Loading...
Loading...
Standardized benchmarks for OpenClaw forks running on real hardware constraints. Each test runs in a Docker container matching the device's CPU and memory profile.
| # | Device | Fork | Score |
|---|---|---|---|
| 1 | Cloud VPS (2GB)Cloud | TypeScriptMoltworker | 77 |
| 2 | Cloud VPS (4GB) |
A repeatable, containerized pipeline that tests every fork under real hardware constraints.
Fork is cloned into a Docker container with CPU and RAM limits matching the target device.
Dependencies installed via the native toolchain — Go, Rust, Python, TypeScript, or C.
Entry point detected, cold start timed, peak memory tracked via cgroup, disk usage measured.
Results combined into a 0–100 composite score weighted across four dimensions.
| TypeScriptMoltworker |
| 72 |
| 3 | Cloud VPS (2GB)Cloud | TypeScriptMoltworker | 7.5 |
| 4 | Cloud VPS (2GB)Cloud | TypeScriptMoltworker | 7.5 |
| 5 | Cloud VPS (2GB)Cloud | TypeScriptMoltworker | 7.5 |
| 6 | Cloud VPS (2GB)Cloud | TypeScriptMoltworker | 7.5 |
| 7 | Cloud VPS (2GB)Cloud | TypeScriptMoltworker | 7.5 |
| 8 | Cloud VPS (2GB)Cloud | TypeScriptMoltworker | 7.5 |
| 9 | Cloud VPS (2GB)Cloud | TypeScriptMoltworker | 7.5 |
Messaging, browser, code exec, memory, files, search, MCP, tool use
Cold start time — clone + install + startup. Under 5s = full marks
Disk footprint after install. Under 20MB = full marks
5 pts for dependency install, 5 pts for successful startup
Detected via static source analysis and runtime module probing. Each passed test contributes 5 pts to the capabilities score.
Run benchmarks locally or contribute improvements