| What it does | Policy-driven spending controls for AI agents
| AI teammates that do recurring business work with approvals, budgets, and receipts
|
|---|
| Stage | Not given
| MVP
|
|---|
| Founded | Not given
| 2025
|
|---|
| 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: 1,000 credits (one time), no card required. Pro: $29/month with 10,000 credits monthly. Team: $99/month with 35,000 credits monthly. Enterprise: from $1,500/month. Credits cost $0.001 each; typical costs are 6 credits for a chat message, 3 credits for a background task run, 15-60 credits for d
|
|---|
| 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
| - Agents run per task on demand with no servers to manage
- Every tool call is policy-checked with a receipt
- Approvals for third-party reach, deletion, and untrusted content
- Credential vault where the model only sees a handle, never a key
- Sandboxed code execution with deny-all egress by default
- Web chat on every plan; Slack and email on Team plan
- Per-agent budgets with work metered in credits
- Workspace export with activity log on Team and Enterprise plans
|
|---|
| 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
| - Security and cost controls built in by default, not enterprise add-ons
- Idle agents cost nothing; work runs on demand then stops
- A standing team you can see with receipts for every action
- Built for work you have to answer for with approvals and audits
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 23 ▲ +1 (up) since last check | 19 ▼ −1 (down) since last check |
|---|
| Trust Flow (Majestic) | 6 | 4 |
|---|
| Citation Flow (Majestic) | 19 | 30 |
|---|
| Referring domains (Majestic) | 12 | 105 |
|---|
ActOnce Spend Gateway
OpenLegion