Astra-Ares
Adaptive reasoning effort for GPT-6 during Codex tasks, powered by Jev to reduce token usage.
314 ★ on GitHub
What it is
Experimental reference implementation. Astra-Ares has a straightforward setup, but runs a separate, patched version of Codex CLI. It is primarily a reference for bringing adaptive reasoning effort into your own agent systems; it is still an early preview for everyday development. Most of my projects focus on…
Where the decision sits
Astra-Ares runs its own weights or its own runtime rather than calling a hosted API, so its decisions do not depend on a vendor being up or on a key being funded. The trade is that the model is now yours to keep current.
How active it is
Created 2026-09-22, last pushed 2026-10-07, 314 stars and 29 forks when we read it on 2026-11-02. Everything in this category is weeks old at most, so a stale push date means something different here than it would on a mature project. Check the repository before you depend on it.
Find out what your data actually supports
We turn your historical decisions into a frozen test set, then tell you which model, which threshold, and how much of it you can safely automate.