| What it does | Visual builder for deterministic AI agent networks
| Policy-driven spending controls for AI agents
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| Not given
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| Pricing | Pay-what-you-think pricing during soft launch with a minimum of $5/month. 7-day money-back guarantee after activation.
| 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.
|
|---|
| Key features | - Real-time execution tracking with token cost monitoring
- PDF rasterization and chunking for image-based PDFs
- Dynamic document loading from Google Drive, APIs, and MCP sources
- Quorum-based consensus verification for field extraction
- Loop patterns for iterating over LLM list elements
- Field-level context mapping between nodes
- Self-hosted execution with customer API keys
- Encrypted credential management for Drive, REST, URLs, and MCP
- Non-technical user interface for prompt and flow editing
| - 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
|
|---|
| What makes it different | - Precise control over agent paths without code-first framework overhead
- Field-level context injection instead of dumping all data into prompts
- Live control and inspection without redeployment cycles
- Compliance-ready with self-hosted execution and customer-controlled keys
- Purpose-built for PDF pipelines and document extraction workflows
| - 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
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 4 ● no change since last check | 23 ▲ +1 (up) since last check |
|---|
| Trust Flow (Majestic) | 16 | 6 |
|---|
| Citation Flow (Majestic) | 27 | 19 |
|---|
| Referring domains (Majestic) | 188 | 12 |
|---|
LLM Flow Designer
ActOnce Spend Gateway