Gut Check
Home Assistant integration that runs weekly checks with Jev judgments and turns confident findings into Repairs cards for you to confirm.
Overview
Gut Check gives a Home Assistant install a weekly checkup. It finds entities that stopped reporting, updates that might break something and integrations that failed to start, and suggests fixes for loose ends such as devices with no area, sensors with no device class, critical labels, diagnostic sensors, recorder settings and dashboard clutter. Jev makes the judgment calls and reports how sure it is.
According to a list summary, its eight checks ask a Score on each pending update's release notes and a Choice per item elsewhere, for example whether an unavailable entity is expected, worth fixing or safe to remove. Answers below 0.5 confidence change nothing, and anything needing action waits in Settings > Repairs for the user to act on or ignore. The README documents what it will never do, cost, exactly what is sent and not sent, and how to change things back. It installs through HACS and has tests and coverage.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Score | How risky is this pending update, based on its release notes? | — |
| Choice | Is this unavailable entity expected, worth fixing or safe to remove? | expected · worth fixing · safe to remove |
How it works
- Run the weekly checks
- Ask Jev about each item
- Ignore answers below 0.5 confidence
- Create Repairs cards for confident findings; user confirms
Strengths
- Never changes things without confirmation
- Transparent about data sent and cost
- Covers many housekeeping checks
Caveats
- Requires a TypeSafe key
- Home Assistant only
Getting started
Add the repository as a custom HACS integration, install Gut Check, and enter your TypeSafe key.At a glance
- Type
- Project
- Status
- beta
- Language
- Python
- Runtime
- Home Assistant integration
- Has code
- yes
- Has tests
- yes
Use cases and integrations
How curated lists describe it
Smart home: Home Assistant integration whose eight install checks ask Jev a `Score` on each pending update's release notes and a `Choice` per item elsewhere, such as whether an unavailable entity is expected, worth fixing or safe to remove; answers below 0.5 confidence change nothing, and the rest that need action become Repairs cards the user must confirm.
yibie/awesome-jevHome Assistant integration that uses TypeSafe AI's Jev to spot problems and suggest cleanups in your install, and asks before changing anything.
hellogumbo/awesome-jev
Frequently asked questions
Will it change my setup automatically?
No, actions wait as Repairs cards for you to confirm.
What happens with uncertain answers?
Below 0.5 confidence, nothing changes.
How often does it run?
Weekly, or on demand.
Related projects
Smart-meter fleet dashboard where code pre-filters telemetry and Jev classifies anomalies for remediation across millions of endpoints.
ProjectprototypeTypeScriptSelf-hosted Stacks blockchain data service whose Slack gate and fault-triage paths reportedly run on Jev decisions.
ServiceproductionTypeScriptScores OpenTelemetry logs with Jev for diagnostic value, priority and routing before any expensive LLM analysis.
ProjectbetaTypeScriptPython CLI that analyses JSON, NDJSON and JSONC logs and artifacts with Jev question packs, anchoring each answer to source lines.
CLIbetaPythonSplunk search command that asks Jev typed questions about events and adds probabilities, choices and scores as fields.
AppbetaPythonOne Jev call per log batch answers noise and severity questions; code maps answers to suppress, watch, review, notify or page.
ProjectbetaPython