AI app starters · Rank #7
ai-reliability-copilot
Grade B: derived only from the two verdicts below. How grades work
Turn a production incident into a structured 9-section LLM response (severity, root cause, mitigation, postmortem). Ships with a 5-scenario regression suite + LLM-as-judge eval pipeline.
Why this verdict
How we check →- 32 commits by 1 contributor in the last 90 days (32 in the last 30). receipt ↗
- Vercel AI SDK 6 declared; latest is 7 (1 major behind). receipt ↗
- On current major: Next.js, React, Supabase JS, Tailwind CSS, Zod. receipt ↗
- Not counted in verdict: TypeScript 5 → 7. receipt ↗
Snapshot: commit a4b648f on main, checked 2026-10-19 07:39 UTC. Receipts link to files at this exact commit.
- No license detected: check terms before commercial use.
Dependency freshness
| Package | Declared | Latest | Status |
|---|---|---|---|
| TypeScript typescript | 5.0.0 | 7.0.2 | Behind, not counted |
| Vercel AI SDK ai | 6.0.191 | 7.0.143 | 1 major behind |
| Next.js next | 16.2.9 | 16.4.2 | Current |
| React react | 19.2.7 | 19.3.1 | Current |
| Supabase JS @supabase/supabase-js | 2.106.2 | 2.118.0 | Current |
| Tailwind CSS tailwindcss | 4.0.0 | 4.3.3 | Current |
| Zod zod | 4.4.3 | 4.6.7 | Current |
Declared = lowest version the kit's dependency file (package.json, pyproject.toml or requirements.txt) allows. Latest = the npm "latest" tag or the newest PyPI release. TypeScript, the Stripe SDK, FastAPI and other 0.x packages are shown but not counted in the verdict.
What's in the stack
Detected from declared dependencies. A listed package means it's installed, not necessarily fully wired up.
What the README says you get
- AIStructured incident reports
It produces a structured response with severity, ranked hypotheses, cited evidence
- AIRanked root cause hypotheses
Root cause hypotheses (3–5, ranked by likelihood with cited evidence)
- AIMitigation with rollback
Mitigation plan (with risk + mandatory rollback per step)
- AIPostmortem draft
Postmortem draft (markdown, all H2 sections in order)
- AIInvestigation checklist
Investigation checklist (copy-pasteable commands, expected outputs)
- AICustomer impact section
Customer impact (externally-facing)
- AISeverity reasoning
Severity reasoning (citing the rubric rule applied)
- APIMCP client integration
connect an MCP client to search runbooks and incident history
- OtherMarkdown/JSON export
export complete investigations and analyses as Markdown or JSON
- OtherCLI alert piping
pipe alerts through the CLI
- OtherLocal evidence file intake
Import up to five UTF-8 `.txt`, `.log`, `.json`, `.md`, or `.csv` files
- OtherCredential detection and redaction
Credential check shows detected credential types and their locations
- TeamsOwner assignment and tracking
assign owners and track investigation, mitigation, and follow-up actions
- UIEvidence workspace filters
local text search, kind and service filters, and cited/uncited views
Extracted from the kit's README by a local AI model (deepseek-flash) on Oct 19, 2026. Every item is checked against an exact README quote. A README claim is the maker's description, not something we tested.
Watch ai-reliability-copilot
Get told if it goes dormant, gets archived, falls further behind on a core dependency, or changes its license or price.
History
Sep 29, 2026 → Oct 19, 2026. One square per check, colored by maintenance status. Hover for details.
Show as a table
| Date | Maintenance | Dependencies | Commits (90d) |
|---|---|---|---|
| Oct 19, 2026 | Active | 1 major behind | 32 |
| Oct 12, 2026 | Active | 1 major behind | 21 |
| Sep 29, 2026 | Active | 1 major behind | 13 |
Sources
Every claim on this page comes from these public records, checked . Open them to verify.
- Commit history ↗ default branch (main) at the checked commit: pulse, contributors, last commit
- Releases ↗ latest release
- package.json ↗ declared dependency versions and stack (at commit a4b648f)
- README ↗ quoted features at the checked commit
- npm registry ↗ latest versions (each linked in the table above)