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.

Build your own AI SRE agents. The open source toolkit for the AI era.

Tracer-Cloud/opensre ↗

Tracer-Cloud/opensre AI coding statistics: 12.8%

of 3,333 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
12.8% agent · top contributor 38.6%69 contributors
org-wide

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

425
agent commits
2,908
other considered commits
69
agent contributors
38.6%
largest contributor

What shapes this result

Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.

Assisted or autonomous

421assisted
4autonomous

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
2026-0218.4%141
2026-032.8%217
2026-042.5%682
2026-0524.2%637
2026-0630%406
2026-078.9%439
2026-085.8%620
2026-0913.1%191

Peak month: 30%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Cursor AgentAnysphere2577.7%
Claude CodeAnthropic1464.4%
GitHub CopilotGitHub391.2%
OpenAI CodexOpenAI10%
Other / generic agentVarious10%

Inspect the matches

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

Matched commit samples

  • f18c59a6 on GitHubfeat(github): scan CI health across every repository in parallel (#6257)Cursor Agent
  • 4a726781 on GitHubrefactor(skills): rename CI fix skills to repair; 30-second CI repair loopCursor Agent
  • ecd20b78 on GitHubfeat(observability): add opt-in Langfuse tracing for turns, LLM calls and Cursor Agent
  • b5b5fbef on GitHubfix(github): address branch-mode review findings from Greptile (#5806 follClaude Code
  • 10d82169 on GitHubfeat(github): add branch mode to fix_github_pr_ci for direct-to-branch CI Claude Code
  • 429bd226 on GitHubrefactor(lambda_client): remove redundant comments (#5703)Claude Code
  • 0c12230f on GitHubdocs: document /remote-sync and remote sync env vars (#4985)GitHub Copilot
  • 012ffd2c on GitHubfeat(integrations): add Buzz (block/buzz) delivery integration (#4756)GitHub Copilot
  • 29fd02e0 on GitHubSM-50: Use HTTPStatus in delivery_transport — replace bare numeric status GitHub Copilot
  • 2892072c on GitHubfeat(scheduler): add scoped read-only GitHub CI health skill (#6015)OpenAI Codex
  • d97e6cbf on GitHubfix(wizard): update stale model lists for Anthropic, OpenAI, and OpenRouteOther / generic agent

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 window3,635
Merge commits removed−101
CI / dependency bots removed−201
Considered3,333

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

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 Tracer-Cloud/opensre

Scan another repository