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.

Build distributed, production-grade, long-running agents.

01Result

agentscope-ai/agentscope-java ↗

agentscope-ai/agentscope-java AI coding statistics: 2.3%

of 572 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
2.3% agent · top contributor 15.4%11 contributors
org-wide

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

13
agent commits
559
other considered commits
11
agent contributors
15.4%
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

13assisted
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
2026-0213.9%36
2026-035%60
2026-040%49
2026-051.5%66
2026-061.3%76
2026-070%112
2026-081.8%111
2026-091.6%62

Peak month: 13.9%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic61%
GitHub CopilotGitHub40.7%
Cursor AgentAnysphere30.5%

03Evidence

Inspect the matches

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

Matched commit samples

  • aaf7a843 on GitHubfix(model): preserve thought signatures across JSON persistence round-tripClaude Code
  • 9589b17c on GitHubfeat(skill): optimize code exec prompt and add e2e benchmark (#1056)Claude Code
  • 3246c932 on GitHubfix(mcp): preserve $defs and definitions fields in JsonSchema conversion Claude Code
  • a425660b on GitHubfix(agui): Suppress ReActAgent handshake events in AG-UI converters (#2639GitHub Copilot
  • 40e77c08 on GitHubfix(middleware): avoid event-loop blocking in WorkspaceContextMiddleware oGitHub Copilot
  • 5c8e9e10 on GitHubIntroduce agentscope-harness module (#1353)GitHub Copilot
  • a4c2f4f8 on GitHubchore(ci): bump skywalking-eyes to fix license job Go download (#1521)Cursor Agent
  • 97d931e9 on GitHubfeat(tool): add ToolSchemaModule to support @ToolParam parsing. (#783)Cursor Agent
  • 5037ed00 on GitHubfix(tool): preserve generic type info in ToolMethodInvoker (#730)Cursor Agent

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 window657
Merge commits removed−10
CI / dependency bots removed−75
Considered572

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 →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 agentscope-ai/agentscope-java

Scan another repository

Try