Ross ROSS = Recommend OSS · open-source software intelligence for agents

HelixDB/helix-db

HelixDB is an OLTP graph-vector database built in Rust on Object Storage. observed · 2026-08-28

github.com/HelixDB/helix-db · homepage · Rust · Apache-2.0 (permissive) observed · 2026-08-28

Health v2 · maintenance only

84/100

  • Activity 99
  • Release rhythm 86
  • Longevity 46
How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: 0.0
  • age_days: 648
  • days_rel: 17
  • days_push: 7
  • n_releases_24m: 183

Full methodology

Adoption not part of the score

5857 stars · 342 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

HelixDB is an open-source OLTP graph-vector database written in Rust that combines labeled property graphs with native vector, full-text, and temporal search on object storage. It ships with a CLI, SDKs for TypeScript, Python, Go, and Rust, an embedded runtime, and a cloud offering, targeting AI memory, GraphRAG, and company-knowledge applications.

Use cases

  • store long-term memory for AI agents
  • build a GraphRAG assistant with graph traversal and vector search
  • create a company brain searching people, projects, and documents together
  • map code dependencies and search a codebase semantically
  • build recommendations combining relationships and similarity
  • run a self-hosted graph-vector database on object storage
  • query knowledge graphs with vector and full-text search in one engine

When to choose

  • you need graph relationships, vector similarity, and full-text search in a single transactional store
  • you are building AI agent memory, GraphRAG, or enterprise knowledge applications
  • you want an embedded or self-hosted database backed by object storage with low cost at scale
  • you want pre-filtering so vector results respect graph and permission boundaries

When to avoid

  • you need a mature, battle-tested database with a long production track record
  • you only need a simple key-value or relational store without graph or vector features
  • you require a large ecosystem of third-party tools and connectors
  • you need heavy analytical (OLAP) workloads rather than OLTP

Facets

service · maturity active

database vector-database search-engine rag cli sdk databases large-language-models developer-tools rust windows self-hosted python go cloud graph-database graphrag agent-memory object-storage embedded-database hybrid-search knowledge-graph oltp full-text-search mcp retrieval-augmented-generation ai-agents search macos linux docker nodejs

7 sources

Member repositories

RepositoryRoleHealth v2
HelixDB/helix-dbmain84

For agents

markdown · JSON · MCP: product_card(name="HelixDB/helix-db")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem