| What it does | The credential layer for AI agents
| Real-time steering and guardrails for AI agents
|
|---|
| Stage | Startup
| Not given
|
|---|
| Founded | 2026
| Not given
|
|---|
| Based in | ES
| Not given
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| Pricing | Free: 1 agent, 30 runs/month, public scoring only. Pro: unlimited agents, 1,000 runs/month, private runs, $120/year or $12/month. Team: unlimited agents, 5,000 runs/month, 5 seats, $261/year or $29/month. Enterprise: 25,000 pooled runs/month, SSO, SCIM, from $499/month billed annually.
| Team: Free per organization, unlimited users, 200 session-hours per month. Enterprise and Gateway: Custom pricing, billed annually.
|
|---|
| Key features | - Standardised work sample testing with composite scoring (40% success, 30% latency, 30% cost)
- Five-axis diagnostic radar (correctness, latency, cost, tool efficiency, robustness)
- Ed25519-signed certificates with public key verification
- Hiring Frontier cost-per-task analysis across model candidates
- Embedded badge rendering for README files
- Private screening (Pro plan and above)
- Team workspaces with up to 5 seats
- CSV and PDF export
- API access with rate limits
| - Reads every tool call agents make and blocks unsafe ones before they run
- Catches stalled and runaway sessions while they run
- Steers agents back when they go past what was asked
- Tracks every session's tokens against usual usage
- Stops credential and data leaks before they leave the machine
- Inventories all agents, MCP servers and skills in use
- Blocks dangerous calls before they run in agent hooks and at the gateway
- Sends every finding to Slack, webhook or SIEM
- Verifies each agent's identity before access
- Keeps audit-grade masked records of every action and decision
|
|---|
| What makes it different | - Standardised testing ensures scores are comparable, not self-reported
- Free forever for public scoring with no credit card required
- Model-agnostic testing works with any LLM provider
- Screening completes in under 5 minutes
| - Works with Claude Code, Codex, Cursor, Devin and more
- Runs on your machines, gateways and in the cloud
- Active steering corrects or stops drifting runs
- One policy applied across all MCP servers, plugins and skills
- Continuously monitors components for known vulnerabilities
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 1 ● no change since last check | 3 ▲ +2 (up) since last check |
|---|
| Trust Flow (Majestic) | 0 | 13 |
|---|
| Citation Flow (Majestic) | 19 | 25 |
|---|
| Referring domains (Majestic) | 10 | 23 |
|---|
badgeIA
Stacktrace