| What it does | Policy-driven spending controls for AI agents
| Deploy production-grade AI agents in 2 minutes with built-in PII protection
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| NZ
|
|---|
| 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.
| Basic (Free): 100k tokens, 1k requests, GPT-6 Luna, email and community support. Starter: $19/month (was $49): 1m tokens, 10k requests, all models with newest first, priority 24/7 support, direct roadmap input, monthly 1:1 product call, free compliance assessment. Custom: contact for enterprise need
|
|---|
| 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
| - Guardian Layer PII protection with remove, mask, transform or detect options
- Support for over 100 AI models including OpenAI, Anthropic, Google, Mistral and open-source
- Build with Python, JavaScript or visual no-code builder
- Multi-agent routing with specialized agents on different models
- Tools including web search, Gmail, X, URL scraping and document parsing
- Built-in knowledge base with automatic retrieval, embeddings and citations
- Zero infrastructure deployment with hosted endpoint and auto-scaling
- Session memory included in deployments
- Bring your own API key or use Custodian-managed models
- Custom entity types for PII protection
|
|---|
| 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
| - Guardian Layer proprietary PII protection keeps context while protecting sensitive data
- Deploy production agents in 2 minutes with no infrastructure setup
- One-line model switching across 100+ models without changing agent logic
- Complete support agent with knowledge base and memory in 6 lines of code
- Built-in multi-agent routing for specialized agent teams
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 23 ▲ +1 (up) since last check | 3 ● no change since last check |
|---|
| Trust Flow (Majestic) | 6 | 9 |
|---|
| Citation Flow (Majestic) | 19 | 23 |
|---|
| Referring domains (Majestic) | 12 | 52 |
|---|
ActOnce Spend Gateway
Custodian Labs