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.

Coding Agent singularly focused efficiency and context curation. Reduces API costs by 50-80% vs other agent AND improves the code quality at the same time. Uses Hash Anchored edits, massively parallel operations, AST manipulation and many many other optimizations. https://dirac.run/

01Result

dirac-run/dirac ↗

dirac-run/dirac AI coding statistics: 2.4%

of 862 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
2.4% agent · top contributor 57.1%4 contributors
team

A small group is using agents. Adoption has spread beyond one person but is not project-wide.

21
agent commits
841
other considered commits
4
agent contributors
57.1%
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

9assisted
12autonomous

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
2026-040%251
2026-055.3%94
2026-061.5%135
2026-070%133
2026-088.1%173
2026-090%76

Peak month: 8.1%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
DevinCognition161.9%
Claude CodeAnthropic50.6%

03Evidence

Inspect the matches

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

Matched commit samples

  • a32675a4 on GitHubFB-15a: split attemptApiRequest into TaskApiRequestAttempt.tsDevin
  • 00bd674d on GitHubFB-15a: extract attemptApiRequest and recursivelyMakeDiracRequests into TaDevin
  • ff7f3c41 on GitHubFB-15a: extract waitForFollowUp and submitCardResponse into TaskUserInput.Devin
  • 40e1e55e on GitHubfix(UIHelpers): don't forward undefined onlyPartial to removeLastPartialMeClaude Code
  • 5a893763 on GitHubtest(handlers): fix EditFile and RenameSymbol tool handler test configsClaude Code
  • c639367c on GitHubtest(providers): fix usage chunk tests after totalCost was added to usage Claude Code

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 window955
Merge commits removed−93
CI / dependency bots removed−0
Considered862

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 →Devin commitsBrowse repositories with detected Devin signatures →TypeScript AI coding statisticsCompare evidence across TypeScript 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 dirac-run/dirac

Scan another repository

Try