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

PostHog/posthog

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

3,091 open issues

#72192 Intercom "Update contacts" destination: 409 conflict race when concurrent invocations create the same new contact
bug
#72187 Traces (alpha): span_attribute value filters (exact/icontains) return 500 on the spans query endpoint
#72155 Allow accessing nested JSON properties in UI filters
enhancement
#72152 Model SMS as a channel with a selectable provider in Workflows
#72151 Add Plivo as a data warehouse source
#72105 Web analytics weekly digest email sent with all-zero metrics despite project having traffic
#71889 Web analytics: AI visibility — AI channel, bot analytics, and citations (Clarity AI visibility equivalent)
enhancement
team/web-analytics
#71826 Stripe Discount warehouse sync fails with KeyError: 'created'
#71818 Support Android Emulator
enhancement
#71795 Feature flag API accepts a numeric flag-dependency key, but /flags then returns 500 for the entire project
feature/feature-flags
team/feature-flags
#71714 Agent platform: harden the untrusted-caller (authenticated/public) audience — follow-ups
#71711 Feature flag test evaluation: surface holdout in the condition breakdown
feature/feature-flags
team/feature-flags
#71356 Add support for session replays of terminals (CLI commands + TUIs/PTYs)
enhancement
#71311 [Bug] MCP: data_schema feature flag doesn't work in mode=tools
bug
#71306 Anthropic 1-hour prompt-cache writes use the 5-minute rate in auto-costing
#71123 Agent Builder should hand off directly to newly created agents
enhancement
team/agents
#71101 500 Internal Server Error when creating ticket via POST /api/projects/:project_id/conversations/tickets/
bug
#71065 LLM analytics: cost double-counts Gemini reasoning tokens (output tokens already inclusive)
#70960 Bar chart x-tick labels no longer displayed diagonally
enhancement
#70958 Object-level access controls for llm_prompt can be created but are never enforced
team/experiments
#70912 Feature request: Inbox/Self-driving - Framer MCP support
enhancement
self-driving
team/self-driving
#70852 Bug report: experiments - stale full-array save silently drops metrics
bug
team/experiments
feature/experiments
#70850 Filter out "Hidden" events on Event Definitions page
enhancement
#70819 ADHD Mode
enhancement
#70808 temp query
#70637 Repository selection
#70636 ClickHouse Migration Error (DB::Exception: Table system.crash_log doesn't exist)
bug
#70627 Live viewers & edit history for an analytics dashboard
enhancement
#70589 NGINX Unit is archived/unmaintained
bug
#70574 Backfill for streaming behavioral cohorts
feature/cohorts
team/feature-flags