Vector + Graph + Column StoreThe Agentic Memory
for Autonomous AI
The unified database combining vectors, knowledge graphs, and structured data. The cognitive backbone your AI agents need. Microsecond retrieval, VelesQL, zero cloud dependency.
Why Agents Need More Than Vector Search
AI agents need three types of memory: semantic (what feels similar), episodic (what is factually connected), and structured (explicit knowledge). Traditional databases can't provide all three unified.
Traditional Vector DBs
- Vectors only, no relationships
Can't model factual connections
- 50-100ms latency per query
Network round-trips add up fast
- No offline, no data sovereignty
Your data on someone else's servers
VelesDB Agentic Memory
- Vector + Graph + Columns unified
Complete memory for AI agents
- 57µs search latency (10K)
1000x faster than cloud alternatives
- Runs anywhere, works offline
Server, Browser, Mobile — your data stays local
| Metric | VelesDB | Cloud Vector DBs |
|---|---|---|
| Search Latency (10K) | 57µs | 50-100ms |
| 10 Retrievals | 1.3ms total | 500ms-1s total |
| Time to First Token | Instant | Noticeable delay |
Features
The complete memory system for autonomous AI agents
Semantic Memory (Vectors)
HNSW index with SIMD acceleration. What your agent perceives as similar. Multi-Query Fusion with RRF, Average, Maximum strategies.
Episodic Memory (Graph)
Native Knowledge Graph with nodes, edges, and the MATCH clause. What your agent knows is factually connected.
VelesQL - SQL + NEAR + MATCH
Unified query language for vectors (NEAR), graphs (MATCH), and structured data. No JSON DSL to learn.
Hybrid Search
Combine BM25 full-text, vector similarity, and graph traversal in a single query. Trigram Index 22-128x faster.
SIMD + GPU Ready
AVX-512/AVX2/NEON auto-detection. 35ns dot product for 768D. GPU acceleration via wgpu.
Run Anywhere
Server, CLI, Python, TypeScript, WASM, iOS, Android, Tauri. Same core, same performance.
Metadata-Only Collections
Lightweight collections without vectors for catalogs, configs, or text-only search. Memory efficient.
Advanced Quantization
SQ8 (4x compression, <2% recall loss) + Binary (32x compression). Dictionary Encoder for strings.
SIMD Performance (1536D Vectors)
HNSW Recall Profiles (10K/128D)
| Mode | ef_search | Recall@10 | Latency P50 | vs v1.0 |
|---|---|---|---|---|
| Fast | 64 | 92.2% | 36µs | NEW |
| Balanced | 128 | 98.8% | 57µs | -80% |
| Accurate | 256 | 100% | 130µs | -72% |
| Perfect | 2048 | 100% | 200µs | -92% |
Native Rust benchmarks (no HTTP overhead). Run your own: cargo bench
Use Cases
The cognitive backbone for autonomous AI
Agentic Memory
Complete memory system for autonomous agents: semantic (vectors), episodic (graph), and structured data in one unified store.
-- Agentic Memory: Vector + Graph unified
SELECT * FROM memories
WHERE vector NEAR $embedding
AND MATCH (a)-[:KNOWS]->(b)
LIMIT 10;GraphRAG
Combine knowledge graph traversal with vector similarity for superior context retrieval. MATCH + NEAR in one query.
-- GraphRAG: MATCH + NEAR in one query
SELECT doc.*, similarity()
FROM documents doc
WHERE vector NEAR $query
AND MATCH (doc)-[:CITES]->(ref)
ORDER BY similarity() DESC;AI Desktop Apps
Build offline-capable AI applications with Tauri or Electron. Single binary, no server needed.
const results = await invoke('plugin:velesdb|search', {
collection: 'memories',
vector: embedding,
topK: 10
});Browser Vector Search
Run vector search directly in the browser with WASM. Privacy-first, no backend required.
import { VectorStore } from 'velesdb-wasm';
const store = new VectorStore(768, 'cosine');
const results = store.search(query_vector, 10);Mobile AI (iOS/Android)
Native SDKs for mobile with 32x memory compression via Binary Quantization.
let db = VelesDatabase.open("./agent_memory")
let results = collection.search(embedding, topK: 10)Robotics & Autonomous Systems
Microsecond decision-making for real-time autonomous systems. Knowledge graph for world modeling.
// <100µs latency for real-time decisions
let context = memory.search(sensor_embedding, 5);
let world_model = graph.traverse(current_node);On-Premises / Air-Gapped
Full data sovereignty for regulated industries. GDPR, HIPAA, PCI-DSS ready.
./velesdb-server --data-dir /secure/vectors --bind 127.0.0.1:8080Multi-Agent Collaboration
CRDT-based memory synchronization for collaborative AI systems. Local-first, conflict-free merge.
// CRDT sync for collaborative agent memory (Premium)
await sync.connect_peer("agent_b_address");
agent_a.memory.sync();Comparison
The only database with Vector + Graph + Columns
Looking for Agentic Memory?
| Feature | 🐺VelesDB | Qdrant | Milvus | Pinecone | pgvector |
|---|---|---|---|---|---|
| Architecture | Single Binary | Container | Cluster | SaaS | Postgres Ext |
| Search Latency (10K) | 57µs | ~30ms | ~20ms | ~50ms | ~50ms |
| Knowledge Graph | Native MATCH | None | None | None | None |
| Setup Time | < 1 min | 5-10 min | 30+ min | 5 min | 15+ min |
| Binary Size | 15 MB | 100+ MB | GBs | N/A | Extension |
| Query Language | SQL (VelesQL) | JSON DSL | SDK | SDK | SQL |
| WASM/Browser | |||||
| Mobile SDK | |||||
| License | ELv2 | Apache 2.0 | Apache 2.0 | Closed | PostgreSQL |
Why VelesDB for Agentic Memory
Get Started in 60 Seconds
Download, install, and run. No complex setup, no dependencies, no cloud accounts required.
cargo add velesdb-coreQuick Example
velesdb-server --data-dir ./my_datacurl -X POST localhost:8080/collections \
-d '{"name":"agent_memory","dimension":768,"metric":"cosine","graph":true}'curl -X POST localhost:8080/query \
-d '{"query":"SELECT * FROM agent_memory WHERE vector NEAR $v AND MATCH (a)-[:KNOWS]->(b) LIMIT 10"}'Join developers building autonomous AI with VelesDB's unified Vector + Graph + Column store
Join developers building autonomous AI with VelesDB's unified Vector + Graph + Column store