| What it does | Policy-driven spending controls for AI agents
| The agent-native Growth OS that turns your AI agent into a disciplined growth hacker
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| US
|
|---|
| Pricing model | Freemium
| Not given
|
|---|
| Pricing | Free: $0/month (open source, self-hosted). Pro: $24/month with hosted dashboard, 3 agents, 1,000 spend checks/month. Team: $99/month with 10 agents, 10,000 checks/month, team approvals. Business: $299/month with unlimited agents and checks.
| Free: 1 member, 1 project, unlimited free contributors and viewers. Solo: $19.90/month for 1 member with unlimited projects. Team: $39/month for up to 3 members, then $10/month per extra member, with unlimited projects and private projects.
|
|---|
| Key features | - Policy Engine with YAML configuration for amount limits, merchant allowlists, category blocks, business hours, and duplicate windows
- Duplicate Detection using SQLite to prevent the same purchase twice within a configurable time window
- Human-in-the-Loop approval with Telegram alerts and dashboard queue for purchases exceeding threshold
- MCP-Native integration for OpenClaw, Hermes, and any MCP-compatible agent
- Zero Credential Exposure with no access to cards, tokens, or Stripe credentials
- Local-first architecture with all policy files, logs, and databases stored on your machine
- Dry-run and simulation mode for testing policies before deployment
| - Complete experiment backlog with candidate ideas
- Status tracking from idea to outcome
- Shared experiment learnings across team and agents
- ICE, PIE, RICE scoring frameworks with voting
- Enforced experiment stages with mandatory results and learnings
- MCP server for AI agent read and write access
- Skills that teach agents the methodology
- Plugin for Claude Code and Codex
- Web app for team review and collaboration
- OAuth security with granular permissions
|
|---|
| What makes it different | - Policy-driven rules that the agent cannot override, unlike prompt-based guardrails
- Zero credential exposure means the gateway never sees payment cards or API keys
- Duplicate detection with SQLite prevents duplicate purchases within a configurable time window
- Native MCP integration works out of the box with OpenClaw, Hermes, Claude Code, and Cursor
| - Agents cannot bypass the method: tests cannot close without measured results and written learnings
- Enforced workflow prevents confident guesses and invented wins
- Shared memory ensures experiments are never repeated and evidence is preserved
- Agents read and write to the same record as teams under identical rules
- Data stays in EU on Hetzner servers in Finland
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 21 ● no change since last check | Not checked yet ● no change since last check |
|---|
| Trust Flow (Majestic) | 6 | 1 |
|---|
| Citation Flow (Majestic) | 19 | 18 |
|---|
| Referring domains (Majestic) | 12 | 4 |
|---|
ActOnce Spend Gateway
Hypotize