gibram-io/gibram
GibRAM is an in-memory knowledge graph server designed for retrieval augmented generation (RAG / GraphRAG) workflows.
Combines graph traversal with vector search to retrieve both semantically similar and structurally connected context in a single query. Built as an ephemeral, RAM-resident store with configurable TTL, designed for short-lived analysis rather than persistence. Provides a Python SDK with swappable components (chunker, extractor, embedder) for customizable GraphRAG workflows, supporting both named entity extraction and relationship mapping alongside semantic embeddings.
104 stars.
Stars
104
Forks
8
Language
Go
License
MIT
Category
Last pushed
Jan 31, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/gibram-io/gibram"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
zilliztech/vector-graph-rag
Graph RAG with pure vector search, achieving SOTA performance in multi-hop reasoning scenarios.
Qubit02/BrainTrace
BrainTrace: GraphRAG-based on-device knowledge management system for secure and efficient...
vivy1024/daml-rag-framework
🧠 DAML-RAG: Domain-Adaptive Multi-source Learning RAG Framework | GraphRAG混合检索 + 推理时学习 +...
ApexIQ/End-to-End-Graphrag-implementation
End-to-End-Graphrag-implementation
scthornton/hybrid-rag-pivot-attacks
Retrieval Pivot Attacks in Hybrid RAG (Vector → Graph)