- Dataset
- 2026-10-27-catalog-ai-v2
- Ruleset
- b2e8889c66f7
- Scanned
- 2026-10-27
- Window
- February–September 15, 2026
Google Flights MCP, CLI and Python Library
01Result
punitarani/fli ↗punitarani/fli AI coding statistics: 69.6%
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 | 57.9% | 19 |
| 2026-04 | 69.2% | 13 |
| 2026-05 | 75.7% | 37 |
Peak month: 75.7%. Bars are scaled to that peak, not to 100%.
Which agents
| Agent | Vendor | Commits | Share |
|---|---|---|---|
| Claude Code | Anthropic | 46 | 66.7% |
| Cursor Agent | Anysphere | 5 | 7.2% |
03Evidence
Inspect the matches
Public commit samples let you inspect the signatures behind the aggregate result.
Matched commit samples
121d34feon GitHubfeat(js): add Google Flights booking links to the TypeScript library (#191Claude Codedaf9e9a7on GitHubfeat: add per-flight booking deep-link URLs via tfs+tfu protobuf encoding Claude Code4942911bon GitHubdocs: add TypeScript docs/examples and reorganize by language (#186)Claude Code24305797on GitHubUpgrade FastMCP to 3.2 (#121)Cursor Agent29a18a22on GitHubParse returned flight currency (#78)Cursor Agentccf7ac9fon GitHubAdd JSON output format to CLI (#77)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 | 86 |
| Merge commits removed | −0 |
| CI / dependency bots removed | −17 |
| Considered | 69 |
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 punitarani/fli