# RushDB

> RushDB is an open-source database for AI. It records fields, types and values on every write, so agents can read the schema before they query.

This index is generated at request time from the current website configuration and published CMS records. Use the linked documentation for exact API details.

## Core Pages

- [Homepage](https://rushdb.com/): RushDB is an open-source database for AI: write JSON, get linked records with a schema catalog updated on every write, and query them with SQL, Cypher, Gremlin, Mongo-style documents, and hybrid vector + BM25 search. One Rust binary (Apache-2.0), or managed on RushDB Cloud.
- [Features](https://rushdb.com/features): Linked records from nested JSON, the schema catalog updated on every commit, the same query in SQL, SQL/PGQ, openCypher, ISO GQL, Gremlin and SearchQuery with maturity and transports, vector + BM25 + hybrid search, transactions, architecture, what is stable, and what is coming soon.
- [Use cases](https://rushdb.com/use-cases): Agent memory, company knowledge and RAG across sources, search and assistants in apps, and agent analytics, with docs tutorials for each and where RushDB is not a fit.
- [Pricing and RushDB Cloud](https://rushdb.com/pricing): RushDB Cloud plans, and what Cloud adds on top of the engine: managed embeddings, natural-language search, relationship suggestions, hosted MCP, dashboard. The engine is free under Apache-2.0.
- [Security](https://rushdb.com/security): Security, privacy, compliance and responsible disclosure.
- [Changelog](https://rushdb.com/changelog): What changed in each release.
- [Blog](https://rushdb.com/blog): Guides, comparisons, tutorials, engineering notes and release notes.
- [Full website content for LLMs](https://rushdb.com/llms-full.txt): Full text of the Features, Use cases and Pricing pages, plus every published blog post and CMS page.
- [GitHub repository](https://github.com/rush-db/rushdb): The open-source RushDB engine (Apache-2.0).

## Documentation

- [Quick tutorial](https://docs.rushdb.com/3.x/get-started/quick-tutorial): The fastest path to a working RushDB project.
- [Engine manual](https://docs.rushdb.com/3.x/engine): Install, data model, query languages, search, and operations for the self-hosted engine.
- [Schema catalog](https://docs.rushdb.com/3.x/engine/data-model/schema-catalog): The exact, per-commit catalog of labels, properties, types, and relationship shapes.
- [Query languages](https://docs.rushdb.com/3.x/engine/languages): SQL, openCypher, ISO GQL (not GraphQL), Gremlin, SQL/PGQ, and Mongo-style documents.
- [Hybrid search](https://docs.rushdb.com/3.x/engine/indexes-and-search/hybrid-search): Filter once, rank by vector and BM25, fuse with RRF or DBSF.
- [REST API](https://docs.rushdb.com/3.x/learn/reference/rest-api/introduction): RushDB Cloud REST API documentation.
- [TypeScript SDK](https://docs.rushdb.com/3.x/learn/reference/typescript): JavaScript and TypeScript SDK documentation.
- [Python SDK](https://docs.rushdb.com/3.x/learn/reference/python): Python SDK documentation.
- [Records](https://docs.rushdb.com/3.x/engine/data-model/records-and-labels): Records and labels: the basic unit of data.
- [Relationships](https://docs.rushdb.com/3.x/learn/relationships): Graph links between records.
- [Transactions](https://docs.rushdb.com/3.x/learn/records-and-queries/transactions): Multi-statement transactions over MVCC snapshots.
- [Search](https://docs.rushdb.com/3.x/learn/search-query): Structured filtering, traversal, selection, grouping, and analytics.
- [Semantic search](https://docs.rushdb.com/3.x/learn/semantic-search): Vector search over your own vectors, or managed embeddings on Cloud.
- [Embedding indexes](https://docs.rushdb.com/3.x/learn/reference/rest-api/ai-and-vectors/indexing): Create and monitor searchable embedding indexes.
- [MCP server](https://docs.rushdb.com/3.x/connect/mcp): Connect RushDB to MCP-capable agents and clients.
- [Self-hosting](https://docs.rushdb.com/3.x/deploy): Deploy the engine with Docker, Helm, systemd, or platform templates.

## Use Cases

- [Agent memory](https://rushdb.com/use-cases#memory): Agents that remember, and can show where a memory came from.
- [Company brain & RAG](https://rushdb.com/use-cases#company): Answers that span your docs, CRM, support, billing and code, with the record behind every fact.
- [AI search & assistants](https://rushdb.com/use-cases#apps): Search and assistants on the records your app already writes.
- [Analytics](https://rushdb.com/use-cases#analytics): Questions about your data, answered by a read-only query you can inspect.

## Blog Categories

- [Engineering](https://rushdb.com/blog/category/engineering): How the RushDB engine is built: storage, query planning, search and the decisions behind them.

## Blog: Engineering

- [Vector RAG vs GraphRAG vs Agentic RAG: Why There Is No Winner](https://rushdb.com/blog/vector-rag-graphrag-agentic-rag-comparison-c203b6): Vector RAG, GraphRAG, and Agentic RAG preserve different context. Learn when each works, where each fails, and how to combine them in one app.
- [Persistent Agent Memory for OpenClaw and Hermes with RushDB](https://rushdb.com/blog/persistent-agent-memory-openclaw-hermes-rushdb): RushDB brings scoped, durable, lifecycle-aware memory to OpenClaw and Hermes Agent through native connectors and one shared event contract.
- [Vector Search Doesn't Understand Data Structure](https://rushdb.com/blog/vector-search-doesn-t-understand-data-structure-cda544): Embeddings rank similarity but ignore joins, cardinality, and constraints. Learn how RushDB combines semantic retrieval with explicit graph relationships and live schema discovery.
- [Why Every AI Stack Grows Into Five Data Pipelines](https://rushdb.com/blog/why-every-ai-stack-starts-with-five-data-pipelines-2a1d57): LLM applications naturally fragment into ETL, embedding, graph sync, search indexing, and metadata pipelines. Learn why this happens and how a single ingestion layer can replace.
- [Stop Teaching Agents Your Schema](https://rushdb.com/blog/stop-teaching-agents-your-schema-d57a76): Every new agent needs a prompt explaining your tables and fields. RushDB lets agents fetch a structured snapshot of the live graph at runtime.

## Blog: Other

- [RushDB 2.0: Memory Infrastructure for the Agentic Era](https://rushdb.com/blog/rushdb-2-0-release): RushDB 2.0 is a major release built for the agentic era: native semantic search, ontology-aware querying, MCP with OAuth, bring-your-own Neo4j, and prebuilt agent skills. It turns memory infrastructure into one unified layer, so developers can store structured context, traverse relationships, and search by meaning without stitching together multiple systems.
- [Labeled Meta Property Graphs (LMPG): A Property-Centric Approach to Graph Database Architecture](https://rushdb.com/blog/labeled-meta-property-graphs-rushdb-s-revolutionary-approach-to-graph-database-architecture): Discover how LMPG transforms graph databases by treating properties as first-class citizens rather than simple node attributes. This comprehensive technical guide explores RushDB's groundbreaking architecture that enables automatic schema evolution, property-first queries, and cross-domain analytics impossible in traditional property graphs or RDF systems.
- [Knowledge Graphs: Semantic Reasoning Meets Graph Architecture](https://rushdb.com/blog/knowledge-graphs-semantic-reasoning-meets-graph-architecture): RushDB article.
- [Labeled Property Graphs: A Comprehensive Guide to Enhanced Graph Data Modeling](https://rushdb.com/blog/labeled-property-graphs-a-comprehensive-guide-to-enhanced-graph-data-modeling): Labeled Property Graphs (LPGs) represent an evolution of traditional property graphs, introducing explicit type labels for nodes and relationships. This enhancement not only improves schema clarity but also boosts query performance, making LPGs a preferred choice for complex data modeling scenarios. In this article, we explore the advantages, challenges, and practical applications of LPGs.
- [RDF: A Comprehensive Guide to Semantic Web Data Modeling](https://rushdb.com/blog/rdf-a-comprehensive-guide-to-semantic-web-data-modeling): Resource Description Framework (RDF) represents a fundamental paradigm shift in how we model and represent knowledge on the web. As the cornerstone of the Semantic Web, RDF provides a standardized method for describing resources and their relationships in a way that is both machine-readable and semantically rich. Unlike traditional data models that focus on storage and retrieval efficiency, RDF prioritizes meaning, interoperability, and automated reasoning.
- [Rethinking the Graph: How Labeled Meta-Property Graphs Unlock Structure Without Sacrificing Flexibility](https://rushdb.com/blog/rethinking-the-graph-how-labeled-meta-property-graphs-unlock-structure-without-sacrificing-flexibility): RushDB article.
- [Breaking Down the Hidden Costs of Data Silos in Scientific Labs](https://rushdb.com/blog/breaking-down-the-hidden-costs-of-data-silos-in-scientific-labs): RushDB article.
- [Graph Databases Explained: Property Graphs vs RDF vs Knowledge Graphs - Complete Developer Guide 2025](https://rushdb.com/blog/graph-databases-explained-property-graphs-vs-rdf-vs-knowledge-graphs-complete-developer-guide-2025): Complete guide to graph database models: property graphs, RDF, labeled graphs, and knowledge graphs. Learn which graph model fits your use case and how to choose the right technology.
- [Backendless Fullstack Development: React useForm + RushDB](https://rushdb.com/blog/backendless-fullstack-development-react-useform-rushdb): See how a single line of code can replace an entire backend infrastructure while preserving your data's natural structure. Perfect for rapid prototyping, MVPs, and applications with evolving data models.
- [Self-Hosted RushDB: Quick Setup](https://rushdb.com/blog/rushdb-selfhosted-quick-setup): Learn how to run RushDB in self-hosted mode using Docker with either Neo4j Aura or a local container.
- [Introducing RushDB: Zero-Config Instant Database for Modern Apps & AI Era](https://rushdb.com/blog/rushdb-the-zero-config-database-for-modern-apps-and-ai-solutions): RushDB is a zero-config, graph-powered instant database with bulk semi-structured data ingestion, automatic normalization, and powerful querying

## CMS Pages

- [RushDB Cookie Policy](https://rushdb.com/cookie-policy): RushDB information page.
- [RushDB Privacy Policy](https://rushdb.com/privacy-policy): RushDB information page.
- [RushDB Terms of Service](https://rushdb.com/terms-of-service): RushDB information page.
- [RushDB Agent Setup — Persistent Graph Memory for AI Agents](https://rushdb.com/agent-setup): Give any AI agent persistent, graph-structured memory using RushDB. Store sessions, decisions, tasks, and preferences — queryable by meaning across conversations.