Dataset: 2026-09-18-v3.0
Ruleset: b2e8889c66f7
Scanned: 2026-09-16
Window: February–September 15, 2026

Local to this browser

01Result

BerriAI/litellm ↗

BerriAI/litellm AI coding statistics: 23.2%

of 13,360 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

23.2% agent · top contributor 13%143 contributors

org-wide

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

3,096

agent commits

10,264

other considered commits

143

agent contributors

13%

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

2497assisted

599autonomous

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. Across the whole index, 96% of agent commits are assisted.

Agent share by month

Agent-attributed commit share by month
Month	Agent share	Considered commits
2026-01	13.6%	22
2026-02	18.2%	1925
2026-03	32.5%	1826
2026-04	12.4%	1450
2026-05	34.5%	730
2026-06	22.8%	596
2026-07	18.7%	1529
2026-08	15.7%	2929
2026-09	35.4%	2353

Peak month: 35.4%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Devin	Cognition	1377	10.3%
Claude Code	Anthropic	1260	9.4%
Cursor Agent	Anysphere	499	3.7%
GitHub Copilot	GitHub	26	0.2%
OpenAI Codex	OpenAI	22	0.2%
Other / generic agent	Various	5	0%

03Evidence

Inspect the matches

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

Matched commit samples

65f9d9bb on GitHubtest(proxy): use the module-level HTTPException import in the /nvidia_nim Devin
c9dd4b44 on GitHubrevert(model_info): keep Gemini baseline majors single-digitDevin
945adfb6 on GitHubrefactor(model_info): support multi-digit Gemini majorsDevin
501be314 on GitHubfix(proxy): enforce organization budgets when max_budget is 0Claude Code
eddfb5fb on GitHubfix(responses): preserve hosted web search calls (#40828)Claude Code
55c5babb on GitHubdocs(pr-template): fold assumptions guidance into Caveats instructionsClaude Code
f4e21430 on GitHubtest(auth): freeze prefetch cache clock so the org getter cannot miss on aCursor Agent
75b16df6 on GitHubfix(auth): keep prefetched org entries on the 5s getter TTLCursor Agent
abaa2f8b on GitHubfix(auth): put TQ008 suppressions on the patch call linesCursor Agent
5677bc23 on GitHubfix(proxy/batches): resolve managed unified input_file_id to storage_url wGitHub Copilot
0a17c7c3 on GitHubfeat: add LiteLLM Rust workspace with Mistral OCR bridge (#31033)GitHub Copilot
1ccc1e5b on GitHubchore: litellm oss staging160626 (#30527)GitHub Copilot
cc400502 on GitHubfix(mcp): canonicalize bearer scheme on bridge egressOpenAI Codex
1a2a24ec on GitHubchore(mcp): document mutable bridge header shapeOpenAI Codex
da036ad0 on GitHubfix(mcp): harden DCR bridge admissionOpenAI Codex
b84f7f82 on GitHubLitellm oss staging (#29492)Other / generic agent
e8fcb012 on GitHubLitellm OSS Staging (#29161)Other / generic agent
58cd6f68 on GitHubtest: fix misleading precedence test per review feedbackOther / generic agent

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 window	18,090
Merge commits removed	−4,704
CI / dependency bots removed	−26
Considered	13,360

Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.

05Provenance

Pinned to a source state

This observation names the repository state, release, and detector that produced it. Use these identifiers when reproducing or citing the result.

Dataset release: 2026-09-18-v3.0
Scan date: 2026-09-16
Ruleset: sha256:b2e8889c66f72c18a61839f0bf1a9f77b5481ba2def044dba33c797b2f2bdcae
Canonical repository: BerriAI/litellm
Default branch: main
Resolved HEAD: a8979fe05466346d78ab4573c8a61b53a4dd9cf6 ↗
Resolved: 2026-09-16
Measurement window: February–September 15, 2026

Download observation JSONDeterministic export · same values as this page

06Peer context

Position among comparable repositories

The cohort uses the same release and measurement window, then narrows to the repository’s ecosystem and removes low-activity observations.

CohortPython · 247 eligible repositories · at least 100 considered commits2026-09-18-v3.0 · February–September 15, 2026 · 145 of 392 ecosystem repositories excluded

Agent-commit share position80th percentile

Midrank percentile; equal shares split the tied positions.

Repository: 23.2%
Cohort median: 6.3%
Share rank: 50 / 247

0th50th100th

Percentile = (repositories below + half of 1 tied repository) ÷ 247.

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 →Devin commitsBrowse repositories with detected Devin signatures →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex 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 BerriAI/litellm

Scan another repository

Try