I built an open-source coding agent that uses 63% fewer tokens than Codex CLI

说明与用途

Mixdog 是一个开源编码代理，在保持相同成功率的情况下，比 Codex CLI 使用少 63% 的令牌。

问题

Claude and ChatGPT subscriptions hit limits because most tokens were spent on reading files, re‑sending context, and full reasoning for every small step.

结果

Mixdog achieved the same success rate as Codex CLI while using 63% fewer tokens and 39% lower cost, demonstrating token‑efficient coding workflow.

工作流

• 1. Sign in with existing Claude, ChatGPT, Grok or Muse Code subscription or provide an API key. 2. Run Mixdog locally or via npm. 3. Mixdog uses a lightweight local model to judge each message and tool step, selecting minimal reasoning effort. 4. It keeps tool results and history compact and displays a context view. 5. Execute coding tasks; Mixdog logs verdicts, scripts, and token usage for verification.

证据

I built Mixdog, an open‑source coding agent focused on doing the same work with fewer tokens.

来源

I ran all 89 Terminal‑Bench 2.1 tasks, 5 trials each, with the same model (GPT‑5.6 Sol, xhigh) on both sides, scored by the official Harbor verifier:

来源

Total tokens: 156.5M for Mixdog, 421.4M for Codex CLI

来源

That's 63% fewer tokens at the same success rate, and fewer tokens on 87 of the 89 tasks.

来源

A 150 MB model running locally on the CPU judges each message and tool step in about 0.1 s and picks the effort it needs, so simple steps don't burn xhigh reasoning.

来源