Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.
Assisted or autonomous
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
Peak month: 34.8%. Bars are scaled to that peak, not to 100%.
Which agents
| Claude Code | Anthropic | 1176 | 13.4% |
| Cursor Agent | Anysphere | 460 | 5.2% |
| Devin | Cognition | 308 | 3.5% |
| GitHub Copilot | GitHub | 26 | 0.3% |
| OpenAI Codex | OpenAI | 7 | 0.1% |
| Other / generic agent | Various | 5 | 0.1% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
f9704497feat(helm): add startupProbe and hpa.behavior to the componentized chart (Claude Codeadd095b4Fix: ComplexityRouter should not score system prompt text for code/technicClaude Code1911269dfix(router): never price a strategy-router alias (#36691)Claude Coded30e933eci: wire credential_endpoints tests into the proxy endpoints job (#36187)Cursor Agentb792fd7ctest(router): cover PatternMatchRouter.remove_deployment for router code cCursor Agent836bf080fix(router): keep team wildcard routers fresh and prioritize them over gloCursor Agent1abde192docs(claude): require ReadOnly on every TypedDict field (LIT012)Devin6e7984e5fix(proxy): requeue spend logs when the DB write fails with a transport erDevine46f2ca6fix(dashscope): honor the model reasoning rate when a tier omits output raDevin5677bc23fix(proxy/batches): resolve managed unified input_file_id to storage_url wGitHub Copilot0a17c7c3feat: add LiteLLM Rust workspace with Mistral OCR bridge (#31033)GitHub Copilot1ccc1e5bchore: litellm oss staging160626 (#30527)GitHub Copilotb4a4277afix(ui): align spend and budget columns (#35176)OpenAI Codexcb888364Add incomplete response error propagation testOpenAI Codexbd5c39c4Log incomplete details in background streamingOpenAI Codexb84f7f82Litellm oss staging (#29492)Other / generic agente8fcb012Litellm OSS Staging (#29161)Other / generic agent58cd6f68test: fix misleading precedence test per review feedbackOther / generic agent
What was excluded
| Commits in window | 11,687 |
| Merge commits removed | −2,874 |
| CI / dependency bots removed | −17 |
| Considered | 8,796 |
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