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.

Koka language compiler and interpreter

koka-lang/koka ↗

koka-lang/koka AI coding statistics: 8%

of 175 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
8% agent · top contributor 92.9%2 contributors
individual

One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.

14
agent commits
161
other considered commits
2
agent contributors
92.9%
largest contributor

What shapes this result

Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.

Assisted or autonomous

14assisted
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%4
2026-035.7%53
2026-040%14
2026-056%50
2026-060%36
2026-0763.6%11
2026-0814.3%7

Peak month: 63.6%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic137.4%
GitHub CopilotGitHub10.6%

Inspect the matches

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

Matched commit samples

  • 9b82368b on GitHubCore: fix type synonyms used only in inline-exposed nested binders (#923)Claude Code
  • 78a663fb on GitHubcore: serialize constructor-context paths in interface filesClaude Code
  • 24e09f90 on GitHubparc: keep match-guard free variables live (fixes use-after-free) (#920)Claude Code
  • dcdf656b on GitHubdocs: add profiling section to readmeGitHub Copilot

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 window185
Merge commits removed−10
CI / dependency bots removed−0
Considered175

Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.

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 koka-lang/koka

Scan another repository