Pulse
2026-09-18-v3.0
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.

Bridge Feishu/Lark to AI coding CLIs — Claude Code, Codex, Gemini, OpenCode… every DM, group or topic spawns its own live-streaming CLI session

01Result

deepcoldy/botmux ↗

deepcoldy/botmux AI coding statistics: 13%

of 2,944 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
13% agent · top contributor 15.6%68 contributors
org-wide

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

384
agent commits
2,560
other considered commits
68
agent contributors
15.6%
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

384assisted
0autonomous

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

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-030.8%262
2026-040%139
2026-057.9%444
2026-0610.3%677
2026-0713.3%744
2026-0824.8%499
2026-0930.2%179

Peak month: 30.2%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic33411.3%
Cursor AgentAnysphere511.7%
OpenAI CodexOpenAI40.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • e964808c on GitHubfeat(codex): 空闲会话自动升级 Codex 版本 (#1306)Claude Code
  • d7d38532 on GitHubfix(setup): 「选择已有应用」登录态失效可重新扫码，不再死循环 (#1392)Claude Code
  • c8344ab5 on GitHubfeat(groups): 支持按群配置新话题默认模型 (#1359)Claude Code
  • fed664e4 on GitHubchore(env): 新增 Cloud Agent 开发环境配置 (#1391)Cursor Agent
  • 12e6e1d8 on GitHubrefactor(session): 开场激活的分散串行化 fence 收进按 session 的命令队列（Stage 3） (#1308)Cursor Agent
  • b0046eaa on GitHubtest(session): 钉住白板绑定失败不写内存Cursor Agent
  • de3025f4 on GitHubfeat(codex-app): 增加独立 Chrome 浏览器桥接 (#1015)OpenAI Codex
  • 48a76d8b on GitHubfeat(dashboard): /dashboard 飞书卡片控制面板 (#263)OpenAI Codex
  • eec70376 on GitHubdocs(workflow): loop 设计稿收敛终稿（claude review 全合入）OpenAI Codex

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 window3,368
Merge commits removed−424
CI / dependency bots removed−0
Considered2,944

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 →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex signatures →TypeScript AI coding statisticsCompare evidence across TypeScript 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 deepcoldy/botmux

Scan another repository

Try