Dataset: 2026-10-27-catalog-ai-v2
Ruleset: b2e8889c66f7
Scanned: 2026-10-27
Window: February–September 15, 2026

Catalog tracking observation. This repository is measured with the same fixed window and ruleset, but it is not part of the published benchmark or its aggregate claims.

The Z3 Theorem Prover

01Result

Z3Prover/z3 ↗

Z3Prover/z3 AI coding statistics: 55.8%

of 1,973 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

55.8% agent · top contributor 37.9%20 contributors

org-wide

Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.

1,101

agent commits

872

other considered commits

agent contributors

37.9%

largest contributor

02Drivers

What shapes this result

Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.

Assisted or autonomous

675assisted

426autonomous

Assisted — a developer’s identity authored the commit and the agent added itself as co-author. Autonomous — a bot identity authored the commit without a human identity attached.

Agent share by month

Agent-attributed commit share by month
Month	Agent share	Considered commits
2026-01	100%	3
2026-02	53.3%	1028
2026-03	74.8%	155
2026-04	48.3%	58
2026-05	39.8%	83
2026-06	44.9%	156
2026-07	59.1%	230
2026-08	63.6%	209
2026-09	66.7%	51

Peak month: 100%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
GitHub Copilot	GitHub	1075	54.5%
Claude Code	Anthropic	31	1.6%

03Evidence

Inspect the matches

Public commit samples let you inspect the signatures behind the aggregate result.

Matched commit samples

2d2fb04f on GitHubFix FP overflow with large significands (#10801)GitHub Copilot
f056f6a6 on GitHubopt: return exact algebraic optimization bounds through the API (#10783)GitHub Copilot
8a6d409e on GitHubMake seq_regex_live::reachable_live take a seq::view (#10787)GitHub Copilot
b2e921ce on GitHubopt: enumerate Pareto fronts of pure NRA problems over an nlsat-backed solClaude Code
a0b0affd on GitHubopt: build Pareto dominance constraints from algebraic model values (#1072Claude Code
aded9b63 on GitHubSplit seq_parikh unit test: keep fast grids in -a, move the rest to seq_paClaude Code

04Method

What entered the denominator

The result begins with commit history, removes merges and routine automation, and reports literal agent signatures as a lower bound.

Exclusion ledger

Commits in window	2,250
Merge commits removed	−157
CI / dependency bots removed	−120
Considered	1,973

Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.

Continue exploring

Claude Code commitsBrowse repositories with detected Claude Code signatures →GitHub Copilot commitsBrowse repositories with detected GitHub Copilot signatures →C++ AI coding statisticsCompare evidence across C++ repositories →GitHub AI commit analyzerInspect another repository with the same evidence model →

Reproduce this observation

Run the same detector locally.

Deterministic signature matching; no code-style inference. Squash merges can remove trailers, so this result remains a measured floor.

npx qmmit-cli Z3Prover/z3

Scan another repository

Try