| What it does | Policy-driven spending controls for AI agents
| Autonomous AI agents that plan, execute, and deliver work without setup or babysitting
|
|---|
| Stage | Not given
| Startup
|
|---|
| 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: $0/month with unlimited projects and tasks plus $2 of agent work to get started, no credit card required. Starter: $39/month with $50 of agent work monthly and up to 6 AI agents. Pro: $99/month with $120 of agent work monthly and unlimited agents, marked as most popular. Enterprise: custom pri
|
|---|
| 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
| - Create agents by describing their role in natural language; Tulsk automatically builds them with the right skills, tools, and schedules
- Agents run continuously in the cloud on schedules, events, mentions, or connected channels without user intervention
- Memory system that learns preferences and project context, separated between personal and team-shared knowledge
- Reusable skills that agents follow consistently without re-explanation across the entire team
- Approval system for writes to connected apps and new connections before agents act
- Connect Slack, Telegram, or WhatsApp for agents to receive and respond to messages with the team's preferred communication tools
- Real workspace files created by agents with live preview; files persist even when the workspace computer sleeps
- Mac desktop app for quick access via keyboard shortcut to chat, inbox, and workspace in any application
|
|---|
| 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 run autonomously in the cloud without requiring setup, configuration screens, or DevOps knowledge
- Integration with any HTTP API, MCP server, or internal company API without agents being limited to one suite
- Reusable skills and shared knowledge layer allow teams to teach patterns once and have all agents follow them consistently
- Free tier with unlimited projects and tasks plus $2 of agent work lets teams start and explore without credit card commitment
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 21 ● no change since last check | 23 ● no change since last check |
|---|
| Trust Flow (Majestic) | 6 | 3 |
|---|
| Citation Flow (Majestic) | 19 | 30 |
|---|
| Referring domains (Majestic) | 12 | 122 |
|---|
ActOnce Spend Gateway
Tulsk