FinalRun
By FinalRun. Category: Mobile testing with AI. Homepage
FinalRun's documentation describes FinalRun as an open-source tool for AI-driven Android and iOS test automation. Tests are plain-English YAML specs, and agent skills for Claude Code, Cursor and Codex generate, run and fix them. The FinalRun CLI executes tests with a vision-based AI model, using the user's own Gemini, GPT or Claude key or FinalRun Cloud. Android tests run on real devices and emulators, and iOS tests on simulators only. The CLI is free under Apache-2.0; FinalRun Cloud bills per execution after included credits. CI/CD runs are supported only on FinalRun Cloud.
Description written from the vendor's documentation.
Status
Status: Active
Facts
| Fact | Value | Evidence | Source | Verified on |
|---|---|---|---|---|
| Status | Active | Documented | github.com | |
| Founded | Not documented | Not documented | None found | |
| Headquarters | Not documented | Not documented | None found | |
| AI capabilities | Documented | docs.finalrun.app | ||
| Test creation | Documented | docs.finalrun.app | ||
| Test output | Proprietary runner | Documented | docs.finalrun.app | |
| Surfaces | Documented | docs.finalrun.app | ||
| Hosting | Documented | docs.finalrun.app | ||
| Pricing model | Documented | docs.finalrun.app | ||
| Free tier | Yes | Documented | docs.finalrun.app | |
| CI integrations | Vendor-stated | finalrun.app | ||
| Self-healing | Vendor stated | Vendor-stated | finalrun.app | |
| Agent integration | FinalRun agent skills (/finalrun-generate-test, /finalrun-use-cli, /finalrun-test-and-fix) installed with npx skills add final-run/finalrun-agent, for Claude Code, Cursor, Codex and other skills-protocol agents | Documented | docs.finalrun.app | |
| Open source | Yes, licence Apache-2.0 | Documented | github.com |
Published prices
No prices are published.
Vendor-stated, verbatim
What FinalRun says about its product, quoted as published and not confirmed in documentation.
“#1 on AndroidWorld: 97.4% — Google DeepMind's agent benchmark”
Alternatives
Tools in the same category (Mobile testing with AI), ordered by the number of shared creation and surface values, then by name. Each line lists documented facts that differ from FinalRun.
- AutoMobile: Mobile testing with AI; no documented difference in output, creation, hosting or free tier
- Digital.ai Testing: documents output Mixed; creation by recording; status acquired
- Drizz: Mobile testing with AI; no documented difference in output, creation, hosting or free tier
- HeadSpin: documents no free tier
- noqa: documents hosting hybrid
- Panto AI: Mobile testing with AI; no documented difference in output, creation, hosting or free tier
Questions
Is this page a review of FinalRun?
No. This page is a fact sheet. Each fact shows its evidence level, its source and the date it was checked. We do not rate or rank tools.
Does FinalRun have a free tier?
Yes. FinalRun has a free tier. This is documented, checked on 2026-09-24.
What test output does FinalRun produce?
Output: Proprietary runner. This is documented, checked on 2026-09-24.
Is FinalRun still available?
Status: Active, checked on 2026-09-24.
Sources
- FinalRun homepage Opened
- final-run/finalrun-agent GitHub repository (README) Opened
- finalrun-agent CHANGELOG Opened
- FinalRun docs home Opened
- FinalRun documentation index (llms.txt) Opened
- FinalRun FAQ: accounts, AI providers, pricing, and CI/CD Opened
- Get your FinalRun Cloud API key Opened
- FinalRun AI agent skills: generate, run, and fix tests Opened
- FinalRun YAML test format Opened
Spotted an outdated or wrong fact about FinalRun? Send the source and we apply it at the next monthly update.