devswha

Claw Bench — Development skill for Claude Code

Development community

Benchmark suite: Claw Code (Rust) vs Claude Code (Node.js).

How to install Claw Bench

This entry records only its repository, not the path inside it, so there is no exact command to give. Open devswha/claw-bench and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Claw Bench does

Benchmark suite: Claw Code (Rust) vs Claude Code (Node.js).

Alternatives in Development

Claw Code Agent — Claw Code No Rust No TypeScript Only Python 543 ★
Run Benchmarks — Run Benchmarks — GenAIIDP empirical config/scaling suite 295 ★
Obsidian Claw — Obsidian Claw Skill for Claude and Openclaw 172 ★

README

claw-bench

**Runtime overhead benchmarks for AI coding CLIs — Rust vs Node.js**

**Note:** Task-effectiveness benchmarking (SWE-bench, practical coding tasks, token tracking) has moved to **[OpenBench](https://github.com/devswha/OpenBench)** — an open benchmarking framework that compares coding-agent CLIs (Claude Code, Codex, and their plugin wrappers) with same tasks, same environment, and comparable results. claw-bench remains available for runtime overhead measurements (startup, memory, binary size).

[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE) [![CI](https://github.com/devswha/claw-bench/actions/workflows/benchmark.yml/badge.svg)](https://github.com/devswha/claw-bench/actions/workflows/benchmark.yml) [![Benchmark](https://img.shields.io/badge/benchmark-stable_suite-E8590C)](bench-all.sh)

Measured on Ubuntu 24.04 · [Run your own benchmarks](#quick-start) · Inspired by [claw-code](https://github.com/devswha/claw-code)

Minimal benchmark suite comparing **Claw Code** (Rust single-binary CLI) vs **Claude Code** (Node.js CLI), with **optional Codex runtime comparison** for the stable local-only benchmarks.

Stable Default Suite

`./bench-all.sh` intentionally runs only the **stable local runtime core**:

startup time
install footprint
idle memory

Everything else in this repo is **manual / experimental** and should be treated as exploratory rather than headline-quality benchmarking.

Default stable-suite behavior remains **human-readable terminal output**. If you want machine-readable artifacts, the three stable benchmark scripts support an optional `--json` mode that writes one JSON file under `results/tier0/`, and `./bench-all.sh --json` writes a timestamped Tier 0 directory containing one per-benchmark JSON file plus `manifest.json`. The three per-benchmark Tier 0 JSON files