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.

The execution layer for AI agents. Act across more of your systems with precise controls: safer, faster and more efficient than MCP tools and gateways.

01Result

withcoral/coral ↗

withcoral/coral AI coding statistics: 3%

of 1,086 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
3% agent · top contributor 18.2%13 contributors
org-wide

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

33
agent commits
1,053
other considered commits
13
agent contributors
18.2%
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

32assisted
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
2026-047.9%189
2026-052.6%350
2026-065.2%134
2026-070.4%261
2026-080.7%143
2026-090%9

Peak month: 7.9%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic232.1%
Cursor AgentAnysphere60.6%
OpenAI CodexOpenAI30.3%
GitHub CopilotGitHub10.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • 0b928362 on GitHubfeat(search)!: return grouped catalog surfaces (#2041)Claude Code
  • 915c18bc on GitHubfix(app): unify Universal Search with runtime catalog (#1781)Claude Code
  • 69ca4342 on GitHubfeat(episode): bound the per-workspace log by bytes with oldest-out evictiClaude Code
  • 8c549f42 on GitHubfeat(sources/community/dodopayments): add Dodo Payments community source (Cursor Agent
  • 12d97fe4 on GitHubfeat(sources/community/helpscout): add Help Scout community source (#1120)Cursor Agent
  • 4cf3a9d3 on GitHubfeat(sources/community/gmail): add search function and message metadata (#Cursor Agent
  • 0207f57b on GitHubfix(ci): avoid persisted checkout credentials in release-please (#593)OpenAI Codex
  • e6a18a7e on GitHubfix(ci): avoid exposing skills write token during export (#592)OpenAI Codex
  • 9616f879 on GitHubfix(docs): correct How Coral works wording (#270)OpenAI Codex
  • 9af5382c on GitHubfix(spec): validate inner expr for base64_decode (#322)GitHub Copilot

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 window1,120
Merge commits removed−0
CI / dependency bots removed−34
Considered1,086

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 →Rust AI coding statisticsCompare evidence across Rust 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 withcoral/coral

Scan another repository

Try