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.

Enterprise-grade, commercial-friendly agentic workflow platform for building next-generation SuperAgents.

01Result

iflytek/astron-agent ↗

iflytek/astron-agent AI coding statistics: 4.9%

of 466 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
4.9% agent · top contributor 43.5%8 contributors
team

A small group is using agents. Adoption has spread beyond one person but is not project-wide.

23
agent commits
443
other considered commits
8
agent contributors
43.5%
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

23assisted
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
2026-023.1%32
2026-033.3%122
2026-045.5%110
2026-050%58
2026-0616.9%71
2026-070%29
2026-080%41
2026-090%3

Peak month: 16.9%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic132.8%
GitHub CopilotGitHub51.1%
Gemini CLIGoogle51.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • 0517b36a on GitHubfix(agent-skills): update AgentToolCallbackResolverTest for new resolve APClaude Code
  • 11cc0793 on GitHubdocs: set CLAUDE.md heading to # CLAUDE.mdClaude Code
  • 09f126b8 on GitHubfix(agent-skills): dedup skillIds when building skill tool callbacksClaude Code
  • 72af72c9 on GitHubPotential fix for code scanning alert no. 54: Server-side request forgeryGitHub Copilot
  • 3ba637af on GitHubdocs: add open source workflows link to Chinese and English READMEs (#1130GitHub Copilot
  • e5078aa5 on GitHubdocs: add tutorial link to README and README-zh (#1127)GitHub Copilot
  • 14e3df7b on GitHubfix: resolve Python CI formatting failures and fix workflow unittest (#11Gemini CLI
  • 261d1364 on GitHubrefactor(console-backend): improve code quality and `make test-java` passeGemini CLI
  • 757325cd on GitHubApply suggestion from @gemini-code-assist[bot]Gemini CLI

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 window831
Merge commits removed−365
CI / dependency bots removed−0
Considered466

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 →Gemini CLI commitsBrowse repositories with detected Gemini CLI signatures →Java AI coding statisticsCompare evidence across Java 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 iflytek/astron-agent

Scan another repository

Try