Pulse
2026-09-18-v3.0
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 live data layer for apps and AI agents. Create up-to-the-second views into your business, just using SQL

01Result

MaterializeInc/materialize ↗

MaterializeInc/materialize AI coding statistics: 33.2%

of 2,731 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
33.2% agent · top contributor 26.8%36 contributors
org-wide

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

908
agent commits
1,823
other considered commits
36
agent contributors
26.8%
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

839assisted
69autonomous

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
MonthAgent shareConsidered commits
2026-029.6%313
2026-0312.2%344
2026-0429.7%320
2026-0534.4%355
2026-0639.2%411
2026-0741.7%458
2026-0845.8%354
2026-0959.7%176

Peak month: 59.7%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic90633.2%
GitHub CopilotGitHub30.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • a8d6814f on GitHubCLO-216: balancerd: enforce a max connection limit (#38436)Claude Code
  • 7005919b on GitHubdocs: add a cluster sizing guide built on hydration history (#38726)Claude Code
  • 2daa609a on GitHubpgwire: make the frame length ceiling a per-call-site argument (#38809)Claude Code
  • 5a8b0f34 on GitHubadapter: remove unused timestamp-difference metrics and their redundant peGitHub Copilot
  • b088d23e on GitHubCLO-108 Pass app.kubernetes.io/* labels to clusterd/balancerd/console sts/GitHub Copilot
  • 16d611fb on GitHub[mysql source versioning] add binlog setting to mysql source details at puGitHub Copilot

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 window3,135
Merge commits removed−28
CI / dependency bots removed−376
Considered2,731

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 →Rust AI coding statisticsCompare evidence across Rust 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 MaterializeInc/materialize

Scan another repository

Try