An AI assistant for Grafana.
The value is not writing the query. It is going from the query result to the line of code without leaving the session.
Query in natural language
PromQL and LogQL are both easy to read and irritating to compose from memory, especially the rate and histogram_quantile shapes that come up constantly during an incident. Describing what you want and getting the query is a small saving individually and a real one at three in the morning.
The step that matters
Most assistants stop at the query result. This one also has your repository open, so it can find the code that emits a metric or a log line and propose a change. Going from a spike on a dashboard to a diff is the workflow; the query is a step in it rather than the point.
Reads dashboards you already have
It connects to your Grafana rather than replacing it. Existing dashboards, data sources and alert rules remain yours; the agent reads them for context, which means it knows what you already consider worth watching.
Local, because logs contain everything
Log lines routinely include user identifiers, request payloads and occasionally things that should never have been logged. Running against a local model means none of that is transmitted to answer a question about it.
In the Dashboards tab
Questions
Related
- Local-First AI Coding AgentSame agent core in a native desktop app and a 6 MB Rust binary, running whichever model you choose, including one on your own laptop.
- Local LLM Coding AgentFor when the constraint is not cost but that the code cannot leave the building.
- Diagram-Driven DevelopmentThe diagram stops being documentation produced after the fact and becomes the instruction the code is written from.
- Terminal Coding AgentOne binary, no runtime, no browser. Free and open source.