Pulse
2026-09-18-v3.0
Dataset
2026-09-18-v3.0
Ruleset
b2e8889c66f7
Scanned
2026-09-16
Window
February–September 15, 2026
Local to this browser

01Result

vectorize-io/hindsight ↗

vectorize-io/hindsight AI coding statistics: 6%

of 2,576 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
6% agent · top contributor 29%42 contributors
org-wide

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

155
agent commits
2,421
other considered commits
42
agent contributors
29%
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

155assisted
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. Across the whole index, 96% of agent commits are assisted.

Agent share by month

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-0215.4%149
2026-0311.1%296
2026-044.9%371
2026-052.6%308
2026-067.1%452
2026-076.8%310
2026-082.2%413
2026-094%277

Peak month: 15.4%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic1495.8%
Cursor AgentAnysphere30.1%
GitHub CopilotGitHub20.1%
OpenAI CodexOpenAI10%

03Evidence

Inspect the matches

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

Matched commit samples

  • 1a000a52 on GitHubfix(control-plane): serve the UI when bound to a loopback address (#4379)Claude Code
  • ee615d61 on GitHubfeat(python-client): add task-local retain suspension (#4285)Claude Code
  • 16d4025f on GitHubblog: Onboarding an Engineer vs. Onboarding an Agent (#4100)Claude Code
  • 41852405 on GitHubperf+fix(graph-maintenance): catch the #2529 sweep deadlock in continuous Cursor Agent
  • 84e67efb on GitHubfix(cursor-cli): parse Cursor 3.x role-nested agent transcripts (#2465)Cursor Agent
  • ef2e8ab7 on GitHubfix(openclaw): apply configured defaults to dynamic banks (#2441)Cursor Agent
  • f3f2c6b0 on GitHubFix timeline group sort: localeCompare → numeric Date comparison (#820)GitHub Copilot
  • 8ce06e3e on GitHubAdd wall-clock timeout to reflect operations (#643)GitHub Copilot
  • 532aa869 on GitHubfix(worker): detect stuck tasks by stage progress (#3720)OpenAI 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 window2,643
Merge commits removed−2
CI / dependency bots removed−65
Considered2,576

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

05Provenance

Pinned to a source state

This observation names the repository state, release, and detector that produced it. Use these identifiers when reproducing or citing the result.

Dataset release
2026-09-18-v3.0
Scan date
2026-09-16
Ruleset
sha256:b2e8889c66f72c18a61839f0bf1a9f77b5481ba2def044dba33c797b2f2bdcae
Canonical repository
vectorize-io/hindsight
Default branch
main
Resolved HEAD
de0b34a1af90fc1b985f22646b8b653607ec29d1 ↗
Resolved
2026-09-16
Measurement window
February–September 15, 2026
Download observation JSONDeterministic export · same values as this page

06Peer context

Position among comparable repositories

The cohort uses the same release and measurement window, then narrows to the repository’s ecosystem and removes low-activity observations.

CohortPython · 247 eligible repositories · at least 100 considered commits2026-09-18-v3.0 · February–September 15, 2026 · 145 of 392 ecosystem repositories excluded
Agent-commit share position48th percentile

Midrank percentile; equal shares split the tied positions.

Repository
6%
Cohort median
6.3%
Share rank
128 / 247
0th50th100th

Percentile = (repositories below + half of 2 tied repositories) ÷ 247.

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 →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex 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 vectorize-io/hindsight

Scan another repository

Try