- Dataset
- 2026-10-27-catalog-ai-v2
- Ruleset
- b2e8889c66f7
- Scanned
- 2026-10-27
- Window
- February–September 15, 2026
An open, programmable decision layer for models and compute.
01Result
vllm-project/semantic-router ↗vllm-project/semantic-router AI coding statistics: 3.3%
Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.
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 |
|---|---|---|
| 2026-02 | 4.5% | 110 |
| 2026-03 | 0.6% | 161 |
| 2026-04 | 3.4% | 119 |
| 2026-05 | 1.3% | 78 |
| 2026-06 | 0.6% | 155 |
| 2026-07 | 7.5% | 147 |
| 2026-08 | 3.2% | 185 |
| 2026-09 | 4.5% | 224 |
Peak month: 7.5%. Bars are scaled to that peak, not to 100%.
Which agents
| Agent | Vendor | Commits | Share |
|---|---|---|---|
| Cursor Agent | Anysphere | 22 | 1.9% |
| Claude Code | Anthropic | 12 | 1% |
| GitHub Copilot | GitHub | 5 | 0.4% |
03Evidence
Inspect the matches
Public commit samples let you inspect the signatures behind the aggregate result.
Matched commit samples
60c7b8b7on GitHub[Router] add cross-model KV transfer wire headers (#2976) (#3770)Cursor Agentcd250d0eon GitHub[Docs] Add community.vllm-sr.ai link and Slack hyperlink to README (#3440)Cursor Agent5658f7f9on GitHub[Docs] Add agent-based routing proposal for Epic #2994 (#3098)Cursor Agent070ab460on GitHubRegister llm/sequence classifier tests in the PR-lane CI test list. (#3731Claude Codeb1d1ebc3on GitHub[Test] Add E2E coverage for the reask signal (#3653)Claude Codebc2556b9on GitHub[Test] Add E2E coverage for the language signal (#3507)Claude Codef0503475on GitHubtest(e2e): cover request mutation plugins (#3649)GitHub Copilota9e28e1bon GitHubResolves #2062: bug: flaky memory-test-integration (#2072)GitHub Copilot9fc22aa2on GitHubctx chainGitHub Copilot
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 | 1,246 |
| Merge commits removed | −54 |
| CI / dependency bots removed | −13 |
| Considered | 1,179 |
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 vllm-project/semantic-router