GitHub Trending daily report · 2026-09-03
Period and coverage
2026-09-03 to 2026-09-03 · Asia/Shanghai. 1 saved daily snapshots, 19 unique repositories and 19 repository observations.
The recorded daily Star totals add up to 8,997. For multi-day periods this is the sum of the saved daily signals, not a measurement of net Stars gained between two exact timestamps. Only available snapshots are included.
Leading recorded signals
-
DietrichGebert/ponytail — 1,364 recorded daily Stars, best rank #3, present in 1 saved snapshot. Ponytail: A Claude Code Plugin that removes more code than it writes
-
mattpocock/skills — 1,272 recorded daily Stars, best rank #17, present in 1 saved snapshot. A collection of skills for AI coding agents
-
pacifio/atlas — 895 recorded daily Stars, best rank #9, present in 1 saved snapshot. Source control for coding agents
All projects in this period
| Project | Recorded daily Stars | Best rank | Snapshots |
|---|---|---|---|
| DietrichGebert/ponytail | 1,364 | 3 | 1 |
| mattpocock/skills | 1,272 | 17 | 1 |
| pacifio/atlas | 895 | 9 | 1 |
| debpalash/VoiceStudio | 834 | 4 | 1 |
| Imbad0202/academic-research-skills | 801 | 11 | 1 |
| Gitlawb/openclaude | 776 | 18 | 1 |
| firecrawl/pdf-inspector | 589 | 19 | 1 |
| NousResearch/hermes-agent | 529 | 7 | 1 |
| affaan-m/ECC | 516 | 12 | 1 |
| blader/humanizer | 366 | 15 | 1 |
| google-research/timesfm | 326 | 2 | 1 |
| JuliusBrussee/caveman | 234 | 16 | 1 |
| ChromeDevTools/chrome-devtools-mcp | 140 | 6 | 1 |
| sngyai/Sequoia-X | 138 | 5 | 1 |
| vercel-labs/portless | 69 | 14 | 1 |
| zyronon/TypeWords | 68 | 10 | 1 |
| superlinked/sie | 61 | 8 | 1 |
| protocolbuffers/protobuf | 16 | 13 | 1 |
| fmtlib/fmt | 3 | 1 | 1 |
Daily records
- 2026-09-03 — 19 projects, 8,997 daily Stars.
Reading the signals
Star counts and rank changes measure attention in the saved Trending observations, not software quality, security or suitability. A gap in this archive does not establish that a project left GitHub Trending. Follow the project details and official documentation to check requirements before choosing a tool.
This English report is generated from the same saved snapshots and reporting period as the Chinese edition. It is a data summary; the Chinese edition may also contain editorial interpretation. No missing observations or publication timestamps are invented.