| What it does | Catch where AI agents get stuck on your API or MCP server, rank problems by impact, and draft fixes as pull requests
| Give your agents their own computer
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | US
| AT
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| Pricing | 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.
| Hobby: free (1 concurrent VM, 2 vCPU/4GB RAM, community support). Pro: $20/mo (includes $20/mo usage credits, then metered on vCPU-seconds, RAM-GB-seconds, storage-GB-hours, and egress-GB). Enterprise: custom pricing.
|
|---|
| Key features | - 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
| - VMs boot in ~2 seconds from snapshot with dev server already running
- Claude Code and Codex pre-authenticated with your own credentials
- Real machine with systemd, root, and Docker inside every VM
- Wildcard HTTPS URLs behind *.onhomemade.com for every VM
- Web terminal attached to persistent session
- Automatic PR previews and Linear ticket VMs
- MCP servers injected at boot
- Agent signals and sibling VM requests for unattended work
- Hibernation instead of deletion for dormant VMs
|
|---|
| What makes it different | - 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
| - Real machines with full Linux kernel, not containers pretending to be machines
- Agents start already authenticated—no login prompts or shared bot accounts
- Usage-based pricing: pay for only what VMs actually consume
- VMs boot from warm snapshots in ~1 second, not minutes
- Instant live preview URLs for every environment to share with reviewers
|
| Community votes | 0 | 0 |
| DR (Domain Rating by Ahrefs) | 1 ● no change since last check | Not checked yet ● no change since last check |
| Trust Flow (Majestic) | 1 | 0 |
| Citation Flow (Majestic) | 14 | 0 |
| Referring domains (Majestic) | 4 | 1 |