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.

✨ The open-source multi-agent platform. Every agent gets its own computer, desktop, network, and long-term memory. You can bring your own key, or host your coding agent like Claude Code, Codex and so on.

01Result

felinics/Memoh ↗

felinics/Memoh AI coding statistics: 5.6%

of 1,364 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
5.6% agent · top contributor 47.4%12 contributors
org-wide

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

76
agent commits
1,288
other considered commits
12
agent contributors
47.4%
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

76assisted
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
2026-022.5%326
2026-030.4%228
2026-040%149
2026-050%140
2026-065.4%148
2026-074.7%129
2026-0820.2%124
2026-0923.3%120

Peak month: 23.3%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic564.1%
Cursor AgentAnysphere90.7%
GitHub CopilotGitHub60.4%
DevinCognition50.4%

03Evidence

Inspect the matches

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

Matched commit samples

  • bbb22093 on GitHubfix(web): 终态帧不能丢掉屏幕上那一轮的失败原因 (#1269)Claude Code
  • 270408ec on GitHubfeat(queue): steer 在认领时就拿到 turn 身份，不再等 step 落库 (#1267)Claude Code
  • 3a3bc812 on GitHubfix(chat): 工具输出入库前归一化 NUL 与非法 UTF-8 (#1255)Claude Code
  • 67c05ef2 on GitHubfeat(context): cross-stack lifecycle, budget, fallback, and ACP context inCursor Agent
  • dead2cdf on GitHubfix(agent): persist interrupted-turn marker, stop retry storms on timeout,Cursor Agent
  • a2343dfb on GitHubfeat: Component wall design system and chat rendering polish (#598)Cursor Agent
  • 2f301ff5 on GitHubUpdate internal/auth/jwt_test.goGitHub Copilot
  • 4d1ca633 on GitHubUpdate agent/src/index.tsGitHub Copilot
  • 3e3379a8 on GitHubUpdate agent/src/index.tsGitHub Copilot
  • da2a1648 on GitHubfeat: 工具状态标签中性化，edit/write 渲染为上下文 diff (#1217)Devin
  • d5621403 on GitHubfix(desktop): 旧版运行时双击 DMG 副本提示退出,不再静默原地运行 (#1219)Devin
  • 05b84913 on GitHubfix(web): shelve composer voice input until default transcription model (#Devin

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 window1,407
Merge commits removed−36
CI / dependency bots removed−7
Considered1,364

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 →Go AI coding statisticsCompare evidence across Go 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 felinics/Memoh

Scan another repository

Try