- Dataset
- 2026-10-27-catalog-ai-v2
- Ruleset
- b2e8889c66f7
- Scanned
- 2026-10-27
- Window
- February–September 15, 2026
Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.
01Result
kvcache-ai/Mooncake ↗kvcache-ai/Mooncake AI coding statistics: 17.6%
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 | 14.1% | 78 |
| 2026-03 | 8.9% | 112 |
| 2026-04 | 16.9% | 118 |
| 2026-05 | 25.2% | 123 |
| 2026-06 | 25.8% | 209 |
| 2026-07 | 16.7% | 233 |
| 2026-08 | 15.7% | 274 |
| 2026-09 | 14.2% | 183 |
Peak month: 25.8%. Bars are scaled to that peak, not to 100%.
Which agents
| Agent | Vendor | Commits | Share |
|---|---|---|---|
| Claude Code | Anthropic | 138 | 10.4% |
| Cursor Agent | Anysphere | 42 | 3.2% |
| GitHub Copilot | GitHub | 33 | 2.5% |
| Gemini CLI | 25 | 1.9% | |
| OpenAI Codex | OpenAI | 4 | 0.3% |
03Evidence
Inspect the matches
Public commit samples let you inspect the signatures behind the aggregate result.
Matched commit samples
6c07cb78on GitHub[TENT] Export EGM host memory over multi-node NVLink (opt-in) (#3978)Claude Code715d1cfcon GitHub[Bugfix][TransferEngine] Prevent peer failures from latching RDMA contextsClaude Code345dc35don GitHubtest: migrate storage-tier RPC scenarios to the DSL (#3847)Claude Codecd71eeecon GitHub[Bugfix][Store] Properly enable O_DIRECT for OffsetAllocator vector I/O (#Cursor Agent38da7053on GitHub[Bugfix][Store] Set ACL context on DummyClient copy RPCs (#3998)Cursor Agentdb752df1on GitHub[TransferEngine] Enrich Ascend init and register-mem error logs with conteCursor Agentbb69438eon GitHub[Doc] Backport vLLM-style notes for large changes (#4032)GitHub Copilot0a09c221on GitHubdocs: update README AgentX news (#4011)GitHub Copilote389a850on GitHub[Bugfix][TransferEngine] Export the requested range for dma-buf registratiGitHub Copilot7192ff4fon GitHub[TE] Add host control fallback for IBGDA QP setup (#2867)Gemini CLIdf84a553on GitHub[wip] docs: add vLLM V1 MooncakeStore KV cache sharing benchmark (#2773)Gemini CLI0d7f0a02on GitHub[Bench] Enable replay speedup and multi-threading in SSD Benchmarking (#27Gemini CLI6bfdb18fon GitHub[Bugfix][TENT] Preserve ownership after failed memory free (#3582)OpenAI Codexf5433782on GitHubperf(store): batch io_uring bucket reads (#3488)OpenAI Codexf4e1de1con GitHubfix(store): reject cross-shard standby duplicates (#3527)OpenAI Codex
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 | 1,340 |
| Merge commits removed | −2 |
| CI / dependency bots removed | −8 |
| Considered | 1,330 |
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 kvcache-ai/Mooncake