Lite is free during beta.
Lite is $0 during beta through 31 December 2026 UTC, with $10/month planned afterward. Pro is planned at $20/month and is not available for purchase. AI usage stays on your own provider bill.
The beta may be extended. We will give at least 30 days' notice before free beta access ends. A paid plan requires your explicit choice: no automatic charges. Your work and data remain yours.
Beta enrollment is open. Sign in to check your eligibility and current access.
No AI credits are included · use your own keys or subscriptions · your provider bills model usage
Teams is a future direction
A future team plan is under consideration. Shared administration and collaboration are not available. Organization accounts, shared authorization, SSO and SCIM are not implemented.
Questions people actually ask
What is the difference between Lite and Pro?
Lite is $0 during beta through 31 December 2026 UTC, with $10/month planned afterward. Pro is planned at $20/month and is not available for purchase. Lite includes one open folder, two concurrent logical tasks and one identity per harness, plus basic roles and raw data export. Pro purchasing is unavailable; planned benefits focus on more capacity, reusable workflows and extended analysis. Beta enrollment is open. Sign in to check your eligibility and current access.
What do you charge for model usage?
Nothing. Auton does not include AI credits or resell model tokens. You connect your own keys or subscriptions, and your AI provider bills that usage separately from Auton.
What happens when the beta ends?
The beta may be extended. We will give at least 30 days' notice before free beta access ends. A paid plan requires your explicit choice: no automatic charges. Your work and data remain yours.
Does anything leave my machine?
Auton keeps code, diffs and local journals on your machine except the prompts and context you choose to send to your AI provider. Auton's account service handles identity, sessions and beta access. Payments are disabled. Optional reporting and its controls are described in the privacy information.
Can I use my own agent?
The integrated launchers are Claude Code, Codex CLI, pi and Antigravity. Other CLIs appear in the cookbook or can run through a shell; model discovery, accounts, MCP, skills and usage support vary by harness.
Are containers, remote runners and hard spending caps available?
No. This preview runs in local folders and Git worktrees. Container and remote targets are unsupported and fall back to the folder; they do not provide isolation. Hard spending stops across harnesses are unproven. Usage observations are not an invoice or an enforced spending cap.
Can I route a custom provider through Auton?
The planned Pro gateway supports specific routes, aliases and fallback. Adding a custom endpoint in Accounts records its details; it does not automatically route that provider. Native provider setup remains separate.