_Update, 2026-10-23: the public sample projects in the Free plan are planned._
Emolysis will have a Free plan, and it will be bring your own key. You will create a key with the AI model provider you choose, add it to Emolysis, and the agent will use it. The provider will bill you for what you use. Emolysis will charge nothing. This post explains why we chose that model and what it means for your data.
Why a free plan built on your own key
A coding agent needs a model, and models cost money per request. On the Free plan, you will pay your provider for that directly, with your own key. Pro, Max and Team will include model usage, Enterprise will meter it, and every plan will still accept your key. The engine, the local loop, the templates and the tests are what Emolysis will add. The model is something you may already pay for, under an agreement your company has already reviewed.
So the Free plan is designed to include the local engine, DuckDB with a local lakehouse per project, one platform connection, the core templates, the MCP server for editors and coding agents, and the public sample projects. You bring the key.
Why we do not name providers
You will not find model provider names on this site. That is deliberate. The choice is yours, and it often depends on things we cannot see from here: your company's agreements, its data terms and where its approved accounts are. Emolysis is designed to work with several providers, and we would rather not steer that choice.
What the provider sees
Whatever provider you choose will receive the agent's prompts and return its responses. To write correct code, a prompt can include table and column names, schemas, the template being filled and sample values from your data. With your own key, those requests will go to the provider under your key and its terms. Read them; they govern what happens to your prompts there. See what the model provider sees.
Your key will be kept in your machine's credential store, never in a project file. You will be able to replace or remove it at any time.
What the paid plans will add
Some people do not want to manage a key. Pro, Max and Team will include model usage, so you will not need one. Past a limit, usage credits will keep the agent working at standard metered rates, until you turn them off or reach a spend limit you set. Enterprise will have no included allowance: model usage will be billed at standard metered rates from the first request, within spend limits that admins set, unless the organization uses its own model key. With a paid plan's included usage or usage credits (on Enterprise, metered usage), prompts and responses will pass through Emolysis's metering service on the way to the model provider. That service is designed not to store or log their content; it will record token counts for billing.
The planned paid plans are Pro, Max, Team and Enterprise. Every plan will accept your own key too, and requests made with it will not count against your plan's limits. Beyond model usage, the paid plans will add what a key cannot: every platform connection, the full template library with updates, web dashboards and sharing, the GitHub App and pull request checks, and for teams, a shared catalog, an organization workspace, audit export and single sign-on. The pricing page describes each plan, and the docs explain model keys and credits.
The trade-off
Bring your own key will give you control and cost us nothing to serve, which is why it can be free. It also means you will manage the key, its spending limits and its rotation. Included usage and credits will trade that work for one bill. Both are meant to be first-class ways to use Emolysis.
Nothing can be bought or downloaded yet. When plans open, we will announce it here.
Emolysis is in private development. Nothing described here is released yet.