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.

Intel staging area for llvm.org contribution. Home for Intel LLVM-based projects.

01Result

intel/llvm ↗

intel/llvm AI coding statistics: 3.3%

of 31,247 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
3.3% agent · top contributor 35%149 contributors
org-wide

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

1,023
agent commits
30,224
other considered commits
149
agent contributors
35%
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

1023assisted
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.

Agent share by month

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-020.6%3657
2026-031.5%4342
2026-041.5%3993
2026-052.5%3701
2026-063.1%4188
2026-075.5%4730
2026-085.6%4203
2026-096.5%2433

Peak month: 6.5%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic9012.9%
Cursor AgentAnysphere710.2%
GitHub CopilotGitHub410.1%
OpenAI CodexOpenAI140%
Gemini CLIGoogle10%

03Evidence

Inspect the matches

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

Matched commit samples

  • 91c01ae8 on GitHub[SYCL][ESIMD] Fix leak of the demangler output buffer in `ESIMDRemoveHostCClaude Code
  • b6912258 on GitHubclang: Fix exception model flag tests if webassembly isn't build (#223770)Claude Code
  • a3d2f4b4 on GitHub[[mlir][linalg] Infer reduction-neutral padding values in rewriteAsPaddedOClaude Code
  • 90f36e05 on GitHub[OpenMP] Remove the LocationDescription constructor that dropped the locatCursor Agent
  • 092ac4c2 on GitHub[clang][OpenMP] Don't drop debug location when handing off to OMPIRBuilderCursor Agent
  • f276d8f0 on GitHub[OMPIRBuilder] Don't leak a foreign debug loc into the taskwait call (#222Cursor Agent
  • 32656805 on GitHub[SYCL] Add macro to disable SYCL's device copyability checks (#23102)GitHub Copilot
  • a812bebb on GitHubAdd test ioq operations ordering (#22740)GitHub Copilot
  • 3e0045a4 on GitHub[SYCL] Fix kernel range check for interop kernels (#23099)GitHub Copilot
  • b8c7806b on GitHub[Flang][OpenMP] Fix use_device_addr descriptor types (#222961)OpenAI Codex
  • d450ba4b on GitHub[AMDGPU] Improve handling of numRecords for make.buffer.rsrc (#213180)OpenAI Codex
  • fe1bfb32 on GitHub[SPIR-V] Lower nested aggregate insertvalue operands (#204239)OpenAI Codex
  • 4b5f5954 on GitHub[clang][docs] Add basic user documentation for Hardware-assisted AddressSaGemini CLI

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 window32,092
Merge commits removed−655
CI / dependency bots removed−190
Considered31,247

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 →Gemini CLI commitsBrowse repositories with detected Gemini CLI 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 intel/llvm

Scan another repository

Try