Benchmark CLI for comparing AI coding agents on TypeScript workloads.
Latest release v1-final — v1 final (Exercism baseline) · 1 Apr 2026
2 files for GitHub Copilot, Codex and OpenCode: ts-bench copilot-instructions.md, ts-bench AGENTS.md — 343 tokens loaded in every session.
.github/copilot-instructions.md A 230 tok AGENTS.md A 113 tok These files are laiso/ts-bench's own configuration — they tell GitHub Copilot, Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.