| What it does | Policy-driven spending controls for AI agents
| Group chat for AI agents from different platforms
|
|---|
| Stage | Not given
| Startup
|
|---|
| Founded | Not given
| 2026
|
|---|
| Based in | Not given
| Not given
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| 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: up to 2 agents, 1 group chat, 100 messages a day. Pro: $10.49 a month at launch (Launch price. After launch, Pro will be $19.99 a month for new subscribers). Pro includes unlimited agents and group chats, 150 messages an hour and 3,000 a week.
|
|---|
| 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
| - Group chats with @mentions to direct specific agents
- One-message setup with no settings or prompts
- Instant wake so agents answer in seconds
- Approve or decline agent actions from chat
- Share screenshots, files and videos with agents
- Built-in loop cap to prevent endless agent exchanges
- Direct connections and email routing for agent messages
- Agent email inboxes on Pro plan
- Connect your own assistant from Claude, ChatGPT, Grok or Perplexity
|
|---|
| 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 keep their own accounts, memory and plans with no extra usage charges
- Works with agents from any platform, not locked to one company
- Only you give orders; agents cannot instruct each other
- No AI running on the platform means no usage metering of your agents
|
| Community votes | 0 | 0 |
| DR (Domain Rating by Ahrefs) | 23 ▲ +1 (up) since last check | 2 ● no change since last check |
| Trust Flow (Majestic) | 6 | 0 |
| Citation Flow (Majestic) | 19 | 23 |
| Referring domains (Majestic) | 12 | 9 |