| What it does | AI coworker for design, implementation, and iteration
| 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 | Free
| Freemium
|
|---|
| Pricing | Not given
| 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 | - Project context memory that maintains understanding of codebase and architecture decisions
- Code implementation with writing, review, and refactoring capabilities
- Design collaboration for system design discussions and architectural trade-offs
- Task breakdown into manageable, actionable tasks
- Technical documentation generation and maintenance
- Continuous learning that adapts to preferences and coding style
- Problem diagnosis analyzing errors and identifying root causes
- Knowledge management organizing project knowledge and decision processes
- Natural language interaction understanding needs and providing solutions
| - 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 | - Reduces communication overhead by maintaining project context through the entire workflow
- Applies Claude Cowork workflow patterns independently without Anthropic affiliation
- Connects design discussions to code implementation across the development lifecycle
- Supports iterative refinement based on feedback and evolving requirements
- Always available to provide engineering support whenever your team needs it
| - 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) | 14 ● no change since last check | 21 ● no change since last check |
|---|
| Trust Flow (Majestic) | 8 | 6 |
|---|
| Citation Flow (Majestic) | 23 | 19 |
|---|
| Referring domains (Majestic) | 43 | 12 |
|---|
Cowork AI
ActOnce Spend Gateway