- Dataset
- 2026-10-27-catalog-ai-v2
- Ruleset
- b2e8889c66f7
- Scanned
- 2026-10-27
- Window
- February–September 15, 2026
A local-first desktop workspace for persistent AI teammates. Run Codex, Claude, and Grok with dedicated workspaces, task queues, file sharing, browser control, and agent-to-agent collaboration.
01Result
nightly-labs/openbot ↗nightly-labs/openbot AI coding statistics: 21.5%
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 |
|---|---|---|
| 2026-08 | 0% | 217 |
| 2026-09 | 37.3% | 295 |
Peak month: 37.3%. Bars are scaled to that peak, not to 100%.
Which agents
| Agent | Vendor | Commits | Share |
|---|---|---|---|
| Claude Code | Anthropic | 109 | 21.3% |
| Cursor Agent | Anysphere | 1 | 0.2% |
03Evidence
Inspect the matches
Public commit samples let you inspect the signatures behind the aggregate result.
Matched commit samples
c4213430on GitHubSeed a new dev profile, and give each OpenCode model its own efforts (#537Claude Codeed210661on GitHubSpeed up CI: vmThreads for the jsdom projects, and split the macOS Check jClaude Code06b7eba1on GitHubWrite only the streamed message on a delta flush (#534)Claude Code76d0829fon GitHubAgent Description -> Instructions + autogrow. (#262)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 | 516 |
| Merge commits removed | −1 |
| CI / dependency bots removed | −3 |
| Considered | 512 |
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 nightly-labs/openbot