16 boosters for "knowledge graph" — open source, verified from GitHub, ready to install
"name": "understand-anything", "description": "AI-powered codebase understanding — analyze, visualize, and explain any project", "homepage": "https://github.com/Lum1104/Understand-Anything",
Local GraphRAG knowledge base backed by SQLite + MNN embeddings. Fully compatible with Android OfflineAI RAG database format. On first use, (~400 MB) is auto-downloaded into .
Graphlit MCP Server integrates the Graphlit knowledge graph platform with Claude, enabling developers to build AI agents with RAG capabilities, document parsing, and intelligent retrieval. It's ideal for teams building document-heavy AI applications, knowledge management systems, and enterprise AI agents.
"description": "Lightweight knowledge graph for AI-assisted development. Impact analysis, code search, dependency tracking, and context generation.", "email": "freepeak@example.com" "homepage": "https://github.com/FreePeak/LeanKG",
CortexGraph is a temporal memory system for AI assistants that implements human-like forgetting curves using local storage (JSONL and Markdown), enabling natural conversation memory across Claude, Cursor, and other platforms without explicit save commands.
"version": "0.14.4", "description": "Persistent memory system for AI coding assistants. Captures decisions, learnings, and context from coding sessions and surfaces them when relevant.", "name": "Robert Allen",
"name": "@tekmidian/pai", "displayName": "PAI Knowledge OS", "description": "Personal AI Infrastructure — persistent memory, session continuity, and knowledge graph for Claude Code",
Cortex is a local-first knowledge graph that automatically watches your project files, extracts entities and relationships using LLMs, and enables natural language queries across multiple projects. It's ideal for developers who need intelligent cross-project search and knowledge management without relying on external services.
"name": "brainlayer", "name": "Etan Heyman", "url": "https://github.com/EtanHey"
MRF is a security-hardened metaprompting framework designed to protect AI agents from prompt injection attacks while enabling structured decision-making. It benefits developers building production agents on Claude platforms who need robust input sanitization and instruction clarity.
DevOMeter is a Cursor workflow automation rule that standardizes GitHub issue creation and Knowledge Graph synchronization, preventing duplicates and maintaining canonical task links. It benefits developers managing complex project workflows with GitHub CLI integration.
HoloLoom is a neural decision-making system prompt integrating prompt management, analytics, and Thompson Sampling optimization for LLM applications. Developers working with multi-agent systems and prompt optimization would benefit from its structured approach to prompt selection and performance tracking.
A Cursor rules booster that standardizes GitHub issue creation and Knowledge Graph synchronization workflows, preventing duplicates and maintaining canonical task links. Ideal for teams using GitHub CLI and Cursor together for project management.
Cursor rules for standardizing GitHub issue creation and Knowledge Graph synchronization with automated deduplication and shell commands. Useful for teams managing task workflows across repositories.
Fodda Knowledge Graphs provides expert-curated domain-specific knowledge graphs (Retail, Beauty, Sports, etc.) as an MCP server for AI agents, enabling developers to integrate structured, industry-specific data into Claude applications.
This MCP server enables Claude to maintain persistent project memory using a Kuzu-powered knowledge graph, allowing developers to preserve context and relationships across conversations. It's useful for teams managing complex projects that need to retain institutional knowledge and cross-reference information.
