Go · MIT
Siddhant-K-code/distill
Context intelligence layer for LLM agents: persistent memory with write-time dedup, sensitivity tagging, conflict detection, and hierarchical decay. ~12ms. No LLM calls. MIT.
★ 199
Stars
20 forks · 4 open issues
+2.0/wk
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
35.8
Momentum / 100
see the breakdown below
10mo ago
Created
last push 38d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 2.1 | +2.0/wk, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 15.0 | last week ran 2.48× the monthly pace |
| Freshness | 15 | 12.0 | last push 38d ago; decays to zero at 180 days |
| Scale | 15 | 6.7 | 199 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 35.8 | sum of the above |
Detail
| Topics | ai-agentsanthropiccompressioncontext-optimizationdeduplicationdeterministicdeveloper-toolsgogolangllmopenaipineconeprompt-cachingqdrantragvector-database |
| Matched on | RAG (vector-database) |
| Short window | +2 stars over 7 days = 0.3/day |
| Long window | +3 stars over 26 days = 0.1/day |
| Lifetime average | 0.64 stars/day over 309 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |