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.

Trackers gives you clean, modular re-implementations of leading multi-object tracking algorithms released under the permissive Apache 2.0 license. You combine them with any detection model you already use.

01Result

roboflow/trackers ↗

roboflow/trackers AI coding statistics: 52.2%

of 180 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
52.2% agent · top contributor 40.4%12 contributors
org-wide

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

94
agent commits
86
other considered commits
12
agent contributors
40.4%
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

93assisted
1autonomous

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
2026-022.2%45
2026-030%6
2026-0480%15
2026-0557.1%21
2026-0691.7%12
2026-0761.5%39
2026-0883.3%30
2026-0975%12

Peak month: 91.7%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic7843.3%
GitHub CopilotGitHub4625.6%
Cursor AgentAnysphere95%
OpenAI CodexOpenAI95%

03Evidence

Inspect the matches

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

Matched commit samples

  • 80a09d68 on GitHubrefactor(tracklet): share scale-aware noise machinery between BoT-SORT andClaude Code
  • 076ecef1 on GitHubperf(ocsort): reuse the box returned by predict (#580)Claude Code
  • 1b3d9435 on GitHubperf(eval): reuse contiguous prepared IDs (#579)Claude Code
  • c25b2347 on GitHub⬆️ bump the uv-lock group with 7 updates (#592)GitHub Copilot
  • 1cb7a071 on GitHubdocs(readme): say "object tracking in Python" in the README (#587)GitHub Copilot
  • 8de9ca07 on GitHubfix(io): order image-directory frames naturally (#558)GitHub Copilot
  • 8de9ca07 on GitHubfix(io): order image-directory frames naturally (#558)Cursor Agent
  • 35dd78b7 on GitHubfix(utils): decode batched `xcycsr_to_xyxy` in floating point (#557)Cursor Agent
  • cf72d2da on GitHubdocs(comparison): add McByte default metrics and rename page title (#539)Cursor Agent
  • 74f1a377 on GitHubperf(kf): avoid bbox decoding during scale-aware noise refresh (#572)OpenAI Codex
  • 7ff4075a on GitHubrefactor(cli): rename scripts→cli, add `jsonargparse` with --config YAML sOpenAI Codex
  • 3b3cdc10 on GitHubperf(config): set McByte CMC downscale default to 6 (#538)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 window323
Merge commits removed−0
CI / dependency bots removed−143
Considered180

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 →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex signatures →Python AI coding statisticsCompare evidence across Python 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 roboflow/trackers

Scan another repository

Try