| What it does | Leave your desk. Not your AI.
| Catch where AI agents get stuck on your API or MCP server, rank problems by impact, and draft fixes as pull requests
|
|---|
| Stage | MVP
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| US
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| Pricing | Free access during beta. The first 5,000 founding members receive 25% off their first three months at launch.
| Open source: free. Team: $199/month with 14-day free trial (1 API or MCP service, 25,000 reports/month, 15 coding-agent runs/month). Business: $799/month (up to 3 services, 250,000 reports/month, 60 coding-agent runs/month). Extra coding-agent runs: $6 each.
|
|---|
| Key features | - Live agent progress with real-time status and activity feed
- Execution plan tracking with completed and upcoming tasks
- Answer agent questions from phone with a tap
- Review and approve generated files and diffs before returning to desk
- Send follow-up instructions mid-task from phone
- Pause or stop agent runs from phone
- Session summary with changed files, commits, and test results
- Intelligent notifications for critical moments
| - Session replay for MCP servers to identify failed agent sessions
- Clustering reports by agent goals and workflows
- Priority ranking weighted by frequency, failed workflows, and affected accounts
- Claude Code generates pull requests with tests
- Review queue with diff, tests, agent reports, and evidence
- Isolated git worktree prevents unauthorized code push
- Schema validation and rate limiting for feedback
- Open Agent Feedback Protocol with TypeScript and Python SDKs
- GitHub integration for draft PR creation
|
|---|
| What makes it different | - Works with multiple AI agents: Claude Code, Codex CLI, and Gemini CLI
- Source code never leaves your machine
- Lightweight companion app instead of remote desktop
- Human-in-the-loop supervision with approval requirements for destructive operations
| - Only AI agent failures on successful HTTP responses get detected and ranked
- Automated pull request drafts with your approval required before shipping
- Session replay captures failures even when agents don't report them
- Pay only for coding-agent runs, not feedback submission
- Open protocol and SDKs can be self-hosted at no cost
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 1 ● no change since last check | 1 ● no change since last check |
|---|
| Trust Flow (Majestic) | 10 | 1 |
|---|
| Citation Flow (Majestic) | 16 | 14 |
|---|
| Referring domains (Majestic) | 10 | 4 |
|---|
Clarsky
Backloop