HelixDB: an open-source graph-vector database built from scratch in Rust.

Website | Docs | Discord | X/Twitter

---

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.

Get started with HelixDB

---

Key Features

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 and can be run locally or through Enterprise Cloud.
Ultra-Low Latency	Helix is built in Rust and uses LMDB as its storage engine to provide extremely low latencies.
Dynamic Queries	The v2 query API accepts JSON requests through POST /v1/query, so local development does not require a compile/deploy loop.

Getting Started

Helix CLI

Start by installing the Helix CLI tool to deploy Helix locally.

1. Install CLI

   curl -sSL "https://install.helix-db.com" | bash

2. Initialize a project

   mkdir <path-to-project> && cd <path-to-project>
   helix init

3. Start a local v2 development instance

   helix run dev

4. Send a dynamic query

   helix init creates examples/request.json, which is a ready-to-run dynamic query request.

   helix query dev --file examples/request.json

   Dynamic query requests are JSON payloads sent to POST /v1/query:

   {
     "request_type": "read",
     "query": {
       "queries": [{
         "Query": {
           "name": "node_count",
           "steps": [
             {"NWhere": {"Eq": ["$label", {"String": "User"}]}},
             "Count"
           ],
           "condition": null
         }
       }],
       "returns": ["node_count"]
     },
     "parameters": {}
   }

5. Stop the local instance when finished

    helix stop dev

Enterprise Cloud clusters use a separate deploy path. After linking an Enterprise instance with helix init enterprise or helix add enterprise, run helix push <instance> to compile and upload the Enterprise query project, and helix sync <instance> to reconcile source snapshots and refresh cloud metadata.

License

HelixDB is licensed under the The AGPL (Affero General Public License).

Commercial Support

HelixDB is available as a managed service for selected users, if you're interested in using Helix's managed service or want enterprise support, contact us for more information and deployment options.

---

Just Use Helix