Navigara
OpenAI

codex — Engineering Performance

33 engineers all time · Apr 2025 – Aug 2026 · built 2026-08-23 · GitHub

Performance snapshot

Today's rolling 90-day reading for codex, compared with the start of the series. Pick a window to move that comparison point.

Eff. capacity added

+137.6engineers

23 devs deliver like 161 (7.0x pre-AI)

Avg. perf / dev / mo (ETV)

+262.9%

1.65 → 6.00

Active engineers

+228.6%

7.0 → 23.0

Features

−25.5pp

61.1% → 35.6%

codex vs. OpenAI

Per-engineer ETV for codex against OpenAI as a whole. Both lines are 90-day rolling averages scaled to a 30-day month, so they share one axis and can be read against each other at any point. Pick a window to zoom the chart to it.

codex
6.00ETV / dev / mo
0.59 (9.0%) past 90d
OpenAI
9.85ETV / dev / mo
+3.60 (+57.6%) past 90d

Performance over time

ETV stacked by Features / Maintenance / Tests / Docs / Fixes — 90-day moving average, normalized to ETV / month.

Engineering capacity

Effective engineers behind codex, in pre-AI terms. Per-engineer ETV divided by the Q1 2025 baseline of 0.86 ETV / dev / mo gives a capacity multiple, and that multiple applied to the engineers active in the trailing 90 days turns it into engineer-equivalents. The line is the real headcount, so the gap between line and area is what the leverage is worth.

Effective engineers
161engineer-equivalents
+138 engineers above real headcount
Real engineers
23engineers
active in the trailing 90 days
Capacity vs pre-AI
7.0x
per engineer, vs 0.86 ETV / dev / mo

Knowledge concentration

How dependent is this repo on a small number of engineers? Higher top-1 share = higher key-person risk.

Top 1
21.3 %
Top 3
45.0 %
Top 5
61.6 %

jif owns 21.3 % of commits.

Reports

Written summary of the work completed each month.

No monthly reports available yet.

Most impactful commits

Top 10 by ETV in the all-time window.