quantum-memory-graph 0.2.0

Quantum-optimized knowledge graph memory for AI agents. Relationship-aware subgraph selection via QAOA.

Quantum Memory Graph ⚛️🧠

Relationship-aware memory for AI agents. Knowledge graphs + quantum-optimized subgraph selection.

Every memory system treats memories as independent documents — search, rank, stuff into context. But memories aren't independent. They have relationships. "The team chose React" becomes 10x more useful paired with "because of ecosystem maturity" and "FastAPI handles the backend."

Quantum Memory Graph maps these relationships, then uses QAOA to find the optimal combination of memories — not just the most relevant individuals, but the best connected subgraph that gives your agent maximum context.

Benchmarks

LongMemEval (ICLR 2025) — Industry Standard

500 questions across 53 conversation sessions. The gold standard for AI memory retrieval.

System	R@5	R@10	NDCG@10
MemPalace raw	96.6%	98.2%	88.9%
Quantum Memory Graph (bge-large)	95.9%	98.2%	94.0%
OMEGA	95.4%	—	—
Mastra OM	94.9%	—	—
Quantum Memory Graph (MiniLM, default)	93.4%	97.4%	90.8%

#2 in the world on retrieval. #1 on ranking quality (NDCG@10). Free. Open source.

Use model="BAAI/bge-large-en-v1.5" for high-accuracy mode.

MemCombine — Combination Recall (250 Scenarios)

Method	Coverage	Evidence Recall	F1	Perfect
Embedding Top-K	92.3%	93.9%	91.3%	181/250
Graph + QAOA	96.2%	97.7%	95.1%	212/250

Graph-aware quantum selection beats pure similarity by +3.8% on combination tasks.

Install

pip install quantum-memory-graph

Quick Start

from quantum_memory_graph import store, recall

# Store memories — automatically builds knowledge graph
store("Project Alpha uses React frontend with TypeScript.")
store("Project Alpha backend is FastAPI with PostgreSQL.")
store("FastAPI connects to PostgreSQL via SQLAlchemy ORM.")
store("React components use Material UI for styling.")
store("Team had pizza for lunch. Pepperoni was great.")

# Recall — graph traversal + QAOA finds the optimal combination
result = recall("What is Project Alpha's full tech stack?", K=4)

for memory in result["memories"]:
    print(f"  {memory['text']}")
    print(f"    Connected to {len(memory['connections'])} other selected memories")

Output: Returns React, FastAPI, PostgreSQL, and SQLAlchemy memories — connected, complete, no noise. The pizza memory is excluded because it has no graph connections to the tech stack cluster.

How It Works

Query: "What's the tech stack?"
        │
        ▼
┌─────────────────────┐
│  1. Graph Search     │  Embedding similarity + multi-hop traversal
│     Find neighbors   │  Discovers memories connected to relevant ones
└────────┬────────────┘
         │ 14 candidates
         ▼
┌─────────────────────┐
│  2. Subgraph Data    │  Extract adjacency matrix + relevance scores
│     Build problem    │  Encode relationships as optimization weights
└────────┬────────────┘
         │ NP-hard selection
         ▼
┌─────────────────────┐
│  3. QAOA Optimize    │  Quantum approximate optimization
│     Find best K      │  Maximizes: relevance + connectivity + coverage
└────────┬────────────┘
         │ K memories
         ▼
┌─────────────────────┐
│  4. Return with      │  Each memory includes its connections
│     relationships    │  to other selected memories
└─────────────────────┘

Why Quantum?

Optimal subgraph selection is NP-hard. Given N candidate memories, finding the best K that maximize relevance, connectivity, AND coverage has exponential classical complexity. QAOA provides polynomial-time approximate solutions that beat greedy heuristics — this is the one problem where quantum computing has a genuine algorithmic advantage over classical approaches.

Architecture

Three Layers

1. Knowledge Graph (graph.py) — Memories are nodes. Relationships are weighted edges based on:

   • Semantic similarity (embedding cosine distance)
   • Entity co-occurrence (shared people, projects, concepts)
   • Temporal proximity (memories close in time)
   • Source proximity (same conversation/document)

2. Subgraph Optimizer (subgraph_optimizer.py) — QAOA circuit that maximizes:

   • α × relevance (individual memory scores)
   • β × connectivity (edge weights within selected subgraph)
   • γ × coverage (topic diversity across selection)

3. Pipeline (pipeline.py) — Unified store() and recall() interface.

Optional: MemPalace Integration

Use MemPalace (MIT, by @bensig) as the storage/retrieval backend for 96.6% base retrieval quality:

from quantum_memory_graph.mempalace_bridge import store_memory, recall_memories

# MemPalace stores verbatim → ChromaDB retrieves candidates → QAOA selects optimal subgraph
result = recall_memories("What happened in the meeting?", K=5, use_qaoa=True)

API Server

pip install quantum-memory-graph[api]
python -m quantum_memory_graph.api

Endpoints:

• POST /store — Store a memory
• POST /recall — Graph + QAOA recall
• POST /store-batch — Batch store
• GET /stats — Graph statistics
• GET / — Health check

Advanced Usage

Custom Graph

from quantum_memory_graph import MemoryGraph, recall
from quantum_memory_graph.pipeline import set_graph

# Tune similarity threshold for edge creation
graph = MemoryGraph(similarity_threshold=0.25)
set_graph(graph)

# Store and recall as normal

Tune QAOA Parameters

result = recall(
    "query",
    K=5,
    alpha=0.4,       # Relevance weight
    beta_conn=0.35,   # Connectivity weight  
    gamma_cov=0.25,   # Coverage/diversity weight
    hops=3,           # Graph traversal depth
    top_seeds=7,      # Initial seed nodes
    max_candidates=14, # Max qubits for QAOA
)

Run MemCombine Benchmark

from benchmarks.memcombine import run_benchmark

def my_recall(memories, query, K):
    # Your recall implementation
    return selected_indices  # List[int]

results = run_benchmark(my_recall, K=5)
print(f"Coverage: {results['avg_coverage']*100:.1f}%")

IBM Quantum Hardware

For production workloads, run QAOA on real quantum hardware:

pip install quantum-memory-graph[ibm]
export IBM_QUANTUM_TOKEN=your_token

Validated on ibm_fez and ibm_kingston backends.

Requirements

• Python ≥ 3.9
• sentence-transformers
• networkx
• qiskit + qiskit-aer
• numpy

License

MIT License — Copyright 2026 Coinkong (Chef's Attraction)

Built with MemPalace by @bensig (MIT License). See THIRD-PARTY-LICENSES.

Links

• quantum-agent-memory — The QAOA optimization engine
• MemPalace — Storage and retrieval backend
• MemCombine Benchmark — Test memory combination quality