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.

Memory library for building stateful agents

01Result

plastic-labs/honcho ↗

plastic-labs/honcho AI coding statistics: 30.8%

of 312 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
30.8% agent · top contributor 27.1%24 contributors
org-wide

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

96
agent commits
216
other considered commits
24
agent contributors
27.1%
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

96assisted
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
2026-0210.5%38
2026-0319%21
2026-046.7%45
2026-0514.3%21
2026-0638.7%31
2026-0729.4%34
2026-0843.1%72
2026-0958%50

Peak month: 58%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic8828.2%
Cursor AgentAnysphere103.2%

03Evidence

Inspect the matches

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

Matched commit samples

  • e5bbebdf on GitHubfeat: exposing conclusion attribution (source & times derived) (#952)Claude Code
  • 09421ddd on GitHubfix(llm): surface provider outages as 503 instead of 500 (#1165)Claude Code
  • 9b5eab55 on GitHubfix(harness-plugin-core): ship a compiled dist/ so the package loads underClaude Code
  • e5bbebdf on GitHubfeat: exposing conclusion attribution (source & times derived) (#952)Cursor Agent
  • 9523172d on GitHubfeat(cli): add --scope and --sessions recall bounds on chat (#1151)Cursor Agent
  • 8341bb67 on GitHubfeat(mcp): identify MCP API traffic with X-Honcho-Host and X-Honcho-PluginCursor 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 window322
Merge commits removed−10
CI / dependency bots removed−0
Considered312

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 plastic-labs/honcho

Scan another repository

Try