Python · MIT
hhy-huang/HiRAG
[EMNLP'25 findings] An easy-to-use Graph RAG system using hierarchical knowledge.
★ 555
Stars
81 forks · 3 open issues
flat
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
11.1
Momentum / 100
see the breakdown below
20mo ago
Created
last push 4mo ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 0.0 | flat, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | needs 7-day and 30-day rates side by side |
| Freshness | 15 | 3.2 | last push 4mo ago; decays to zero at 180 days |
| Scale | 15 | 8.0 | 555 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 11.1 | sum of the above |
Detail
| Topics | clusteringgraphraglarge-language-modelsnlpragretrieval-augmented-generation |
| Matched on | RAG (retrieval-augmented-generation) |
| Short window | +0 stars over 7 days = 0.0/day |
| Long window | +-2 stars over 26 days = -0.1/day |
| Lifetime average | 0.92 stars/day over 601 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |