HelixDB is a cutting-edge, open-source database built from scratch in Rust, designed to unify graph, vector, and document data models into a single platform. It eliminates the need for managing separate databases for different data types, providing a streamlined solution for building modern AI-driven applications and RAG (Retrieval-Augmented Generation) systems.
The database features built-in support for embedding generation, vector search, and graph traversals, all accessible through a type-safe query language, HelixQL. With its focus on low latency and ease of use, HelixDB empowers developers to create sophisticated applications that can reason over interconnected data without the operational complexity of polyglot persistence.
Use Cases:
HelixDB: an open-source graph-vector database built from scratch in Rust.
Website | Docs | Discord | X/Twitter
Docs (https://img.shields.io/badge/docs-latest-blue) Change Log (https://img.shields.io/badge/changelog-latest-blue) GitHub Repo stars (https://img.shields.io/github/stars/HelixDB/helix-db) Discord (https://img.shields.io/discord/1354148209005559819?logo=discord) LOC (https://img.shields.io/endpoint?url=https://ghloc.vercel.app/api/HelixDB/helix-db/badge?filter=.rs$,.sh$&style=flat&logoColor=white&label=Lines%20of%20Code) Manta Graph (https://getmanta.ai/api/badges?text=Manta%20Graph&link=helixdb)
HelixDB is a database that makes it easy to build all the components needed for an AI application in a single platform.
You no longer need a separate application DB, vector DB, graph DB, or application layers to manage the multiple storage locations to build the backend of any application that uses AI, agents or RAG. Just use Helix.
HelixDB primarily operates with a graph + vector data model, but it can also support KV, documents, and relational data.
| Built-in MCP tools | Helix has built-in MCP support to allow your agents to discover data and walk the graph rather than generating human readable queries. |
| Built-in Embeddings | No need to embed your data before sending it to Helix, just use the Embed function to vectorize text. |
| Tooling for RAG | HelixDB has a built-in vector search, keyword search, and graph traversals that can be used to power any type of RAG applications. |
| Secure by Default | HelixDB is private by default. You can only access your data through your compiled HelixQL queries. |
| Ultra-Low Latency | Helix is built in Rust and uses LMDB as its storage engine to provide extremely low latencies. |
| Type-Safe Queries | HelixQL is 100% type-safe, which lets you develop and deploy with the confidence that your queries will execute in production |
Open-source, local-first collaboration platform combining chat, docs, and databases, usable offline and self-hosted.
Modern Jellyfin client featuring offline downloads, intro skipping, Chromecast support, and Jellyseerr integration.
Free, open-source desktop IDE for Kubernetes offering cluster visualization, log resource management, and extension support.
Peer-to-peer, end-to-end encrypted file and folder transfer over QUIC with resumable downloads, no accounts, and cross-platform desktop builds.
Context-aware Windows overlay assistant that reads your screen and delivers translations, summaries, and answers via multi-LLM backends with a sleek keyboard-driven UI.
WebRTC P2P tool for files, text, and desktop sharing with end-to-end encryption, ACK reliability, Docker/single-binary deploys, and a responsive Next.js UI.