arriadne 0.1.3

AI agent memory system — sub-millisecond hybrid search (FAISS vector + FTS5 keyword + RRF fusion), knowledge graph traversal, cognitive retention modeling, and auto-deduplication. Zero infrastructure.

Ariadne

Memory for AI agents. Sub-millisecond search. Zero infrastructure.

---

Quick Start

from arriadne import AriadneMemory

mem = AriadneMemory(db_path="memory.db", embedding_dim=384)

mem.remember("VPS has 4 cores, 8GB RAM", importance=0.8)

results = mem.recall("server specs", k=5)

pip install arriadne

---

Why

	Ariadne	Mnemosyne	Mem0	ChromaDB
Vector search	0.89ms	153ms	12ms	8ms
Hybrid search	✅ RRF	❌	❌	⚠️ basic
Knowledge graph	✅ BFS	⚠️ basic	❌	❌
Auto-dedup	✅ MinHash	❌	❌	❌
Runs locally	✅	✅	❌	✅
No daemon	✅	✅	❌	❌

---

Features

0.89ms Vector Search

FAISS-powered. 12× faster than sqlite-vec. Auto-upgrades from exact to approximate search as your data grows.

Engine	10K vectors
FAISS (Ariadne)	0.89ms
sqlite-vec	10.5ms

Hybrid Retrieval

Vector similarity + BM25 keywords + graph traversal, fused with Reciprocal Rank Fusion. 90%+ recall@10 (with semantic embeddings).

results = mem.recall("how to deploy to production", k=5)
# Searches both "deploy" (keyword) and semantic similarity in parallel

Knowledge Graph

Typed entities and relationships with multi-hop traversal via SQLite recursive CTEs:

mem.add_edge("WebApp", "API", edge_type="depends_on")
mem.add_edge("API", "Database", edge_type="depends_on")
mem.graph("WebApp", hops=2)  # → [API, Database]

Cognitive Retention

Ebbinghaus forgetting curve with stability growth on each access. Priority-weighted scoring from importance, recency, and access count. Memories strengthen with use, fade without it.

Auto-Deduplication

MinHash LSH catches near-duplicates at 1.25ms before they enter the system.

---

Performance

Benchmarked on a 4-core 8GB VPS, 10K memories, 384-dim embeddings:

Operation	Latency
Vector search (FAISS)	0.89ms
Keyword search (FTS5)	1.74ms
Hybrid search (RRF)	2.46ms
Dedup check (MinHash)	1.25ms
	Memory insert
Graph traversal (3 hops)	0.06ms

---

Hermes Agent Integration

Ariadne works as a drop-in memory provider for Hermes Agent.

# Copy plugin
git clone https://github.com/kyssta-exe/Ariadne.git /tmp/ariadne-repo
cp -r /tmp/ariadne-repo/plugin ~/.hermes/plugins/ariadne

# Switch provider
hermes config set memory.provider ariadne
hermes restart

Full guide: ariadne.mantes.net/guide/hermes

---

Configuration

from arriadne import AriadneConfig, AriadneMemory

config = AriadneConfig(
    db_path="memory.db",
    embedding_dim=384,
    faiss_type="auto",          # auto | flat_ip | ivf_flat
    dedup_threshold=0.8,
    retention_half_life=86400,  # 1 day
)

mem = AriadneMemory(config=config)

---

Documentation

ariadne.mantes.net

• Quick Start
• Installation
• Hermes Setup
• Search & Retrieval
• Knowledge Graph
• API Reference
• Benchmarks

---

License

MIT — see LICENSE.

---

_{Powered by Mantes}