kremis
Active·★ 12·Apache-2.0·Updated 2026-05-25
★ Trending★ Data Processing★ Dev Tooling
A minimal graph engine for grounded AI — records, associates, and retrieves, but never invents. Written in Rust.
Kremis is a deterministic knowledge graph MCP server written in Rust. It provides a local, single-binary solution for recording, associating, and retrieving knowledge without relying on LLMs. The system ensures determinism, inspectability, and grounding through ACID transactions and BLAKE3 hashing.
#ai#ai-agents#anti-hallucination#cli#deterministic#embedded-database#explainable-ai#graph-database
01
Features
01Deterministic graph engine
02CLI + HTTP API + MCP bridge
03BLAKE3 hashing for integrity
04Canonical export (KREX)
05Zero baked-in knowledge
02
Compatibility
Linux
Linux
Verified via docs
macOS
macOS
Verified via docs
Windows
Windows
Verified via docs
03
Quick start
1
$ git clone https://github.com/TyKolt/kremis.git
2
$ cd kremis
3
$ cargo build --release
04
Use cases
↳AI agent memory via MCP
↳LLM fact-checking
↳Provenance and audit trail
05
Alternatives
agents-best-practices★ 1.1k
Provider-neutral Agent Skill for Codex, Claude Code, and agentic harness design.
awesome-claude★ 250
HeyClaude is a curated registry and distribution surface for Claude and AI-workflow assets: agents, MCP servers, skills, commands, hooks, rules, guides, tools, jobs, Raycast feeds, static data exports, and an npm MCP package.
initrunner★ 38
Define AI agent roles in YAML and run them anywhere: CLI, API server, or autonomous daemon
Related searches
Comments
Log in to leave a comment
- HHarper WhiteMay 21, 2026
Minimal graph engine for grounded AI that records, associates, and retrieves.
- DDakota MartinezMay 16, 2026
Good for AI systems that need knowledge grounding without heavy graph infrastructure.
- RRiver PatelMay 10, 2026
Minimal design means it's auditable — you can understand what it knows and why.
- JJamie ThompsonApr 9, 2026
Grounded AI approach reduces hallucination by keeping claims tied to recorded facts.