- Dataset
- 2026-10-27-catalog-ai-v2
- Ruleset
- b2e8889c66f7
- Scanned
- 2026-10-27
- Window
- February–September 15, 2026
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.
01Result
chenhg5/cc-connect ↗chenhg5/cc-connect AI coding statistics: 63.9%
Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.
02Drivers
What shapes this result
Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.
Assisted or autonomous
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
| Month | Agent share | Considered commits |
|---|---|---|
| 2026-02 | 93.3% | 15 |
| 2026-03 | 67.3% | 489 |
| 2026-04 | 75.2% | 226 |
| 2026-05 | 51.1% | 174 |
| 2026-06 | 66.4% | 131 |
| 2026-07 | 52.5% | 40 |
| 2026-08 | 31.5% | 54 |
| 2026-09 | 0% | 8 |
Peak month: 93.3%. Bars are scaled to that peak, not to 100%.
Which agents
| Agent | Vendor | Commits | Share |
|---|---|---|---|
| Claude Code | Anthropic | 705 | 62% |
| Cursor Agent | Anysphere | 66 | 5.8% |
| Devin | Cognition | 3 | 0.3% |
| GitHub Copilot | GitHub | 2 | 0.2% |
03Evidence
Inspect the matches
Public commit samples let you inspect the signatures behind the aggregate result.
Matched commit samples
ea3fa4fbon GitHubfix(claudecode): bound session teardown — WaitDelay, kill retry, close/spaClaude Code9cb6d05con GitHubfix(pi): remove unused "os" import that breaks windows builds (#1738)Claude Code1ddbac04on GitHubfeat(kimi): native Kimi Code CLI dialect support (Fixes #1561) (#1564)Claude Code617dd9d6on GitHubfix(feishu): expand merge_forward content when quoting a replyCursor Agent80713167on GitHubdocs(changelog,readme): v1.5.1-beta.1Cursor Agent129753c0on GitHubFeature/feishu topic workspace isolation (#1551)Cursor Agentfcba1da9on GitHubfix(core/markdown_html): render inline formatting inside GFM table cells (Devinf0c4e933on GitHubfix(telegram): make HTML→plain-text fallback observable (#674)Devin1b8a0843on GitHubfeat(agent): add Devin CLI as a first-class agent (#672)Devin7b93b085on GitHubfeat(googlechat): add Google Chat platform adapter (#1424)GitHub Copilot80ce4a56on GitHubAdd `models` list to provider config for per-provider model selection via 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 | 1,248 |
| Merge commits removed | −111 |
| CI / dependency bots removed | −0 |
| Considered | 1,137 |
Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.
Continue exploring
Related coding-agent evidence
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