- Dataset
- 2026-10-27-catalog-ai-v2
- Ruleset
- b2e8889c66f7
- Scanned
- 2026-10-27
- Window
- February–September 15, 2026
Portable project memory across Claude Code, Codex and OpenCode, plus token accounting measured from harness transcripts. Local file I/O, no API calls, no telemetry.
01Result
cytostack/openwolf ↗cytostack/openwolf AI coding statistics: 30.3%
One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.
02Drivers
What shapes this result
Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.
Assisted or autonomous
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
| Month | Agent share | Considered commits |
|---|---|---|
| 2026-03 | 0% | 20 |
| 2026-04 | 25% | 4 |
| 2026-05 | 20% | 5 |
| 2026-06 | 0% | 2 |
| 2026-07 | 10.3% | 29 |
| 2026-08 | 73.7% | 38 |
| 2026-09 | 0% | 11 |
Peak month: 73.7%. Bars are scaled to that peak, not to 100%.
Which agents
| Agent | Vendor | Commits | Share |
|---|---|---|---|
| Claude Code | Anthropic | 33 | 30.3% |
03Evidence
Inspect the matches
Public commit samples let you inspect the signatures behind the aggregate result.
Matched commit samples
12c21b59on GitHubdocs(2.5): retire "second brain", lead with portable project memoryClaude Code4b06864don GitHubfeat(2.5): no model calls, working Windows hooks, cost on the dashboardClaude Code16d63bb9on GitHubdocs: one wordClaude Code
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 window | 123 |
| Merge commits removed | −14 |
| CI / dependency bots removed | −0 |
| Considered | 109 |
Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.
Continue exploring
Related coding-agent evidence
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 cytostack/openwolf