Does Tessary need access to my repo to find the root cause?

Not strictly: RCA still runs and completes on trace evidence alone when no repo is connected, it just says so and reports a lower ceiling on what it can conclude. With a repo linked, it reads the code alongside the trace evidence to work backward through what actually changed, and the resulting report can name the specific files behind a hypothesis. Without one, it stays at the trace level: no files to cite, hypotheses about behavior rather than about a specific code change. If you want the fuller report, connecting the repo is what buys it. Skipping that step doesn’t block an investigation, it just caps what the investigation can tell you.

keep reading

More on this.

Two ways to run Tessary.

Tessary is an open-source agent reliability platform. Cloud and self-hosted run the same workflow on the OpenTelemetry traces your agent already emits.

Tessary Cloud

We host it for you. Send your first trace with nothing to deploy and no model key.

what's includedper organization
traces
10,000 per calendar month
stored trace data
1 GB
retention
30 days
model credit
$10, one-time, for triage and root-cause analysis
credit card
not required

Self-hosted Tessary

Run the open-source code on your own infrastructure with one command. Add your own model key for triage and root-cause analysis.

Self-host Tessary for me by following https://github.com/tessaryai/tessary/blob/main/setup.md

docker compose -f oci://docker.io/tessaryai/tessary:compose up -d -y