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

ccxt/ccxt ↗

ccxt/ccxt AI coding statistics: 5.7%

of 1,961 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
5.7% agent · top contributor 25.2%22 contributors
org-wide

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

111
agent commits
1,850
other considered commits
22
agent contributors
25.2%
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

111assisted
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
2026-020.8%130
2026-030%193
2026-048.3%121
2026-0511.6%172
2026-063.1%327
2026-073.5%343
2026-087.2%538
2026-0913.9%137

Peak month: 13.9%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
GitHub CopilotGitHub613.1%
Claude CodeAnthropic512.6%
Cursor AgentAnysphere10.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • 1927d7a0 on GitHubchore(build): batch 8 merge-gate-green small fixes (#30328, #30271, #30260GitHub Copilot
  • eb86fadd on GitHubtest(safeFloat): add extra tests (#30265)GitHub Copilot
  • 4fed9f5a on GitHubfix(iso8601): fixes & unification & perf across all langs (#30224)GitHub Copilot
  • c24369f4 on GitHubfix(base): handle signed mantissa in precisionFromString exponent par… (#3Claude Code
  • 57801a7f on GitHubBatch 4 PRs: #30411, #30406, #30046, #29896 (#30415)Claude Code
  • 1927d7a0 on GitHubchore(build): batch 8 merge-gate-green small fixes (#30328, #30271, #30260Claude Code
  • 9698f727 on GitHubfix: route OKX RPI order book updates (#29886)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 window7,144
Merge commits removed−331
CI / dependency bots removed−4,852
Considered1,961

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
ccxt/ccxt
Default branch
master
Resolved HEAD
97fb49e2455c5e525fa38f1f0024d305c61b39c1 ↗
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.

CohortRust · 117 eligible repositories · at least 100 considered commits2026-09-18-v3.0 · February–September 15, 2026 · 33 of 150 ecosystem repositories excluded
Agent-commit share position72nd percentile

Midrank percentile; equal shares split the tied positions.

Repository
5.7%
Cohort median
2%
Share rank
33 / 117
0th50th100th

Percentile = (repositories below + half of 1 tied repository) ÷ 117.

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 →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 ccxt/ccxt

Scan another repository

Try