Tares for AI SRE

An AI SRE watches your services for you. Tares brings in your logs, metrics, alerts and deploys, an agent checks every service on a schedule, and when something looks wrong a second agent looks into it and writes an incident note: what is failing, the likely cause, the evidence and the next step. The note lands in Slack, where your team takes it, resolves it, or says whether it was worth raising.

Your alerting and dashboards stay as they are. Tares gives each incident a head start.

How it works

1. Connect your data. Logs, metrics, alerts, traces and deploys. Every event is tied to the service it is about, so each service has one timeline. Connect your data
2. Watch. The watcher checks every service on a schedule and raises what is unusual. Watching
3. Investigate. The investigator reads the service’s whole timeline and writes the incident note. Runbooks you write for a service go into every investigation. Incidents, Runbooks and memory
4. Respond. The note goes to your Slack channel with buttons: I’m on it, Resolve, Reopen, and whether it was worth raising. Your answers sharpen what the watcher raises next.

The console shows the services, the open incidents, the timeline and whether anybody is watching. Your coding agent can ask the same questions over MCP. Use it from your coding agent

Where Tares runs

On Tares Cloud, create an AI SRE workspace and connect your data. On your local machine, tares up runs the same open source Tares. Install and run

Start here