OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
RAG & Knowledge Systems

Gibram

Gibram is an in-memory knowledge graph server for RAG and GraphRAG workflows, pairing vector search with graph traversal and a Python SDK for document indexing and queries.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Gibram — OpenViST project profile in RAG & Knowledge Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Gibram when an application needs graph-aware retrieval over a short-lived document collection and can run a server alongside its Python indexing workflow.

Who it is for

  • Developers building RAG or GraphRAG applications.
  • Teams that need temporary document indexing and graph-aware context retrieval for analysis or exploration.

Documented uses

  • Index documents into entities, relationships, chunks and embeddings.
  • Retrieve relevant context using semantic search and traversal across related graph nodes.
  • Adapt document chunking, extraction or embedding components to a workflow.
Before you choose

Requirements & limits

  • The server stores data in RAM with configurable time to live and is intended for ephemeral use, not persistent storage.
  • The documented server default is port 6161, and the Python SDK connects to a running server.
  • The README's indexer example uses an LLM API key and shows an OpenAI key as an option.
  • The repository lists the project under the MIT license.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up a Docker server and Python indexing workflow

Start the documented server container, install the Python SDK, and configure an indexer to connect to it.

Before you start

  • Docker
  • Python and pip
  • An LLM API key for the documented indexer example

Steps

  1. Start the server with the command below.

    Documented command
    docker run -p 6161:6161 gibramio/gibram:latest

  2. Install the SDK with the command below.

    Documented command
    pip install gibram

  3. Initialize GibRAMIndexer with the server host and port, a session ID, and an LLM API key or the OPENAI_API_KEY environment variable.

Expected outcome

A running server and a configured Python indexer ready for the documented indexing and query workflow.

Guide limitations

  • This setup recipe does not include indexing or querying steps.
  • The server stores data in RAM with a configurable time to live and is intended for short-lived analysis rather than persistent storage.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Vector search

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
GibramIndex documents into entities, relationships, chunks and embeddings.Docker, Linux, Self-hosted, Server
MettisIndex text documents through an HTTP endpoint.Linux, Self-hosted, Server
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
13 October 2026
Original website title
gibram-io/gibram · Official homepage title · retained in its source language
How we review sourcesSuggest a correction