| What it does | Independent verification for bug fixes in C, C++ and firmware
| On-device moderation that flags hateful, abusive and threatening text in 23 European languages, before the message is sent.
|
|---|
| Stage | MVP
| MVP
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| NL
|
|---|
| Pricing model | Not given
| Freemium
|
|---|
| Pricing | Not given
| Free up to 100k monthly active devices with unlimited inference. Custom licenses available.
|
|---|
| Key features | - Reproduces bugs deterministically on base version before applying fix
- Verifies fix removal confirms bug returns
- Scans diffs for masking patterns like disabled sanitizers and weakened tests
- Runs on real hardware via STM32 NUCLEO boards and ST-Link
- Integrates with AI coding agents as MCP tool
- Posts verdicts as GitHub pull request comments
- Provides per-test verdicts: FIXED, BROKEN, FLAKY ON THE BENCH, FLAKY WORSE
- Runs entirely on your machines with no cloud dependency
- Generates reports for change records and regulatory compliance
- Runs builds and tests in Linux container on your machine
| - Three separate scores: hateful, abusive, threat
- Ten target signals under the hate score: race, color, religion, descent, national or ethnic origin, sexual orientation, gender, disability, age, other
- Runs fully on device with no server calls
- Supports 23 European languages from one model file
- 80MB model size optimized for iOS, Android, and browser
- 0.847 macro F1 accuracy on Multilingual HateCheck
- Warn before message is sent
- Comment triage without infrastructure
|
|---|
| What makes it different | - Only verification tool that reverses the fix to prove tests actually catch the bug
- Deterministic verdict with no AI language model in decision logic
- Tests on real hardware boards, not just laptops
- Detects masking techniques that hide bugs while passing tests
- Validated public benchmark showing 4 VERIFIED and 6 REJECTED on real open-source bugs
| - Multilingual support across 23 European languages in a single 80MB model
- Complete privacy with no data leaving the device
- Free access up to 100k monthly active devices with unlimited inference
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | Not checked yet ● no change since last check | 37 ● no change since last check |
|---|
| Trust Flow (Majestic) | 0 | 20 |
|---|
| Citation Flow (Majestic) | 0 | 39 |
|---|
| Referring domains (Majestic) | 0 | 616 |
|---|
Unfix
Toxic