Documentation
Trefur is the observability platform for AI agents. Trace every prompt, tool call, retry, and sub-agent. Built on OpenTelemetry GenAI Semantic Conventions so you can instrument once and capture everything — across runtimes, vendors, and deployment patterns.
Quickstart
Connect a platform, send OpenTelemetry traces, or turn on Claude Code telemetry, with nothing to install.
How telemetry reaches Trefur
OAuth discovery, OTLP/HTTP traces, Claude Code telemetry and webhooks — pick the layer that fits your runtime.
Claude Code
Send Claude Code's own metrics and API request events to Trefur with a few environment variables.
Integrations
OAuth into Google Workspace, Microsoft 365, OpenAI, Anthropic, Slack, Atlassian — Trefur pulls activity automatically.
Concepts
Unmanaged AI discovery: the AI your company uses that nobody onboarded.
What can I do with Trefur?
- Trace every agent call — inputs, outputs, latency, cost, tool calls, sub-agent spawns, MCP traffic.
- Debug failing agents — drill from a failing customer interaction down to the specific decision that went wrong, in the specific deployment, on the specific build.
- Catch regressions before customers do — alert on p95 latency, retry-rate spikes, cost drift, and error-rate envelopes; route to Slack, PagerDuty, Teams, or any webhook.
- Capture operational audit logs — every agent run recorded with full call graph for multi-agent topologies.
Three paths in. Pick whichever fits.
| Path | Use it when… |
|---|---|
| OAuth connectors | You want to see the AI your company uses in Google Workspace, Microsoft 365, OpenAI, Anthropic, Slack and more, with no code change. |
| OpenTelemetry traces | You own the agent code, or it already emits OpenTelemetry. Point its OTLP/HTTP exporter at Trefur. |
| Claude Code | Your developers use Claude Code. Its own telemetry reports token use, cost and model calls. |
All three land in the same workspace. Use any combination.
For AI assistants reading this
Every page in this documentation site has a machine-readable mirror at <page>.md and a Schema.org TechArticle JSON-LD block embedded in the HTML. A discoverability manifest lives at /llms.txt. See the API reference for ingest and OAuth surfaces, or the reference pages for the OCSF export, audit ledger export, and response actions.