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

home-assistant/core

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

2,489 open issues

#176846 husqvarna_automower_ble: Config flow crashes on None values; Gardena SILENO life then fails during BLE initialization with GATT errors
integration: husqvarna_automower_ble
#176841 switchbot_cloud: Air Purifier: ValueError: 0 is not a valid AirPurifierMode
integration: switchbot_cloud
#176837 Home Assistant Core crashes with a native SIGTRAP (signal 5) approximately once every several hours to a day
#176836 Blink auth/setup appears broken again after #173811 fix path (July 19, 2026)
integration: blink
#176835 Media player entity reports media_position=0 on resume although playback continues at previous position
integration: music_assistant
#176831 growatt_server: login retry on restart can push account into 507 lockout
integration: growatt_server
#176828 UniFi integration missing CPU and memory sensors
integration: unifi
#176826 Ping integration packet loss sensor becomes 'unavailable' instead of reporting '100%' loss
integration: ping
#176821 CRITICAL - historical data loss on backup
integration: recorder
database: sqlite3
#176816 Nanoleaf Essentials HomeKit lightstrip pairing over Thread fails with Invalid request and LibraryShutdown
integration: homekit_controller
#176813 Cloud integrations enabled without consent on fresh HAOS install
integration: default_config
#176808 Device has no entities: UnicodeDecodeError in mitsubishi_comfort local API response parsing
integration: mitsubishi_comfort
#176807 Nest camera.snapshot returns placeholder image instead of real frame for WebRTC-only devices
integration: nest
#176806 Nice G.O.: WebSocket drops 60 seconds after connection
integration: nice_go
#176805 Recorder's wal_checkpoint(TRUNCATE) fails instantly with generic sqlite3.DatabaseError: unknown error, but identical PRAGMA succeeds when run directly
#176801 eheimdigital: Config flow crashes with "Unknown error" — TypeError: unsupported callable in eheimdigital hub.py (getfullargspec on None)
integration: eheimdigital
#176800 Russound RIO: Selectable MCA-66 sources omitted from media_player source_list
integration: russound_rio
#176794 Miele Integration Cooktop KM 7740 reports 4 plates instead of 5.
integration: miele
#176790 UI automation editor calls non-existent automation.reload service with CONF_ID parameter, causing partial reload to silently fail (ServiceNotFound)
integration: automation
#176789 BatteryCameraWorkMode
integration: ezviz
#176784 No Media Controls on Spotify integration
integration: spotify
#176779 Stale MQTT discovery data in core.config_entries overwrites manually configured ESPHome IP addresses after restart
#176776 Core crashes every few hours on 2026.7.2 with "cannot notify on un-acquired lock" in concurrent.futures executor; stable on 2026.6.4 (Python 3.14, HAOS Green)
#176772 Miele integration - Tumble dryer energy consumption negative values
integration: miele
#176770 Person with multiple trackers drops to away if one tracker goes away
#176762 MCP Server: GetLiveContext parameter schema breaks MCP clients — any call with arguments fails with "extra keys not allowed @ data['__unparsedToolInput']"
integration: mcp_server
#176761 cloudflare_r2: fails with IncompleteBody on UploadPart
integration: cloudflare_r2
#176760 SMTP does not recognise image attachments generated with action: camera.snapshot
integration: smtp
#176759 Stop logging TemplateError while editing a template
integration: template
#176755 Support for Tuya Double Digital Meter (unsupported)
integration: tuya