Operate is a self-hosted AI SRE: an AI agent platform that detects, investigates, and resolves production issues. It runs a four-agent pipeline (Context, Root Cause, Verification, and Resolution) that connects to your logs, database, and codebase, then produces an evidence-backed root cause and a draft pull request for human review.

An AI SRE is an AI system that does the work of a site reliability engineer: watching production for errors and regressions, investigating alerts, finding root causes, and proposing fixes. Operate is a self-hosted AI SRE, so it runs inside your own infrastructure with read-only access and a mandatory human approval gate.

How does Operate find the root cause of a production issue?

When triggered from chat (Slack, MS Teams, and other tools) or by an automated alert, Operate pulls traces from log providers like Datadog, CloudWatch, GCP Cloud Logging, and SolarWinds, queries your MongoDB, PostgreSQL, or MySQL database in read-only mode, and reads your codebase via git including blame and diff. A Context Agent gathers signals, a Root Cause Agent proposes a cause with a confidence score, a Verification Agent independently checks the reasoning with a different model, and a Resolution Agent drafts a fix as a pull request.

Does Operate ship code automatically without a human?

No. Operate stops at a draft pull request. A human engineer must review and merge; nothing ships without approval. Every agent step is auditable so reviewers can see the evidence and reasoning behind each finding.

How is Operate deployed?

Operate is deployed as a Docker image into your existing infrastructure with no new cloud accounts. It runs on port 8080 under the /operate path, requires MongoDB and Redis, and uses an App ID from operate.bettrsw.com. It connects via read-only adapters to logs, databases, and observability stacks, and clones your repo at startup via an init container so agents have full git history.

Which integrations does Operate support?

Operate's context layer spans 60+ integrations across 14 categories: source control (GitHub, GitLab), logs (Datadog, CloudWatch, GCP Cloud Logging, SolarWinds), databases (MongoDB, PostgreSQL, MySQL, read-only), error tracking (Sentry, Rollbar), APM (New Relic, Grafana, OpenTelemetry), CI/CD (GitHub Actions, Jenkins, Vercel), feature flags (LaunchDarkly, Statsig), cloud infrastructure (AWS, GCP, Azure, Kubernetes), queues (Kafka, SQS, RabbitMQ), incident management (PagerDuty, incident.io), issue tracking (Jira, Linear, Asana), support (Zendesk, Intercom), status pages, and docs (Confluence, Notion). Triggers: Slack, MS Teams, and other chat tools for on-demand RCA, plus the observability stack for proactive monitoring. AI providers: Anthropic Claude, OpenAI/Azure Codex, enterprise models, or self-hosted open-source LLMs.

How does Operate avoid hallucinated root causes?

Operate uses a two-model verification step. The Root Cause Agent proposes a cause with specific evidence; the Verification Agent, running on a different model to avoid correlated errors, independently evaluates the reasoning. Speculative or unsupported conclusions are rejected before reaching the team.

Why not just point an LLM at our logs ourselves?

An LLM has no inherent knowledge of your logs, schemas, services, or known-bad patterns. Operate provides the connectors, permissions, query layer, repo context, multi-agent verification, and operational runtime that turn a generic model into a reliable production-investigation system.

Engineering teams that lose 30–40% of capacity to unplanned investigation: support escalations, error alerts, performance regressions. With Operate, support and product teams can trigger an RCA from Slack, MS Teams, or whatever chat tool they use, and only loop in engineers when a decision needs to be made.

← All repos

github

apache/superset

Pick an open issue and Operate will investigate its root cause.

269 open issues

#42215 Security scan findings — 2026-07-19
#bug:regression
authentication
#42116 Dashboard Properties Advanced JSON 'refresh_frequency' not supported?
dashboard:properties
dashboard:refresh
#42109 feat(helm): support component-specific extra volumes and mounts
deploy:helm
#42085 SQL Lab: get oracle schema structure: HTTP 422
validation:required
sqllab
data:connect:oracle
#42073 Facing 401 issue in embedded dashboard
authentication:access-control
embedded
#42071 MCP SQL execution falsely flags identifiers containing disallowed function names
validation:required
sqllab
#42050 Docs: Stale docs about what versions of Postgres supported
good first issue
doc:user
doc
#42043 Cannot modify the Druid database if unreachable.
validation:required
data:connect:druid
#42041 permissions underscore replace
authentication:RBAC
#42035 Duplicates permissions
validation:required
authentication:RBAC
#41883 [Country map] Madagascar ISO_3166-2 admin1 boundaries are not unique
viz:charts:geojson
#41854 [SIP-220] Proposal for Extensions Storage
sip
extensions
#41797 [SIP-221] Selective Per-Audience Dashboard Versions for Embedded Multi-Tenant Deployments
sip
design:proposal
#41779 [SIP-219] A uniform model for built-in extensions: registration, resolution, and loading
sip
extensions
#41745 SSH Tunneling is quite slow
#bug:performance
data:databases
#41687 Dashboard/Chart/Dataset export endpoints inherit 1-year Cache-Control, causing stale/cached exports
viz:charts:export
dashboard:export
api
#41610 MCP use JWT token authen failed g.user not found
validation:required
sqllab
authentication
View investigation
#41604 API-key feature enabled but can't appera and used on latest version 6.1.0
validation:required
authentication:fab
#41583 Tooltips in the calendar heat map charts can remain in DOM even when navigating away from a dashboard
viz:charts:tooltip
dashboard:editmode
#41498 [SIP-218] Proposal for Canvas-Based Custom Filter and Date Filter Chart Plugins
sip
design:proposal
viz:charts
#41496 [SIP-217] Dataset Relationship Model — declare and manage relationships between datasets
sip
data:dataset
design:proposal
api
#41268 Failed to add user to db session: Class 'werkzeug.local.LocalProxy' is not mapped
validation:required
authentication:access-control
embedded
#41266 Bug Report: ChunkLoadError when loading lazy-loaded frontend bundle
validation:required
#41154 Tootip (using handlebars) background is transparent, read value is not easy
viz:charts:tooltip
#41153 Superset Helm Chart: configOverrides applied during install causes authentication failures (401 / anonymous user)
deploy:helm
#bug:regression
authentication
#41114 [SIP-215] MCP : Improve MCP chart preview tools - add rendered image and structured data preview options
sip
embedded
#41048 82 - Add CHART_PLUGINS_DEPRECATED feature flag
enhancement:request
viz:dynamic-plugins
#41047 83 - Make the Deck.GL plugin non-legacy
viz:charts:deck.gl
#41046 89 - Migrate and remove the legacy Nightingale chart
viz:charts:pie
#41045 93 - Deprecate/remove JS-based tooltips (and vm2 dependency)
viz:charts:tooltip