| What it does | Check AI agent replies against configured rules and verify signed records
| Independent verification for bug fixes in C, C++ and firmware
|
|---|
| Stage | Not given
| MVP
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| Not given
|
|---|
| Pricing model | Freemium
| Not given
|
|---|
| 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.
| Not given
|
|---|
| 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
| - 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
|
|---|
| 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
| - 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
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | Not checked yet ● no change since last check | Not checked yet ● no change since last check |
|---|
| Trust Flow (Majestic) | 0 | 0 |
|---|
| Citation Flow (Majestic) | 0 | 0 |
|---|
| Referring domains (Majestic) | 0 | 0 |
|---|
Curbi
Unfix