TyKolt/kremis
A minimal graph engine for grounded AI — records, associates, and retrieves, but never invents. Written in Rust.
When working with AI agents or large language models, Kremis helps ensure factual accuracy by providing a verifiable memory layer. It takes your raw data, organizes it into a knowledge graph, and retrieves specific facts, confirming what's true and explicitly marking what's not in your original input. This is for AI practitioners, researchers, or compliance officers who need to guarantee that AI outputs are grounded in reality and free from invented information.
Use this if you need an AI system (like an agent or an LLM) to operate with a completely truthful, non-hallucinating memory, where every piece of information can be traced back to its source.
Not ideal if you need an AI that can creatively generate new information, infer relationships, or operate with probabilistic knowledge, as Kremis only records and retrieves explicitly provided facts.
Stars
8
Forks
1
Language
Rust
License
Apache-2.0
Category
Last pushed
Mar 11, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/TyKolt/kremis"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
topoteretes/cognee
Knowledge Engine for AI Agent Memory in 6 lines of code
CaviraOSS/OpenMemory
Local persistent memory store for LLM applications including claude desktop, github copilot,...
verygoodplugins/automem
AutoMem is a graph-vector memory service that gives AI assistants durable, relational memory:
CortexReach/memory-lancedb-pro
Enhanced LanceDB memory plugin for OpenClaw — Hybrid Retrieval (Vector + BM25), Cross-Encoder...
divagr18/memlayer
Plug-and-play memory for LLMs in 3 lines of code. Add persistent, intelligent, human-like memory...