← the index
llvm/llvm-project
2.8%
of 29,639 commits were committed by an AI agent — a floor, not an estimate
2.8% agent · top contributor 43.2%126 contributors
org-wide

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

828
agent commits
28,811
human commits
126
agent contributors
43.2%
largest contributor

Assisted or autonomous

828assisted
0autonomous

Assisted — a developer’s identity authored the commit and the agent added itself as co-author. The agent ran git commit during a working session, with a person there. Autonomous — a bot identity is the author, no human in the loop. Across the whole index, 93.7% of agent commits are assisted.

Agent share by month

Feb26
Mar26
Apr26
May26
Jun26
Jul26
Aug26
Sep26

Peak month: 5.3%. Bars are scaled to that peak, not to 100%.

Which agents

Claude CodeAnthropic7312.5%
Cursor AgentAnysphere670.2%
GitHub CopilotGitHub170.1%
OpenAI CodexOpenAI140%
Gemini CLIGoogle10%

Verify it yourself

Sample commits that matched. Every one links to GitHub — check the trailers.

  • b6912258clang: Fix exception model flag tests if webassembly isn't build (#223770)Claude Code
  • a3d2f4b4[[mlir][linalg] Infer reduction-neutral padding values in rewriteAsPaddedOClaude Code
  • 88cab6bfRuntimeLibcallsEmitter: Let a consumer's own library variant beat its exclClaude Code
  • 90f36e05[OpenMP] Remove the LocationDescription constructor that dropped the locatCursor Agent
  • 092ac4c2[clang][OpenMP] Don't drop debug location when handing off to OMPIRBuilderCursor Agent
  • f276d8f0[OMPIRBuilder] Don't leak a foreign debug loc into the taskwait call (#222Cursor Agent
  • dc948be7[runtimes] Escape list separators when forwarding search paths (#216169)GitHub Copilot
  • ee1eab2a[clang] Update diagnostics to include matrices as accepted types (#201237)GitHub Copilot
  • bc97c56e[DirectX] Expand {u,s}mul.with.overflow in DXILIntrinsicExpansion (#207297GitHub Copilot
  • b8c7806b[Flang][OpenMP] Fix use_device_addr descriptor types (#222961)OpenAI Codex
  • d450ba4b[AMDGPU] Improve handling of numRecords for make.buffer.rsrc (#213180)OpenAI Codex
  • fe1bfb32[SPIR-V] Lower nested aggregate insertvalue operands (#204239)OpenAI Codex
  • 4b5f5954[clang][docs] Add basic user documentation for Hardware-assisted AddressSaGemini CLI

What was excluded

Commits in window29,820
Merge commits removed0
CI / dependency bots removed181
Considered29,639

Bots are excluded from the denominator entirely. Counting dependabot as “AI-written code” is the fastest way to produce a meaningless number.

How this was measured

Measured over February–August 2026, cloned directly. Detection is deterministic string matching against signatures agents write about themselves — no heuristics, no style analysis. Merge commits and CI bots are excluded from the denominator. The figure is a floor: squash merges strip trailers, so real usage is higher. Contributor counts are aggregate — no individual is named.

Run it yourself: npx qmmit-cli llvm/llvm-project

Scan another repository