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.

Fancy stream processing made operationally mundane

redpanda-data/connect ↗

redpanda-data/connect AI coding statistics: 8.1%

of 642 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
8.1% agent · top contributor 42.3%7 contributors
team

A small group is using agents. Adoption has spread beyond one person but is not project-wide.

52
agent commits
590
other considered commits
7
agent contributors
42.3%
largest contributor

What shapes this result

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

Assisted or autonomous

52assisted
0autonomous

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
2026-021.1%92
2026-037.5%159
2026-045.1%137
2026-0510.5%95
2026-0612.2%49
2026-077.7%39
2026-0821.2%33
2026-0915.8%38

Peak month: 21.2%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic528.1%

Inspect the matches

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

Matched commit samples

  • 2e6dcb71 on GitHubsnowflake_streaming: compare offset tokens numerically, not lexicographicaClaude Code
  • 377fe35b on GitHubiceberg: measure write-path throughput without the pipeline suite (#4786)Claude Code
  • 74fb9f6c on GitHubiceberg: add a commit-regime harness for latency-bound throughput (#4788)Claude Code

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 window706
Merge commits removed−0
CI / dependency bots removed−64
Considered642

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

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 redpanda-data/connect

Scan another repository