Head to head
Kilo Code vs OpenCode
The facts side by side — model held constant. No performance verdict until traces are published under the pre-registered method.
aeqi builds one of the harnesses measured here. This board is in method preview and pre-registration — no performance scores are published yet, and we lead with our own losses, not our wins. Read the method & charter →
| Attribute | Kilo Code | OpenCode |
|---|---|---|
| Maintainer | Kilo-Org | sst |
| License | Apache-2.0 | MIT |
| Category | Coding harness | Coding harness |
| Headless run | Partial — primarily a VS Code extension; CLI exists (npm) but the editor loop is the main surface | Yes — `opencode run --format json` (mind the open non-interactive edge cases) |
| Native OpenRouter | ||
| Determinism | The IDE-embedded surface is the fairness challenge — the CLI is the path to a controlled run. Smoke-test first. | Official container image + git tag to pin. Isolate per run — it has a persistent-server mode that carries state. |
| Benchmark result | Not yet measured | Not yet measured |
Questions
- Is Kilo Code better than OpenCode?
- The aeqi Harness Index does not publish a performance verdict for Kilo Code vs OpenCode yet — scores land only with published traces under the pre-registered method. What this page compares are the verifiable facts: license, category, headless capability, and whether each can be pinned to one shared model for a fair run.
- Can Kilo Code and OpenCode be benchmarked fairly against each other?
- Yes — both document native OpenRouter support, so we can point them at one identical pinned model and attribute any difference to the scaffold, not the model.