| What it does | AI security reviewer for engineering teams
| On-device moderation that flags hateful, abusive and threatening text in 23 European languages, before the message is sent.
|
|---|
| Stage | Not given
| MVP
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | GB
| NL
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| Pricing | Free for up to 2 active contributors or open source projects. Starter $95/month for up to 5 contributors, Team $195/month for up to 15 contributors, Growth $395/month for up to 40 contributors. Annual subscriptions billed upfront at ten times the monthly price (2 months free).
| Free up to 100k monthly active devices with unlimited inference. Custom licenses available.
|
|---|
| Key features | - Codebase context mapping across repositories and components
- Architecture review and security assumptions analysis
- Focused vulnerability hunting with specialised security lenses
- Finding validation and deduplication
- HTML reports with source locations and suggested fixes
- Review state dashboard with findings filtered by severity
- CLI and terminal dashboard interface
- Support for Claude, Codex and OpenCode AI models
- Unlimited repositories and Dokima runs per plan
- Local data processing without uploading findings
| - 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 | - AI-powered security review that learns how your software works and keeps reviewing as code evolves
- Findings challenged before presentation to separate plausible issues from weak ones
- Choose your own AI models to suit your budget and privacy preferences
- Full product trial for 21 days with no payment card required
- Free forever for small teams up to 2 contributors and open source projects
| - 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) | 40 ▲ +38 (up) since last check | 37 ● no change since last check |
|---|
| Trust Flow (Majestic) | 0 | 20 |
|---|
| Citation Flow (Majestic) | 0 | 39 |
|---|
| Referring domains (Majestic) | 1 | 616 |
|---|
Toxic