| What it does | Check AI agent replies against configured rules and verify signed records
| 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 | Not given
| NL
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| Pricing | Free: local open-source checker, browser policy checks, six read-only MCP tools, regression export and offline verification. Managed Check API: $1 per 1,000 checked replies, USD, monthly usage billing through Stripe.
| Free up to 100k monthly active devices with unlimited inference. Custom licenses available.
|
|---|
| Key features | - Check agent replies against configured pricing, forbidden phrases, and action records
- Policy Check tool with browser interface for testing rules
- Model Context Protocol endpoint for Claude, ChatGPT and other MCP clients
- Offline verification with signed records and Merkle proofs
- Repair Lab for reproducing and fixing integration failures
- Managed Check API with pricing transparency
- MIT-licensed open-source local checker
- Framework connectors for LangChain and Vercel AI SDK
- MCP Chaos proxy for testing agent behavior
| - 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 | - Verifiable AI agent compliance without authorization or permission granting
- Evidence and records portable across platforms and models
- Transparent per-reply pricing with clear usage examples
- Open-source core with portable verification
| - 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 |
|---|
Curbi
Toxic