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.

A framework for building realtime voice AI agents 🤖🎙️📹

01Result

livekit/agents ↗

livekit/agents AI coding statistics: 12.8%

of 1,170 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

12.8% agent · top contributor 13.3%73 contributors

org-wide

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

150

agent commits

1,020

other considered commits

agent contributors

13.3%

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

149assisted

1autonomous

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

Peak month: 18.6%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	109	9.3%
Devin	Cognition	28	2.4%
Cursor Agent	Anysphere	16	1.4%
GitHub Copilot	GitHub	3	0.3%

03Evidence

Inspect the matches

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

Matched commit samples

f82ba1eb on GitHubfeat(elevenlabs): secondary languages and language detection for realtime Claude Code
34a4e8f5 on GitHubtests: trace-shape schema and checker (#7148)Claude Code
83367a5b on GitHubfeat(telemetry): one agent_turn span per speech handle (#7143)Claude Code
6835d4cd on GitHubfeat: add openai gpt-live duplex support (#7212)Devin
13d92ff6 on GitHubAdd Palabra STT and TTS plugins (#6681)Devin
c45cb2b7 on GitHubfeat(sarvam): add realtime streaming STT (#6562)Devin
85381a0e on GitHubfeat: add Vakyam TTS plugin (#7009)Cursor Agent
1c472dd2 on GitHubfix(aws): import AsyncBedrockRuntimeClient for bedrock-runtime 0.10+ (#700Cursor Agent
e687cc23 on GitHubfix: attribute playback evidence to its own segment on the same audio outpCursor Agent
b110c91c on GitHubfix(workflows): return corrective instructions as tool output instead of gGitHub Copilot
f3cbd00d on GitHubfix: prevent _cancel_speech_pause from poisoning subsequent user turns (#5GitHub Copilot
8343db12 on GitHubfix(anthropic): add dummy user message for Claude 4.6+ trailing assistant GitHub Copilot

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	1,243
Merge commits removed	−0
CI / dependency bots removed	−73
Considered	1,170

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 →Devin commitsBrowse repositories with detected Devin signatures →Python AI coding statisticsCompare evidence across Python repositories →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 livekit/agents

Scan another repository

Try

Month	Agent share	Considered commits
2026-01	0%	1
2026-02	2.1%	143
2026-03	12.8%	149
2026-04	12.3%	154
2026-05	7.2%	153
2026-06	16.9%	142
2026-07	16%	163
2026-08	17.9%	168
2026-09	18.6%	97