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 local AI coding agents (Claude Code, Cursor, Gemini CLI, Codex) to messaging platforms (Feishu/Lark, DingTalk, Slack, Telegram, Discord, LINE, WeChat Work). Chat with your AI dev assistant from anywhere — no public IP required for most platforms.

chenhg5/cc-connect ↗

chenhg5/cc-connect AI coding statistics: 63.9%

of 1,137 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
63.9% agent · top contributor 35.6%85 contributors
org-wide

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

727
agent commits
410
other considered commits
85
agent contributors
35.6%
largest contributor

What shapes this result

Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.

Assisted or autonomous

727assisted
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
2026-0293.3%15
2026-0367.3%489
2026-0475.2%226
2026-0551.1%174
2026-0666.4%131
2026-0752.5%40
2026-0831.5%54
2026-090%8

Peak month: 93.3%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic70562%
Cursor AgentAnysphere665.8%
DevinCognition30.3%
GitHub CopilotGitHub20.2%

Inspect the matches

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

Matched commit samples

  • ea3fa4fb on GitHubfix(claudecode): bound session teardown — WaitDelay, kill retry, close/spaClaude Code
  • 9cb6d05c on GitHubfix(pi): remove unused "os" import that breaks windows builds (#1738)Claude Code
  • 1ddbac04 on GitHubfeat(kimi): native Kimi Code CLI dialect support (Fixes #1561) (#1564)Claude Code
  • 617dd9d6 on GitHubfix(feishu): expand merge_forward content when quoting a replyCursor Agent
  • 80713167 on GitHubdocs(changelog,readme): v1.5.1-beta.1Cursor Agent
  • 129753c0 on GitHubFeature/feishu topic workspace isolation (#1551)Cursor Agent
  • fcba1da9 on GitHubfix(core/markdown_html): render inline formatting inside GFM table cells (Devin
  • f0c4e933 on GitHubfix(telegram): make HTML→plain-text fallback observable (#674)Devin
  • 1b8a0843 on GitHubfeat(agent): add Devin CLI as a first-class agent (#672)Devin
  • 7b93b085 on GitHubfeat(googlechat): add Google Chat platform adapter (#1424)GitHub Copilot
  • 80ce4a56 on GitHubAdd `models` list to provider config for per-provider model selection via GitHub Copilot

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 window1,248
Merge commits removed−111
CI / dependency bots removed−0
Considered1,137

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

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 chenhg5/cc-connect

Scan another repository