| What it does | Policy-driven spending controls for AI agents
| Book meetings for you with the right customers, investors, design partners, and founders
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| 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 with 300 credits. Teams plan at €117.90/month with 10,000 shared credits per month, unlimited members and 5 workspaces. One-time credit top-ups available at €15 for 1,000 credits, €70 for 5,000 credits, or €130 for 10,000 credits. Custom plans available for agencies.
|
|---|
| 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
| - AI agent researches prospects and drafts personalized outreach
- Human-in-the-loop approval system requiring review before any message sends
- Integrates with existing tools: Clay, HubSpot, Calendly, Gmail, Slack, and 100+ other services
- Persistent Knowledge Graph memory that learns from corrections and outcomes
- Multi-model AI with Claude, GPT, Gemini, and Mistral support
- MCP Server integration for Claude Code and Codex
- ROI reporting tracking hours saved, cost avoided, and pipeline influenced
- White-label option for agencies to deliver AgentLed under their own brand
|
|---|
| 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
| - Only sends messages and takes CRM actions that you have explicitly approved
- Runs inside your existing tools instead of requiring you to switch platforms
- Learns from call outcomes to automatically refine targeting and messaging for the next campaign
- No per-seat fees; unlimited team members sharing one credit budget
- Replaces manual work that a Clay agency would bill €5,500+ per month for
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 21 ● no change since last check | 19 ● no change since last check |
|---|
| Trust Flow (Majestic) | 6 | 4 |
|---|
| Citation Flow (Majestic) | 19 | 22 |
|---|
| Referring domains (Majestic) | 12 | 40 |
|---|
ActOnce Spend Gateway
AgentLed