AI providers and engines

Every owner brings their own AI. AutoRune never pays for inference, and there is no global or fallback key. You can connect several providers. One is active and drives all your avatars. Switching never deletes a key; only Disconnect removes one.

The options

Option	How you connect	Engine	Models
OpenRouter	Sign in with OpenRouter (OAuth with PKCE). OpenRouter creates a key labelled "AutoRune" that you can revoke there.	opencode	A curated list
Anthropic (API)	Paste an API key	opencode	A curated list
OpenAI	Paste an API key	opencode	A curated list
Google Gemini	Paste an API key	opencode	A curated list
Claude subscription (via Claude Code)	Sign in with your Claude Pro/Max account through Claude Code's own login	Claude Code	sonnet (default), opus, haiku

Pasted keys are checked with a cheap, free call to the provider before they are saved (for example, listing models). Validation is rate-limited per user.

Engines

An engine is the stock coding agent that plays the avatar. AutoRune talks to every engine through one small interface (start, prompt, stop; events for replies, thoughts, activity, provider failures and usage limits), so the rest of the system doesn't care which one runs.

opencode

opencode (pinned version, installed with an integrity check) runs as opencode serve inside the sandbox, with rs-sdk's own opencode.json plus the provider and model. The key reaches it only through the sandbox's environment. It is never written in a config file or put on a command line. opencode's auto-update, model catalogue fetch, plugin downloads and sharing are switched off.

Claude Code ("Claude subscription")

The official Claude Code CLI runs as one long-lived claude -p process per avatar, streaming JSON in and out, with rs-sdk's own CLAUDE.md and .mcp.json.

• Sign-in: Settings → Claude subscription (via Claude Code) → Sign in with Claude. AutoRune runs claude auth login in a throwaway sandbox and shows you Anthropic's sign-in link. You sign in on Anthropic's own page in your browser and paste the code it shows. The code goes straight to Claude Code, which completes the login and stores it itself.
• One sign-in per owner: all your avatars share your Claude login, and with it your plan's usage limits.
• Limits: when your plan's limit is reached, the avatar stops with "Limit reached · resets HH:MM" and starts again by itself shortly after the reset.
• Sign out deletes the provider, runs Claude Code's own logout, and wipes your Claude config directory on the server.

Compliance notes for Claude Code

AutoRune follows Anthropic's guidance for products that run Claude Code:

• The binary is unmodified. It is Anthropic's published package, pinned and integrity-checked, run only with documented flags and environment variables (non-essential traffic and auto-updates off). No auth method is removed or restricted.
• Each user authenticates with their own plan, through Anthropic's own flow in their own browser.
• AutoRune never collects, stores, reads or relays Claude credentials or tokens. They live only in the user's Claude config directory on sandbox storage, written and refreshed by Claude Code. They never touch the database, the API's memory, logs or responses. The one-time sign-in code passes through the API once, straight to Claude Code, and is never logged or stored.
• Naming: the option is called "Claude subscription (via Claude Code)". AutoRune doesn't use Anthropic's names or logos as its own.

Codex: deferred

An OpenAI Codex engine is not built. The engine interface is designed so one can be added later as a single glue class plus its sandbox launch, without touching the API, app or autonomy loop.

When the provider fails

Failure	Result
Key rejected (401/403), or signed out of Claude	The avatar stops ("AI provider rejected the key" / "Signed out of Claude"). Settings shows the problem with Reconnect or Sign in again.
Out of credit (402 / quota)	The avatar stops with "Out of credit" until you press Play.
Rate limited (429), or a Claude plan limit	It stops. A Claude plan limit with a known reset time resumes by itself.
Model gone (404)	It stops. Pick another model in Settings.
Provider unreachable (5 retries of one request)	It stops with the reason.
Other one-off errors	The autonomy loop tries again on its next turn, with a growing delay (up to a minute).

Changing the active provider or its model while an avatar runs restarts its agent on the new config.

How the key is protected

See Security and privacy.