| What it does | Assurance, research and network for autonomous AI agents
| An engine for long-running agents that rebuilds its prompt under a cap and runs on your budget
|
|---|
| Stage | Startup
| MVP
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| Not given
|
|---|
| Pricing model | Not given
| Freemium
|
|---|
| Pricing | Not given
| Prototype: free during beta, then from December 16, 2026 it costs $1 per 1,000 agent calls after 1,000 monthly included calls. Production: $20 a month with 20,000 agent calls included, then $1 per 1,000 calls after that. Top-ups: $1 per 1,000 calls, from $10 to $500 at a time, never expiring.
|
|---|
| Key features | - Test agent behavior against explicit authority boundaries
- Preserve separate evidence of actor choice, authorization, containment and effect
- Bounded adversarial behavioral testing
- Repair and retest workflows with lineage
- Public Observatory for longitudinal research
- Provider-neutral and framework-compatible
- Customer-controlled assurance runtime
- Agent-to-agent collaboration and cross-agent encounters
- Test financial authority and spending limits
- Open integration surface with developer tooling
| - Prompt rebuilt from journal under token cap at each step to keep it bounded as history grows
- Spending limits checked before each model call at token prices you declare
- Resume after crash without repeating finished actions
- Tool calls returned as actions for your code to carry out
- Proof of what ran: check prompts, re-run engine, download hash-chained journal
- Integrations with Vercel AI SDK, OpenAI Agents SDK, LangGraph, Mastra, Pydantic AI
- MCP server for Claude Code, Claude Projects and Codex
- Works with any model via bring-your-own-key
- TypeScript and Python clients for HTTP API access
|
|---|
| What makes it different | - Separates evidence of agent behavior from infrastructure containment, so compliance is not mistaken for trustworthiness
- Tests specific agents against explicit authority boundaries rather than universal safety claims
- Preserves longitudinal behavioral history and repair lineage across retests
- Works with multiple agent frameworks and supports customer-controlled environments
- Enables evidence-backed behavioral testing without requiring production credentials
| - Bounded prompt under a fixed cap while history grows, so costs per call stop climbing on long sessions
- Every run recorded with cryptographic proof: rebuilable prompts, hash-chained journal, re-runnable engine
- Resumes from crash without repeating finished actions using stable idempotency keys
- Budget enforcement before each model call, not reactive overage billing
- No model key storage or logging; your provider bills you directly
|
|---|
| Free plan | Not given
| Not given
|
|---|
| Open source | Not given
| Not given
|
|---|
| Platforms | Not given
| Not given
|
|---|
| Public API | Not given
| Not given
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 1 ● no change since last check | Not checked yet ● no change since last check |
|---|
| Trust Flow (Majestic) | 4 | 0 |
|---|
| Citation Flow (Majestic) | 24 | 9 |
|---|
| Referring domains (Majestic) | 37 | 4 |
|---|
Argentic