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.

Telegram-iOS

01Result

TelegramMessenger/Telegram-iOS ↗

TelegramMessenger/Telegram-iOS AI coding statistics: 39.1%

of 1,303 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
39.1% agent · top contributor 92.5%4 contributors
individual

One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.

510
agent commits
793
other considered commits
4
agent contributors
92.5%
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

510assisted
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
2026-020%128
2026-030%160
2026-0433.9%233
2026-0537%135
2026-0659.1%164
2026-0776.1%180
2026-0858.4%161
2026-0937.3%142

Peak month: 76.1%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic51039.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • e7994d5a on GitHubfeat(corelist): measure the commit-to-display depth a baked flight assumesClaude Code
  • e1b19adc on GitHubfix(corelist): stop the keyframe release from stepping the content forwardClaude Code
  • c4fa8388 on GitHubfix(calls): send 60 ms Opus frames from the reference group engineClaude 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 window1,559
Merge commits removed−256
CI / dependency bots removed−0
Considered1,303

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 →Swift AI coding statisticsCompare evidence across Swift 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 TelegramMessenger/Telegram-iOS

Scan another repository

Try