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.

Write HTML. Render video. Built for agents.

01Result

heygen-com/hyperframes ↗

heygen-com/hyperframes AI coding statistics: 24%

of 3,774 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
24% agent · top contributor 45.4%29 contributors
org-wide

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

905
agent commits
2,869
other considered commits
29
agent contributors
45.4%
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

905assisted
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
2026-0363%173
2026-0421.7%346
2026-0520.9%738
2026-0630.9%569
2026-0720.5%1222
2026-0823.1%511
2026-0910.7%215

Peak month: 63%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic89423.7%
Cursor AgentAnysphere100.3%
OpenAI CodexOpenAI20.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • f98b8ead on GitHubfix(studio): guard import.meta.env reads so the player survives non-Vite EClaude Code
  • e8cbf0ca on GitHubfix(skills): keep changelog-video's stamped seams off the clip elements (#Claude Code
  • 4ba8396c on GitHubchore: release v0.8.35Claude Code
  • e5d89f77 on GitHubfeat(check): flag connectors that point at nothing and stylesheets that leCursor Agent
  • 43dba220 on GitHubfix(capture): bound scroll/evaluate timeouts so heavy pages keep capturingCursor Agent
  • 7860d194 on GitHubfix(capture): fall back from networkidle2 to domcontentloaded on nav timeoCursor Agent
  • 96861cba on GitHubperf(studio-server): coordinate cancelable thumbnail generation (#2720)OpenAI Codex
  • ad11de69 on GitHubfeat(producer): auto-fallback screenshot capture for raf and iframes (#331OpenAI Codex

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 window4,336
Merge commits removed−546
CI / dependency bots removed−16
Considered3,774

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 →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex signatures →TypeScript AI coding statisticsCompare evidence across TypeScript 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 heygen-com/hyperframes

Scan another repository

Try