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.

Capture SSL/TLS plaintext with eBPF—no MITM proxy or custom CA installation. Supports Linux and Android on x86_64 and arm64.

01Result

gojue/ecapture ↗

gojue/ecapture AI coding statistics: 22.2%

of 63 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
Too little recent activity to publish. Only 63 commits landed in this window, so the percentage is noisy. Repositories below 100 are excluded from the index for this reason.
22.2% agent · top contributor 42.9%4 contributors
team

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

14
agent commits
49
other considered commits
4
agent contributors
42.9%
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

12assisted
2autonomous

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
2026-020%1
2026-0318.8%16
2026-0420%10
2026-0526.7%15
2026-0630%10
2026-0740%5
2026-080%2
2026-090%4

Peak month: 40%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
GitHub CopilotGitHub69.5%
Claude CodeAnthropic57.9%
DevinCognition23.2%
Cursor AgentAnysphere11.6%

03Evidence

Inspect the matches

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

Matched commit samples

  • faedaf94 on GitHubfix: prevent data loss on EventProcessor shutdown due to worker abandonmenGitHub Copilot
  • 298b28d4 on GitHubfix: warn when --pid/--uid filters are silently ignored on kernel < 5.2 (#GitHub Copilot
  • 41751bc7 on GitHubfix: cgroup filtering support for TC hook and GoTLS uprobe (#979)GitHub Copilot
  • 97c1c1a6 on GitHubtest/e2e: improve pcap interface detection with route verification (#1021)Claude Code
  • f199e33a on GitHubbuilder: use backticks for shell command substitution in RUNClaude Code
  • 49fef4a0 on GitHubfix: OpenSSL version-to-bytecode mapping bugs + Docker build reproducibiliClaude Code
  • 943a19fe on GitHubchore(wiki): translate .devin/wiki.json to English and tighten compliance Devin
  • d5821caf on GitHubchore(wiki): flatten DeepWiki page hierarchy to 2 levels (#995)Devin
  • 8203fdc7 on GitHubfix(gotls): 单次 hook 按 16KB 分段输出 BPF perf 事件 (#1020)Cursor Agent

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 window63
Merge commits removed−0
CI / dependency bots removed−0
Considered63

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 →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →Devin commitsBrowse repositories with detected Devin signatures →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 gojue/ecapture

Scan another repository

Try