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.

Not only memory but a full story

01Result

oceanbase/powercontext ↗

oceanbase/powercontext AI coding statistics: 4%

of 498 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
4% agent · top contributor 20%10 contributors
org-wide

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

20
agent commits
478
other considered commits
10
agent contributors
20%
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

20assisted
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
2026-020%15
2026-030%38
2026-0415.4%13
2026-056.7%15
2026-067.6%92
2026-076.3%64
2026-083.2%125
2026-091.5%136

Peak month: 15.4%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Cursor AgentAnysphere71.4%
Claude CodeAnthropic71.4%
GitHub CopilotGitHub61.2%

03Evidence

Inspect the matches

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

Matched commit samples

  • aa79087e on GitHubfeat(memory): implement RFC 0003 Memory layer (#14)Cursor Agent
  • 3f4fde40 on GitHubtest(storage): add issue #1093 filter key collision regression tests (#113Cursor Agent
  • b1930b6b on GitHubfix(storage): sanitize SQLite FTS5 queries for technical tokens (#1125)Cursor Agent
  • 8659e690 on GitHubfeat(rerank): add NVIDIA NIM rerank providerClaude Code
  • 9571f145 on GitHubfix(config): honor disabled graph store flag (#1130)Claude Code
  • 86eb92c8 on GitHubfix(claude-code-plugin): improve SETUP.md + fix Anthropic temperature/top_Claude Code
  • f03d870b on GitHubdocs: finalize documentation classification and reference guides (#1415)GitHub Copilot
  • 48df3688 on GitHubfix: doctor POWERCONTEXT_CLIENT_SERVER_URL invalid (#1434)GitHub Copilot
  • 8b8b7d23 on GitHubdocs: document reviewed Experience and Skill workflows (#1334)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 window569
Merge commits removed−41
CI / dependency bots removed−30
Considered498

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 →Python AI coding statisticsCompare evidence across Python 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 oceanbase/powercontext

Scan another repository

Try