| What it does | An engine for long-running agents that rebuilds its prompt under a cap and runs on your budget
| Tamper-evident audit trail for AI agents with verifiable records
|
|---|
| Stage | MVP
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| GB
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| Pricing | 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.
| Free: £0, no card required, 1 user, 25,000 live records a month. Solo: £19/month or £190/year, 1 user, 100,000 live records a month (then £5 per 100,000). Team: £49/month or £490/year, unlimited users with roles, 250,000 live records a month (then £5 per 100,000, or £3 above 10 million). Enterprise:
|
|---|
| Key features | - 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
| - Agent signs each record with its own Ed25519 key
- Service co-signs records and chains them to prevent edits or gaps
- Public timestamp bounds each record with hourly verification
- Only salted hashes sent to service; inputs and outputs stay on your machine
- Open verifier code allows independent verification
- Python and TypeScript SDKs for wrapping agent tools
- Verification reports in HTML or PDF format with compliance mapping
- Compliance packs for EU AI Act, ISO/IEC 42001 and SOC 2
- 99.5% uptime guarantee on hosted witness in Google Cloud London
|
|---|
| What makes it different | - 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
| - Records are verifiable offline and survive service shutdown
- Independent co-signature and public time bounds provide proof beyond your control
- Content remains private on your machine in hash-only mode
- Compliance-ready evidence for regulators and auditors
|
|---|
| 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) | Not checked yet ● no change since last check | Not checked yet ● no change since last check |
| Trust Flow (Majestic) | 0 | 0 |
| Citation Flow (Majestic) | 9 | 0 |
| Referring domains (Majestic) | 4 | 0 |