Emmimal/context-graph-benchmark
A pure-Python structured memory benchmark for multi-agent LLM systems — context graph vs vector RAG vs raw history dump, five scenarios, 18 graded queries, zero API calls.
31
Stars
5
Forks
26.0
Radar Score
Stable
Momentum
Scoring Breakdown
Impact12.7
Velocity30.3
Health41.4
Growth Metrics
7-Day Stars
+0
30-Day Stars
+0
Acceleration
x
Language
Python