| What it does | Continuous performance testing for your CI that catches regressions before they reach production
| Open-source runtime for computer-use agents
|
|---|
| Stage | Not given
| Startup
|
|---|
| Founded | Not given
| 2026
|
|---|
| Based in | FR
| Not given
|
|---|
| Pricing model | Freemium
| Open source
|
|---|
| Pricing | Not given
| Not given
|
|---|
| Key features | - Automatic benchmarking in CI
- Low-noise performance data with variance below 1%
- AI-enhanced differential flamegraphs
- Automated performance fixes with Optimization Agent
- GitHub integration
- CPU, memory, and wall-time profiling
- Bare-metal macro runners for isolated testing
- Support for Rust, Python, Node.js, C++, Go, and Java
- Performance gating and merge blocking
| - Works with any OpenAI-compatible model
- Ready-wait mechanism instead of fixed sleeps
- Batches actions and bounds model calls
- Desktop pause, resume and fork with memory
- MCP server for Claude Code and Cursor
- Graded rollouts for computer-use RL
- Works with full desktops
- Supports multiple sandbox providers
|
|---|
| What makes it different | - AI automatically identifies bottlenecks and proposes fixes
- Integrates seamlessly into existing CI workflows and benchmark frameworks
- Free for open-source projects and up to 5 users on private repos
- Detects regressions before they reach production
| - 1.48x faster than Anthropic's computer-use reference loop on the same model
- 19 points more success than OSWorld's Qwen agent at same speed
- Reduces rollout time by 40-53% by eliminating unnecessary waiting
- Published benchmarks run same model on same desktops with reproducible results
- Works with any model and sandbox provider
|
| Community votes | 0 | 0 |
| DR (Domain Rating by Ahrefs) | 65 ▼ −1 (down) since last check | Not checked yet ● no change since last check |
| Trust Flow (Majestic) | 18 | 0 |
| Citation Flow (Majestic) | 37 | 0 |
| Referring domains (Majestic) | 534 | 0 |