← Latest products

GibRAM an in-memory ephemeral GraphRAG runtime for retrieval

GibRAM is an in-memory knowledge graph server designed for retrieval augmented generation (RAG / GraphRAG) workflows. Flat RAG pipelines often fail to retrieve related articles together, even when they are clearly connected through references, definitions, or clauses.

Open source

107 stars · GitHubexternal site

Visit github.comexternal site

Reactions (1)

Similar products

by description similarity

  1. FastGraphRAG

    github.com

    Better RAG using good old PageRank

    Hacker News457 pts

  2. Analyzing Semantic Redundancy in LLM Retrieval (Google GIST Protocol)

    news.ycombinator.com

    Last week, Google research published details on GIST (Greedy Independent Set Thresholding), a new protocol presented at NeurIPS 2025.

    Hacker News6 pts

  3. Open-source GraphRAG Application with your own data

    hub.docker.com

    This is an easy-to-use application for exploring your own data with retrieval augmented generation (RAG) backed by txtai.

    Hacker News12 pts

  4. Live Demo of GraphRAG with GPT-4o mini

    graphrag-demo.deepset.ai

    However, a common critique is the LLM costs for constructing the knowledge graph.

    Hacker News5 pts

  5. SpRAG

    github.com

    Open-source RAG implementation for challenging real-world tasks

    Hacker News69 pts