AI agents with exact memory and verifiable sources
The evidence layer for AI-agent actions
Stage
MVP
Not given
Founded
Not given
Not given
Based in
Not given
US
Pricing model
Not given
Freemium
Pricing
Not given
Developer: Free with no time limit (1,000 verified actions/month). Builder (Founding): $59/month for first 12 months, then $99/month (5,000 verified actions/month, then 2.5¢ per action). Team: $299/month (25,000 verified actions/month, then 1.5¢ per action). Growth: $999/month (100,000 verified acti
Key features
Answers with exact facts and sources
Bit-for-bit consistent outputs
Exact integer arithmetic for models
Open-source code under Apache-2.0 licence
Beta access available
Records agent actions through API or OpenTelemetry spans
Verifies actions against systems of record including Stripe, Shopify, Salesforce, HubSpot, Zendesk, Intercom and Coinbase
Integrates with agent frameworks: LangGraph, CrewAI, OpenAI Agents SDK, Pydantic AI
Supports workflow runtimes: Temporal and Inngest
Action contracts define verification rules with limits and required effects
Settlement window re-checks verify actions again at end of settlement window
Webhooks and Slack/PagerDuty alerts on verdict results
Public hash verification allows verifying verdicts without an account
What makes it different
Exact memory with source verification
Deterministic, reproducible AI outputs
Transparent about uncertainty
Publicly auditable open-source models
Verdicts come from deterministic rules, not language models
Never blocks actions; verifies after the fact only
Takes no payment from vendors; paid only by customer
Tested against real models: Claude, GPT and Gemini
Priced by verified actions, not seats or agent claims