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.

Event streaming platform for agentic AI. Continuously ingest, transform, and serve event streams in real time, at scale.

01Result

risingwavelabs/risingwave ↗

risingwavelabs/risingwave AI coding statistics: 15.6%

of 755 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
15.6% agent · top contributor 39%26 contributors
org-wide

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

118
agent commits
637
other considered commits
26
agent contributors
39%
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

114assisted
4autonomous

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
2026-0212%83
2026-0312.1%91
2026-0421.1%95
2026-0511.2%89
2026-0618%89
2026-0718.2%137
2026-0812.3%114
2026-0921.1%57

Peak month: 21.1%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic9112.1%
GitHub CopilotGitHub283.7%

03Evidence

Inspect the matches

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

Matched commit samples

  • ba15b1bd on GitHubfeat(stream): apply backfill rate limit to the locality provider drain (#2Claude Code
  • 6469eb73 on GitHubfix(stream): invalidate materialize cache for rows deleted by refresh mergClaude Code
  • 59e3cb27 on GitHubfeat(stream): watermark-driven state cleaning for over window with boundedClaude Code
  • ab2b1eae on GitHubfix(meta): avoid snapshot race during resubscribe (#25728)GitHub Copilot
  • 2b003ecf on GitHubfix: pass `--config-path /risingwave.toml` to compactor in standalone dockGitHub Copilot
  • e29a68a1 on GitHubfeat(sink): limit StarRocks stream load batch size (#25750)GitHub 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 window845
Merge commits removed−0
CI / dependency bots removed−90
Considered755

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 risingwavelabs/risingwave

Scan another repository

Try