FrameworksPreviewThis index is in active development: we are still adding agents, refining attribution signatures, and verifying data against sources. The date in the header is when key figures were last re-checked. Numbers can move as coverage improves.
Where each agent's work concentrates across the major frameworks.
22%
React draws the most agent work
Share of classified sampled volume across 22 frameworks
80%
Cursor leads Django
The strongest single-agent concentration
6.8%
Of sampled PRs matched a framework
The rest of the sample has no framework signal
Framework Tilt
Window: 2026-05-25 to 2026-06-14.
| React | 27% | 10% | 10% | 29% | 15% | 9% | 22% |
| Next.js | 35% | 17% | 6% | 16% | 18% | 9% | 13% |
| Flutter | 18% | 17% | 11% | 11% | 19% | 24% | 10% |
| Vue | 7% | 13% | 26% | 5% | 34% | 15% | 7% |
| Astro | 21% | 9% | 15% | 15% | 3% | 38% | 7% |
| Spring | 7% | 2% | 23% | 3% | 64% | 1% | 6% |
| .NET | 16% | 9% | 41% | 4% | 30% | 1% | 5% |
| FastAPI | 33% | 24% | 8% | 15% | 4% | 17% | 5% |
| React Native | 10% | 6% | 8% | 49% | 4% | 22% | 4% |
| Angular | 14% | 15% | 20% | 6% | 44% | 2% | 3% |
| Django | 8% | 4% | 3% | 80% | 5% | 0% | 3% |
| Svelte | 30% | 21% | 10% | 12% | 12% | 15% | 2% |
| Flask | 17% | 27% | 12% | 1% | 11% | 32% | 2% |
| Laravel | 21% | 33% | 13% | 14% | 1% | 17% | 2% |
| SwiftUI | 61% | 25% | 5% | 4% | 5% | 1% | 2% |
| Electron | 30% | 9% | 27% | 26% | 6% | 2% | 2% |
| Express/Nest | 24% | 6% | 19% | 22% | 12% | 18% | 1% |
| Nuxt | 24% | 2% | 14% | 0% | 61% | 0% | 1% |
| htmx | 30% | 46% | 6% | 0% | 0% | 18% | 1% |
| Streamlit | 6% | 6% | 40% | 29% | 15% | 4% | 1% |
| Rails | 37% | 7% | 24% | 20% | 12% | 0% | 1% |
| SvelteKit | 51% | 5% | 5% | 30% | 0% | 8% | 1% |
Cells are each agent's share of the framework's sampled agent PRs; Volume is the framework's share of all classified samples. Click a header to sort; hover a cell for the raw count. Equal-size samples per agent, so this is portfolio tilt, not market share.
Movers
2026-06-15 vs 2026-06-13Framework shares are portfolio tilt, not market share: every agent contributes an equal-size sample, so a small agent can lead a framework it focuses on. For market-share-style adoption with a true baseline, see Languages. Method details on the methodology page.