-
-
Notifications
You must be signed in to change notification settings - Fork 0
Home
github-actions[bot] edited this page Jun 2, 2026
·
11 revisions
The Zero-Overhead, Agent-Ready AI Memory Backbone.
Welcome to the Spector documentation — your central hub for the high-performance, agent-native AI search engine. Whether you're connecting AI agents via MCP, building RAG pipelines, powering recommendation systems, or need sub-millisecond search with zero infrastructure, you're in the right place.
| Metric | Value |
|---|---|
| 🤖 MCP Tools | 6 agent-ready tools (semantic, hybrid, RAG, ingest, delete, status) |
| ⚡ Vector Search Latency | 0.05 ms avg @ 10K docs (128-dim) |
| 🔍 Keyword Search Latency | 0.98 ms avg @ 100K docs |
| 🧬 Hybrid Search Latency | 0.17 ms avg @ 10K docs |
| 🚀 Vector Throughput | 18,800 queries/sec @ 10K |
| 🧵 Concurrent Hybrid | 14,000+ ops/sec @ 16 threads (384-dim) |
| 🗜️ IVF-PQ + TurboQuant | 8–32× memory reduction |
| ✅ Test Suite | 331+ tests, all passing |
| 📦 Dependencies | Zero (JDK only) |
| Page | Description |
|---|---|
| [[Getting Started | Getting-Started--Quickstart]] |
| [[What is Spector | About]] |
| [[JDK API Status | Getting-Started--Jdk-Api-Status]] |
| FAQ | Common questions answered |
| Page | Description |
|---|---|
| [[MCP Integration Architecture | Architecture--Mcp-Integration]] |
| [[MCP Server Guide | Sdk-Usage--Mcp-Server]] |
| Page | Description |
|---|---|
| [[Architecture Overview | Architecture--Overview]] |
| [[Core Concepts | Architecture--Core-Concepts]] |
| [[Ingestion Pipeline | Architecture--Ingestion-Pipeline]] |
| [[RAG Pipeline | Architecture--Rag-Pipeline]] |
| [[Distributed Mode | Architecture--Distributed-Mode]] |
| [[GPU Acceleration | Architecture--Gpu-Acceleration]] |
| Page | Description |
|---|---|
| [[REST API Reference | Api-Reference--Rest-Endpoints]] |
| [[Java SDK Guide | Sdk-Usage--Java-Client]] |
| [[Spring AI Integration | Sdk-Usage--Spring-Ai]] |
| [[CLI Reference | Cli-Reference--Spectorctl]] |
| [[Configuration Guide | Configuration--Parameters]] |
| Page | Description |
|---|---|
| [[Performance Tuning | Operations--Performance-Tuning]] |
| [[Contributing | Operations--Contributing]] |
graph LR
A["🤖 AI Agent"] --> B["📡 MCP Server"]
B --> C["⚡ SpectorEngine"]
C --> D["🧠 Hybrid Search"]
D --> E["🎯 RRF Fusion"]
E --> F["🤖 LLM Re-ranking"]
F --> G["✨ Results"]
H["📄 Document"] --> I["🧩 Chunking"]
I --> J["🧬 Embedding"]
J --> C
Tip
New here? Start with Getting Started to build and run your first search in under 5 minutes. Want to connect an AI agent? See the MCP Server Guide.
| Language | Java 25 |
| License | Apache 2.0 · BSL 1.1 (memory module) |
| Modules | 18 Maven modules |
| Dependencies | Zero (JDK only) |
| SIMD | AVX2 / AVX-512 / NEON |
| GPU | CUDA via Panama FFM |
| MCP | Built-in, 6 agent-ready tools |
| Distributed | gRPC fan-out + consistent hashing |
Built with ⚡ by Spectrayan · GitHub · Apache 2.0 · BSL 1.1 (memory)
- Home
- About
- Getting Started
-
Architecture
- System Overview
- Core Concepts
- MCP Integration
- Ingestion Pipeline
- RAG Pipeline
- Distributed Mode
- GPU Acceleration
- Test Framework & LLM Judge
-
Modules
- Overview
- spector-core
- spector-commons
- spector-config
- spector-storage
- spector-embed-api
- spector-embed-ollama
- spector-index
- spector-query
- spector-gpu
- spector-rag
- spector-engine
- spector-ingestion
- spector-memory
- spector-runtime
- spector-node
- spector-mcp
- spector-cli
- spector-client
- spector-spring
- spector-test-support
- spector-metrics
- spector-events
- spector-bench
- spector-dist
- spector-cortex
- Deep Dives
-
🧠 Cognitive Memory
- Overview
- Getting Started
- Architecture
-
Biological Systems
- Overview
- Cortex — Tier Stores
- Hippocampus — Sleep Consolidation
- Synapse — Tags & Scoring
- Dopamine — Surprise Detection
- Amygdala — Emotional Valence
- 3-Layer Cognitive Graph
- Habituation — Anti-Filter Bubble
- Inhibition — Suppression
- Interference — Deduplication
- Prospective — Future Intents
- Metamemory — Self-Reflection
- Sync — Persistence & Replication
- Advanced Profiles
- Deep Dives
- API Reference
- 🧬 Cortex Dashboard
- Reference
- Operations
- FAQ
- Roadmap
- 🔬 Labs