- Dataset
- 2026-10-27-catalog-ai-v2
- Ruleset
- b2e8889c66f7
- Scanned
- 2026-10-27
- Window
- February–September 15, 2026
One brain, many harnesses. Portable .agent/ folder (memory + skills + protocols) that plugs into Claude Code, Cursor, Windsurf, OpenCode, OpenClaw, Hermes, or DIY Python — and keeps its knowledge when you switch.
01Result
codejunkie99/agentic-stack ↗codejunkie99/agentic-stack AI coding statistics: 3.1%
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 |
|---|---|---|
| 2026-04 | 3.7% | 109 |
| 2026-05 | 0% | 25 |
| 2026-07 | 0% | 15 |
| 2026-08 | 0% | 10 |
| 2026-09 | 50% | 2 |
Peak month: 50%. Bars are scaled to that peak, not to 100%.
Which agents
| Agent | Vendor | Commits | Share |
|---|---|---|---|
| Claude Code | Anthropic | 4 | 2.5% |
| Cursor Agent | Anysphere | 1 | 0.6% |
03Evidence
Inspect the matches
Public commit samples let you inspect the signatures behind the aggregate result.
Matched commit samples
1da6ae85on GitHubfeat: add FTS5 full-text search for memory retrievalClaude Code7c5925ccon GitHubdocs: add release badge and fix cron example for v0.3.0Claude Codecff0a288on GitHubchore: bump formula to v0.3.0Claude Code43b5db3eon GitHubAdd Fable 5.1 parent / Grok 4.6 subagent cavecrew stack for Cursor agents 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 window | 189 |
| Merge commits removed | −28 |
| CI / dependency bots removed | −0 |
| Considered | 161 |
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 codejunkie99/agentic-stack