# Apgar

> Release health for AI agents.

> ## Agent Instructions
> Before you set up or change an Apgar integration, install the Apgar skill: npx skills add https://docs.useapgar.dev
> Search these docs with the MCP server at https://docs.useapgar.dev/mcp. Setup for each agent: https://docs.useapgar.dev/ai-agents.md

- [Introduction](https://docs.useapgar.dev/index.md): Release health for AI agents.
- [Quickstart](https://docs.useapgar.dev/quickstart.md): Run Apgar with Docker Compose, explore the demo, and add your first agent.
- [Use with AI agents](https://docs.useapgar.dev/ai-agents.md): Give your coding agent the Apgar skill and the docs MCP server.
- [How it works](https://docs.useapgar.dev/how-it-works.md): From traces to turns, releases, verdicts, and messages.
- [Troubleshooting](https://docs.useapgar.dev/troubleshooting.md): What to check when turns, releases, verdicts, or messages do not show up.
- [OpenTelemetry](https://docs.useapgar.dev/send-traces/opentelemetry.md): Send agent traces to Apgar over OTLP/HTTP.
- [Langfuse](https://docs.useapgar.dev/send-traces/langfuse.md): Pull traces from a Langfuse project.
- [Attribute reference](https://docs.useapgar.dev/send-traces/attributes.md): Which span and resource attributes Apgar reads, in which order.
- [Releases and baselines](https://docs.useapgar.dev/concepts/releases.md): How Apgar detects a release, picks what to compare it with, and when monitoring ends.
- [Verdicts](https://docs.useapgar.dev/concepts/verdicts.md): How an evaluation becomes a verdict, and what each label means.
- [Metrics](https://docs.useapgar.dev/concepts/metrics.md): What Apgar measures, how much change it allows, and where a change is concentrated.
- [Sessions](https://docs.useapgar.dev/concepts/sessions.md): Why a conversation should stay on one release, and how Apgar treats sessions that do not.
- [Slack](https://docs.useapgar.dev/notifications/slack.md): Post one message per release event to a Slack channel.
- [Webhooks](https://docs.useapgar.dev/notifications/webhooks.md): Receive signed JSON for every release event.
- [Deploy](https://docs.useapgar.dev/self-hosting/deploy.md): Run Apgar with Docker Compose on your own host.
- [Kubernetes](https://docs.useapgar.dev/self-hosting/kubernetes.md): Run Apgar on Kubernetes with the Helm chart.
- [Configuration](https://docs.useapgar.dev/self-hosting/configuration.md): Environment variables, runtime settings, and access.
- [Monitoring](https://docs.useapgar.dev/self-hosting/monitoring.md): Health checks, logs, and Prometheus metrics.
- [CLI](https://docs.useapgar.dev/self-hosting/cli.md): The apgar command and its exit codes.
- [Data handling](https://docs.useapgar.dev/privacy/data-handling.md): What Apgar stores, what it drops, and where it connects to.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.