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

immich-app/immich

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

492 open issues

#30047 App told me to share the error infotmation
#30046 Transcode videos → All keeps re-encoding the same ~60 files after switching from AV1 to H.264
#30045 Mobile: main timeline crashes when backup album has assets with invalid/missing dates (NULL bucket_date in mergedBucket)
#30044 IOS widget memories broken
#30040 Map view thumbnails fail to load on Android app
#30037 RK3588 + RKNN image falls back to CPUExecutionProvider despite correct RKNN configuration
#30031 Mobile: Trashed assets are still included in album date range and latest-photo sorting
#30010 [Bug] Portrait videos play unrotated on iOS (Safari + Chrome) via real-time HLS transcoding, despite correct rotation matrix at every server stage
#30004 Second upload of images due to privacy protection of mobile phone rights
#29982 Cannot edit re-downloaded Live Photos in Lightroom Mobile (Immich or Lightroom issue?)
#29980 RKMPP hardware decoding fails on H.264 files with frame cropping side data in the scale_rkrga path
#29977 Problem syncing Pics: Here Android-App on Google Pixel 9 Pro XL
#29973 Too many elements of NativeVideoViewer
#29971 Slideshow hangs on videos
#29963 Live video transcoding error when audio codec set to mp3, and with hardware acceleration on.
🗄️server
#29956 Thumbnail generation spawns ~8 libvips threads per queued asset (not per core), exhausts container PID limit, and the resulting std::system_error is uncaught (server aborts)
#29945 Slideshow settings and nav buttons poor visibility on white background
#29944 Slideshow on web starts with low res version for each photo
#29943 Live Photos and Selfies from iOS don't generate thumbnails
#29942 Mobile app displays edit button for other users' photos in shared albums, leading to silent failure
#29925 Sync v2 stream has no backpressure — `send()` ignores `response.write()`'s return value, so a large `AssetOcrV1` backlog OOMs the api worker (V8 heap FATAL) and crash-loops it with exit code 0
#29900 [Bug] iOS: Downloaded Live Photo re-uploads as video only (no HEIC sent)
#29875 [mobile] i18n/l10n problem in Ukrainian language
📱mobile
#29869 Immich firefox editor save bug report
#29864 [Bug Report] Ghost header "2027" appears in mobile app timeline despite clean database and metadata
#29853 ios app crashes on browsing search reasults
📱mobile
#29842 Large City Not Found During 'Add a location' to Photo
#29835 Folder view on mobile shows assets from other folders
external-library
#29834 Web viewer paints misaligned stale/partial image blocks while preview streams in (progressive loading, v3.0.2)
needs-answer
#29818 Mobile App (Android) OAuth Auto Launch Not Working
📱mobile