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.

AI conversations that actually remember. Never re-explain your project to your AI again. Join our Discord: https://discord.gg/tyvKNccgqN

01Result

basicmachines-co/basic-memory ↗

basicmachines-co/basic-memory AI coding statistics: 43.3%

of 1,024 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
43.3% agent · top contributor 60.7%15 contributors
team

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

443
agent commits
581
other considered commits
15
agent contributors
60.7%
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

442assisted
1autonomous

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
2026-010%2
2026-0274.3%101
2026-0369.5%59
2026-0426.7%45
2026-0533%91
2026-0641.2%102
2026-0732.8%137
2026-0836.2%246
2026-0945.2%241

Peak month: 74.3%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic43842.8%
Cursor AgentAnysphere50.5%

03Evidence

Inspect the matches

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

Matched commit samples

  • ae5520a6 on GitHubdocs(mcp): regenerate the search-notes man page for the projects parameterClaude Code
  • 5ab7f1fe on GitHubfeat(mcp): search all projects with one scoped query per databaseClaude Code
  • 06b5f935 on GitHubfeat(api): search an explicit set of projects with one query (#1567)Claude Code
  • 25732b2f on GitHubfix: return promoted default state from project create APICursor Agent
  • b92b0340 on GitHubfix: promote first project when config default is missing from DBCursor Agent
  • c7551273 on GitHubfix(cli): ignore CancelledError in background task done callback (#839) (#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 window1,034
Merge commits removed−7
CI / dependency bots removed−3
Considered1,024

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 →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 basicmachines-co/basic-memory

Scan another repository

Try