gibram

Community

Build a local knowledge graph from markdown docs.

Authorcameronsjo
Version1.0.0
Installs0

System Documentation

What problem does it solve?

GibRAM provides an in-memory knowledge graph and vector search to organize and explore large collections of Markdown documents locally.

Core Features & Use Cases

  • In-memory graph with entity nodes, relationships, and embeddings for fast, private research.
  • Session-scoped corpora indexing of Markdown files for cross-doc reasoning and ADR tracing.
  • Claude/MCP integration for querying and indexing workflows, supporting local Ollama or OpenAI backends.

Quick Start

Index a directory of Markdown files into GibRAM and start querying for related concepts.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: gibram
Download link: https://github.com/cameronsjo/dev-toolkit/archive/main.zip#gibram

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.