| What it does | Compare and track AI agents with live usage data, pricing and reliability
| 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 | Free with an account, up to 5 kits per day. No paid plans listed on the site.
| 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 | - 445 AI agents ranked on live public data
- Agent pricing comparison side-by-side
- AI agent starter kits
- Live status pages for 82 agents
- Pricing history since 2024
- 3,861 libraries ranked by project usage
- 231 live code examples
- 524 APIs in 34 categories
- Real-world usage from 10,078 GitHub repos
| - 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 | - Daily-updated live data on agent downloads, GitHub activity and releases
- No paid placements or affiliates; independent data from official sources
- Tested starter kits verified by AI agents building real projects
- Pricing history for 154 agents since 2024 with daily price checks
- Real-world developer stack analysis from 10,078 public AI-built GitHub repos
| - 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) | 1 ● no change since last check | 21 ● no change since last check |
|---|
| Trust Flow (Majestic) | 1 | 6 |
|---|
| Citation Flow (Majestic) | 26 | 19 |
|---|
| Referring domains (Majestic) | 17 | 12 |
|---|
AgentGid
ActOnce Spend Gateway