OpenSRE integrates with your existing observability stack. You don't need to change how you monitor your systems — OpenSRE connects to the tools you already use and queries them during investigations.
| Category | Supported Tools |
|---|---|
| Container Orchestration & Cloud | Kubernetes, AWS, Azure, GCP, Docker |
| Metrics & Monitoring | Prometheus, Grafana, Datadog, New Relic, Coralogix, Honeycomb, VictoriaMetrics |
| Logging | Elasticsearch, Splunk, Loki, VictoriaLogs |
| Distributed Tracing | Jaeger, Datadog APM |
| Error Tracking | Sentry |
| Alerting & Incidents | PagerDuty, Opsgenie, Incident.io, Blameless, FireHydrant |
| Communication | Slack, Microsoft Teams |
| Source Control | GitHub, GitLab, Bitbucket, Sourcegraph |
| Docs & Knowledge | Notion, Google Docs |
| Databases | PostgreSQL, MySQL, Snowflake, BigQuery |
| Ticketing & Project | Jira, Linear, ClickUp |
| LLM Providers | Anthropic (default), any provider via the optional LiteLLM proxy |
OpenSRE can run PromQL queries against your Prometheus instance to check metric anomalies, query alert history, and correlate metrics with incident timelines.
integrations:
prometheus:
url: ${PROMETHEUS_URL}
# Optional basic auth
# username: ${PROMETHEUS_USERNAME}
# password: ${PROMETHEUS_PASSWORD}
OpenSRE can read Grafana dashboard panels, check alert states, and pull annotations that mark deployments or other events.
integrations:
grafana:
url: ${GRAFANA_URL}
api_key: ${GRAFANA_API_KEY}
Full Datadog integration covers metrics, APM traces, monitors, and service health.
integrations:
datadog:
api_key: ${DATADOG_API_KEY}
app_key: ${DATADOG_APP_KEY}
site: datadoghq.com # or datadoghq.eu, us3.datadoghq.com, etc.
OpenSRE ships skills for New Relic, Coralogix, Honeycomb, Jaeger, Loki, VictoriaLogs, and VictoriaMetrics too. Configuration follows the same integrations.<name> pattern — see each skill's SKILL.md under sre-agent/.claude/skills/ for its exact fields, or Configuration for the ones already documented there.
OpenSRE queries Elasticsearch for log patterns, error spikes, and service-specific log analysis.
integrations:
elasticsearch:
domain: ${ELASTICSEARCH_DOMAIN}
username: ${ELASTICSEARCH_USERNAME}
api_key: ${ELASTICSEARCH_API_KEY}
Log investigation over Splunk, via the observability-splunk skill. See its SKILL.md for required credentials.
OpenSRE can look up distributed traces in Jaeger by service, operation, or trace ID, and analyze span timing and error propagation.
OpenSRE queries Sentry for recent error events, stack traces, and release health metrics correlated with the incident timeline.
integrations:
sentry:
auth_token: ${SENTRY_AUTH_TOKEN}
organization: your-org
# Optional: restrict to specific projects
# projects:
# - your-project
OpenSRE can query PagerDuty for recent incident history, on-call schedules, and alert timelines — providing context about whether this is a recurring alert.
integrations:
pagerduty:
api_key: ${PAGERDUTY_API_KEY}
# Optional: restrict to specific service IDs
# service_ids:
# - PXXXXXX
Alert timelines and escalation context via the alerting-opsgenie skill.
Slack integration serves two roles:
By default, OpenSRE's agent calls Anthropic directly — no proxy required:
ai_model:
provider: anthropic
model_id: claude-sonnet-4-6
If you want to route through another provider — OpenRouter, OpenAI, Ollama, or others — start the optional LiteLLM proxy and either point ai_model.provider at it or set ANTHROPIC_BASE_URL to the proxy address. See Configuration and litellm_config.yaml for the full setup. This is an opt-in add-on, not the default request path.
For tools not listed here, you can add custom integrations as investigation skills. See Investigation Skills for how to create a custom skill that queries your specific tool.