Solutions | SurrealDB

Access control & entitlements

Secure systems with graph-based access control and semantic policy evaluation. Manage complex permission hierarchies.

Graph retrieval

Role hierarchies, permission relationships, and access policy graphs.

Vector search

Semantic similarity of access requests, policy documents, and contextual entitlement checks.

Attribute filtering

Filter users by role, department, access level, and permission groups. Query by resource type, action permissions, and temporal access patterns.

File storage

Store policy documents, access logs, and security guidelines as documents. Enable semantic search across compliance requirements and policy enforcement.

Why SurrealDB?

Secure systems by combining graph-based access control with semantic policy evaluation.

Agentic NPCs in video games

Create dynamic NPCs with memory and relationships. Build immersive game worlds with contextual AI interactions.

Graph retrieval

NPC relationship graphs, quest dependencies, and world state tracking.

Vector search

Semantic similarity of dialogue, quest descriptions, and contextual behavior retrieval.

Attribute filtering

Filter NPCs by location, faction, quest status, and relationship strength. Query by dialogue history, inventory items, and behavioral patterns.

File storage

Store NPC dialogue scripts, quest descriptions, and world lore as documents. Enable semantic search across game content and contextual retrieval.

Why SurrealDB?

Create more dynamic NPCs by linking structured world graphs with semantic understanding of game context.

Code indexing & retrieval

Make code retrieval more effective by combining structural code graphs with semantic search capabilities.

Graph retrieval

Code dependency graphs, module relationships, and import/export hierarchies.

Vector search

Semantic similarity of code, documentation, and contextual code search.

Attribute filtering

Filter code by language, framework, complexity, and ownership. Query by function signatures, dependencies, and code patterns.

File storage

Store source code files, documentation, and code comments as documents. Enable semantic search across codebases and contextual code understanding.

Why SurrealDB?

Make code retrieval more effective by combining structural code graphs with semantic search capabilities.

Codebase Q&A assistant

Enable developers to query codebases using both structural relationships and semantic meaning, improving productivity and code understanding.

Graph retrieval

File dependencies, function call graphs, and code ownership relationships.

Vector search

Semantic similarity of code snippets, natural language code search, and contextual documentation retrieval.

Attribute filtering

Filter code by module, function, class, and complexity metrics. Query by code patterns, architectural decisions, and implementation details.

File storage

Store code files, documentation, README files, and technical specifications as documents. Enable semantic search across development knowledge and code context.

Why SurrealDB?

Enable developers to query codebases using both structural relationships and semantic meaning, improving productivity and code understanding.

AI tutor with custom curriculum

Personalize learning by combining curriculum structure with semantic understanding of educational materials.

Graph retrieval

Curriculum graphs, prerequisite relationships, and learning path optimization.

Vector search

Semantic similarity of educational content, personalized question answering, and adaptive content retrieval.

Attribute filtering

Filter students by learning level, progress, and subject mastery. Query by topic difficulty, prerequisite completion, and adaptive learning paths.

File storage

Store educational content, lesson plans, and assessment materials as documents. Enable semantic search across curriculum resources and personalized content delivery.

Why SurrealDB?

Personalize learning by combining curriculum structure with semantic understanding of educational materials.

Customer support copilot

Improve support outcomes by combining relationship graphs with semantic search for faster, more relevant answers.

Graph retrieval

Ticket escalation graphs, customer interaction histories, and support workflow relationships.

Vector search

Semantic similarity of support tickets, knowledge base articles, and contextual response suggestions.

Attribute filtering

Filter tickets by priority, category, status, and customer tier. Query by issue type, resolution time, and escalation patterns.

File storage

Store knowledge base articles, support tickets, and customer communications as documents. Enable semantic search across support resources and contextual assistance.

Why SurrealDB?

Improve support outcomes by combining relationship graphs with semantic search for faster, more relevant answers.

Enterprise knowledge search

Unify enterprise knowledge with graph-based document relationships and semantic search capabilities.

Graph retrieval

Document references, topic hierarchies, and expert networks.

Vector search

Semantic similarity of knowledge articles, contextual Q&A, and document retrieval.

Attribute filtering

Filter knowledge by department, topic, author, and access permissions. Query by document type, creation date, and relevance scores.

File storage

Store enterprise documents, policies, procedures, and knowledge articles as documents. Enable semantic search across organizational knowledge and contextual information retrieval.

Why SurrealDB?

Deliver relevant knowledge by combining graph-based relationships with semantic search across enterprise content.

Drug discovery explorer

Accelerate drug discovery by connecting compound interactions, pathways, and clinical data with semantic search.

Graph retrieval

Compound interaction graphs, pathway relationships, and clinical trial networks.

Vector search

Semantic similarity of research papers, compound descriptions, and contextual data mining.

Attribute filtering

Filter compounds by molecular properties, toxicity, and efficacy scores. Query by target proteins, clinical trial phases, and research outcomes.

File storage

Store research papers, clinical trial reports, and compound databases as documents. Enable semantic search across scientific literature and experimental data.

Why SurrealDB?

Accelerate drug discovery by linking structured biomedical data with semantic literature search.

Financial intelligence engine

Combine graph-based entity and transaction analysis with vector-based anomaly detection for robust financial intelligence and anti-fraud solutions.

Graph retrieval

Entity resolution, transaction graph analysis, money flow tracing, and fraud ring detection.

Vector search

Semantic similarity of transaction descriptions, anomaly detection in unstructured data, and contextual enrichment.

Attribute filtering

Filter transactions by amount, type, location, and risk score. Query by entity relationships, money flow patterns, and regulatory compliance.

File storage

Store financial reports, transaction records, and compliance documents as documents. Enable semantic search across financial data and regulatory requirements.

Why SurrealDB?

Combine graph-based entity and transaction analysis with vector-based anomaly detection for robust financial intelligence and anti-fraud solutions.

Fraud detection & risk graphs

Detect fraud and assess risk by combining graph-based relationship analysis with semantic anomaly detection.

Graph retrieval

Transaction graphs, risk propagation, and entity relationship analysis.

Vector search

Semantic similarity of risk factors, anomaly detection, and contextual alerting.

Attribute filtering

Filter transactions by risk indicators, fraud patterns, and suspicious behaviors. Query by entity connections, transaction velocity, and anomaly scores.

File storage

Store fraud reports, risk assessments, and investigation documents as documents. Enable semantic search across fraud patterns and risk indicators.

Why SurrealDB?

Detect fraud and assess risk by combining graph-based relationship analysis with semantic anomaly detection.

Legal research assistant

Link legal cases, statutes, and expert commentary. Retrieve relevant precedents with contextual awareness.

Graph retrieval

Case-to-case citations, legal topic hierarchy, statute relationships, and judicial precedent networks.

Vector search

Semantic similarity of legal text and case facts, natural language legal queries, and contextual document retrieval.

Attribute filtering

Filter cases by jurisdiction, court level, and legal topic. Query by citation patterns, precedent relationships, and legal doctrine.

File storage

Store legal cases, statutes, regulations, and legal commentary as documents. Enable semantic search across legal texts and contextual precedent retrieval.

Why SurrealDB?

Native traversal of both legal relationships and vector relevance makes graph RAG seamless. Query complex legal precedents while understanding both citation networks and semantic similarity of case facts in a single system.

Memory layers for LLM agents

Enhance LLM agents with both structured memory graphs and semantic recall for richer, more contextual interactions.

Graph retrieval

Agent memory graphs, context chaining, and episodic memory relationships.

Vector search

Semantic similarity of agent experiences, contextual memory retrieval, and long-term memory search.

Attribute filtering

Filter memories by type, importance, and temporal relevance. Query by context, emotional valence, and memory associations.

File storage

Store conversation history, agent experiences, and episodic memories as documents. Enable semantic search across agent memory and contextual recall.

Why SurrealDB?

Enhance LLM agents with both structured memory graphs and semantic recall for richer, more contextual interactions.

Personalized AI doctor

Combine patient relationship graphs with semantic understanding of medical data for personalized healthcare recommendations.

Graph retrieval

Patient history graphs, symptom-diagnosis relationships, and treatment pathways.

Vector search

Semantic similarity of medical records, symptom descriptions, and contextual literature retrieval.

Attribute filtering

Filter patients by demographics, medical history, and risk factors. Query by symptoms, treatment responses, and health outcomes.

File storage

Store medical records, research papers, and clinical guidelines as documents. Enable semantic search across medical knowledge and personalized care recommendations.

Why SurrealDB?

Combine patient relationship graphs with semantic understanding of medical data for personalized healthcare recommendations.

Recommendation engines

Deliver better recommendations by unifying collaborative filtering with semantic understanding of user preferences.

Graph retrieval

User-item interaction graphs, collaborative filtering, and preference propagation.

Vector search

Semantic similarity of product descriptions, reviews, and contextual recommendations.

Attribute filtering

Filter users by preferences, behavior patterns, and demographic attributes. Query by item categories, rating history, and recommendation confidence.

File storage

Store product catalogs, user reviews, and recommendation models as documents. Enable semantic search across product descriptions and user preferences.

Why SurrealDB?

Deliver better recommendations by unifying collaborative filtering with semantic understanding of user preferences.

Sales & market research copilot

Unify structured sales data with unstructured market insights for more effective research, targeting, and pipeline management.

Graph retrieval

Account hierarchies, sales pipeline relationships, and market segmentation graphs.

Vector search

Semantic similarity of sales notes, customer feedback, and market research documents.

Attribute filtering

Filter accounts by industry, size, and sales stage. Query by market segment, competitive landscape, and opportunity value.

File storage

Store market research reports, sales presentations, and competitive analysis as documents. Enable semantic search across market intelligence and sales strategies.

Why SurrealDB?

Unify structured sales data with unstructured market insights for more effective research, targeting, and pipeline management.

Social graph + feed optimization

Optimize social feeds by combining graph-based user relationships with semantic content relevance.

Graph retrieval

User connection graphs, content sharing relationships, and influence networks.

Vector search

Semantic similarity of posts, user interests, and contextual content recommendations.

Attribute filtering

Filter users by interests, engagement patterns, and social connections. Query by content type, popularity metrics, and relevance scores.

File storage

Store social media posts, user profiles, and content metadata as documents. Enable semantic search across social content and personalized feed optimization.

Why SurrealDB?

Optimize social feeds by combining graph-based user relationships with semantic content relevance.

Solutions for every industry

By use case

Agentic and Gen AI

GraphRAG

Knowledge Graphs

Embedded and Edge

By industry

Defence and Aerospace

Energy and Manufacturing

Finance and FinTech

Healthcare

Gaming and Entertainment

Retail and E-commerce

Use case examples

Access control & entitlements

Agentic NPCs in video games

Code indexing & retrieval

Codebase Q&A assistant

AI tutor with custom curriculum

Customer support copilot

Enterprise knowledge search

Drug discovery explorer

Financial intelligence engine

Fraud detection & risk graphs

Legal research assistant

Memory layers for LLM agents

Personalized AI doctor

Recommendation engines

Sales & market research copilot

Social graph + feed optimization

Ready to build your solution?