Skip to main content
The full agentic AI ships in the open-source build — you bring your own model key. On a self-host the key lives on the server (in the environment), shared by every workspace, and is unmetered: you pay your provider directly, nothing is metered by Replayfy. AI is optional and off until you give it a provider. Set three variables and restart the API. Point LLM_PROVIDER at OpenRouter and you reach every provider by model id — no per-provider setup:
Swap LLM_MODEL for any model OpenRouter offers:

​
Anthropic directly

If you’d rather call Anthropic without a gateway:

​
What it powers

Storylines

A narrated summary of what happened across your product.

Signals & investigations

Surfaced issues, with a grounded root-cause pass on demand.

Ask

Ask about a metric, funnel, or session in plain language.

Likely cause

The Overview’s “why did this move” explanations.

​
No key set?

Nothing crashes. AI features tell you they need a key: the Ask panel shows a “set up AI” notice instead of a broken chat, and Settings → AI reports Not configured with the exact env vars to set. Add the key, restart, done.
The key is server-side by design — one key for every workspace, and it stays out of the application database. There is no per-workspace key entry in the self-hosted dashboard.