20.9%

of 11,162 commits were committed by an AI agent — a floor, not an estimate

20.9% agent · top contributor 17.2%132 contributors

org-wide

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

2,331

agent commits

8,831

human commits

132

agent contributors

17.2%

largest contributor

Assisted or autonomous

1924assisted

407autonomous

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: 34.5%. Bars are scaled to that peak, not to 100%.

Which agents

Claude Code	Anthropic	1207	10.8%
Devin	Cognition	687	6.2%
Cursor Agent	Anysphere	474	4.2%
GitHub Copilot	GitHub	26	0.2%
OpenAI Codex	OpenAI	22	0.2%
Other / generic agent	Various	5	0%

Verify it yourself

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

e058aa68test: add mistral ocr transformation parity coverage (#39482)Claude Code
fcc9b813fix(ui): resolve the preset catalog relative to the mock, not cwdClaude Code
099d2620fix(ui): read the preset catalog at runtime in the vitest mockClaude Code
291d02f8fix(mcp): never exchange the LiteLLM virtual key as the upstream subject tDevin
291e84e5feat(datadog_llm_obs): cost tag dimensions, router decision fields, reasonDevin
8065ede4test(guardrails): expect the deduped end-of-stream scan in crowdstrike cadDevin
ae83444afix(openai): treat empty api_key as unset for WIF resolutionCursor Agent
43c64e24fix(cli): keep an existing ENABLE_TOOL_SEARCH valueCursor Agent
096e016bfix(cli): sort claude_settings __all__ for ruff RUF022Cursor Agent
5677bc23fix(proxy/batches): resolve managed unified input_file_id to storage_url wGitHub Copilot
0a17c7c3feat: add LiteLLM Rust workspace with Mistral OCR bridge (#31033)GitHub Copilot
1ccc1e5bchore: litellm oss staging160626 (#30527)GitHub Copilot
cc400502fix(mcp): canonicalize bearer scheme on bridge egressOpenAI Codex
1a2a24ecchore(mcp): document mutable bridge header shapeOpenAI Codex
da036ad0fix(mcp): harden DCR bridge admissionOpenAI Codex
b84f7f82Litellm oss staging (#29492)Other / generic agent
e8fcb012Litellm OSS Staging (#29161)Other / generic agent
58cd6f68test: fix misleading precedence test per review feedbackOther / generic agent

What was excluded

Commits in window	15,036
Merge commits removed	−3,853
CI / dependency bots removed	−21
Considered	11,162

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 BerriAI/litellm

Scan another repository

Try