI compatible

Your key

bc_live_8aJk··········42pQCopy

// drop-in for the OpenAI SDK

const client = new OpenAI({

baseURL: "https://braincell.sh/v1",

apiKey: process.env.BRAINCELL_KEY,

});

Anthropic

OpenAI

Google

OpenRouter

Snapshots and rollback

The agent captures the full project state on every assistant turn. Rewind any decision with a single click. Snapshots are diffable, named, and free on every paid plan. Use them as A/B variants, undo a regression, or fork a working app into two directions.

braincell/Audit log

Streaming

mira@Enabled SSO · SAML2m ago

systemAudit log → S3 export ran14m ago

agentDeployed booking-app to prod1h ago

priya@Added seat · ops team3h ago

Runtime

Sandboxes

braincell does not render previews in a browser stub. Every project boots its own isolated container on a dedicated sandbox host. Your install script runs, your env vars resolve, your routes hit real Node. If something fails in production, it fails in the sandbox first.

Models

Supported models

· Claude Opus 4.7: default, deep multi-step reasoning
· Claude Sonnet 4.6: balanced quality and cost
· Claude Haiku 4.5: fast tool-calls, low credits
· GPT-5 and OpenRouter fallbacks for niche tasks

Tooling

Take it local

Every project exports as a complete working zip: `pnpm install`, `pnpm dev`, and you're running the exact same app on your own machine. No braincell dependency in the exported code. A CLI for two-way sync is on the roadmap.

Common questions.

Reach out at support@braincell.sh for anything beyond this list.

Nothing to install. braincell runs in the browser as a hosted workspace at braincell.sh. Your projects themselves are never stuck there - export the full codebase any time and run it wherever you like.

Stop reading. Start shipping.

The fastest way to learn braincell is to ship one app. Ten credits, no credit card.

Build something Open tutorials

10 free credits on signup. No credit card.