- Dataset
- 2026-10-27-catalog-ai-v2
- Ruleset
- b2e8889c66f7
- Scanned
- 2026-10-27
- Window
- February–September 15, 2026
an open-source alternative to the dots, bots and muses of the world, run an office of claude code/codex like agents on your laptop, sandboxes or anywhere, uses your existing subscriptions
01Result
HarnessMD/munder-difflin ↗HarnessMD/munder-difflin AI coding statistics: 68.9%
A small group is using agents. Adoption has spread beyond one person but is not project-wide.
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 |
|---|---|---|
| 2026-05 | 0% | 3 |
| 2026-06 | 72.5% | 418 |
| 2026-07 | 80% | 30 |
| 2026-08 | 66.6% | 398 |
| 2026-09 | 59.8% | 82 |
Peak month: 80%. Bars are scaled to that peak, not to 100%.
Which agents
| Agent | Vendor | Commits | Share |
|---|---|---|---|
| Claude Code | Anthropic | 635 | 68.2% |
| Cursor Agent | Anysphere | 6 | 0.6% |
03Evidence
Inspect the matches
Public commit samples let you inspect the signatures behind the aggregate result.
Matched commit samples
cb5543c8on GitHubblog: pin Your First Hour With Munder Difflin second in Start hereClaude Code5b867203on GitHubblog: Build Your Personal AGI on Your Computer Using Claude Code and MundeClaude Codee550ffa8on GitHubblog(mission): 3 new posts, run-20260914-2354Claude Code585c1cdbon GitHubfix(hive): keep hire role out of live status captionsCursor Agentee6efc55on GitHubfix(ui): stop live PTY status from overwriting agent descriptionCursor Agent6c932242on GitHubfix(provider): default Cursor CLI binary to cursor-agentCursor 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 | 1,231 |
| Merge commits removed | −269 |
| CI / dependency bots removed | −31 |
| Considered | 931 |
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 HarnessMD/munder-difflin