Open Source Knowledge Graph Tools
Knowledge graphs represent information as entities and relationships, making connections explicit rather than storing facts only in isolated documents or tables. They help people and software systems organize complex domains, trace how concepts relate, and retrieve context for search, analysis, recommendations, and AI-assisted reasoning. By linking sources and preserving structure, they can improve discovery and support queries that depend on relationships across data.
Open source tools in this area include graph databases, modeling and query languages, extraction pipelines, visualization interfaces, and integrations for search or AI retrieval. When choosing one, consider its data model, query capabilities, scale, interoperability, licensing, maintenance activity, and deployment requirements. Check how it handles updates, provenance, and access controls, especially when combining changing or sensitive sources. Knowledge graphs are useful to developers, researchers, data teams, and organizations that need to connect information across repositories or systems.
23 repositories · updated October 4, 2026
lat.md: Keep Codebase Knowledge in a Linked Markdown Graph
lat.md is a TypeScript CLI and markdown-based knowledge graph for documenting codebase concepts and linking them to source code. It helps coding agents and developers find context, keep references consistent, and retain decisions across work sessions.
utopia: Build a Time-Aware Enterprise Knowledge System
Utopia is a self-hosted knowledge system that turns documents and observations into an ontology-guided, bitemporal graph. It combines search, evidence-backed answers, agent access, and human review for teams that need to track how knowledge and decisions change.
llm_wiki: Turn Documents Into an Interlinked Knowledge Base
LLM Wiki is a cross-platform desktop app that uses an LLM to build and maintain a persistent, linked wiki from your documents. It suits people who want source-grounded knowledge they can explore and update, rather than answers assembled from scratch for each query.
gitnexus: Map Codebases for AI-Assisted Exploration
GitNexus indexes a repository into a code knowledge graph so developers and AI coding agents can trace dependencies, call chains, and execution flows. Use its local CLI and MCP integration for ongoing work, or the browser UI for quick exploration.
open-index: Build Searchable Context Graphs for AI Agents
Open Index is a Python tool for building structured, searchable domain knowledge that agents can retrieve and maintain. It suits teams that need validated context across files, connectors, and MCP-enabled agents.
a-mem-mcp: Build Evolving Memory for Coding Agents
A-MEM is an MCP server and Python library that stores agent knowledge as an evolving, connected memory graph. It suits coding-agent users who need to retrieve and build on project context across sessions.
Agent-Memory: Persistent Memory for AI Coding Agents
Agent-Memory gives coding agents persistent, searchable memory across sessions and tools. It is aimed at developers using MCP-compatible agents who want automatic context capture and recall without repeatedly explaining their projects.
graphrag: Build Graph-Powered AI Search and Chat
TigerGraph GraphRAG builds a knowledge graph from documents and combines graph queries with vector retrieval to answer natural-language questions. It suits teams already using TigerGraph that want a self-hosted, configurable RAG application.
code-review-graph: Map Code for AI Reviews
code-review-graph builds a local, persistent map of code structure and serves targeted review context to AI coding tools through MCP and a CLI. It suits teams working in large or interconnected repositories who want impact analysis without repeatedly scanning the whole codebase.
codebase-memory-mcp: Build a Searchable Code Knowledge Graph
A local MCP server that indexes repositories into a persistent graph of code structure and relationships. It helps AI coding agents answer architectural and code-navigation questions with focused queries instead of repeated file searches.
Understand-Anything: Explore Code Through Knowledge Graphs
Understand-Anything analyzes codebases, documentation, and knowledge bases, then presents their structure and relationships as interactive graphs. It is designed for developers and teams who want faster onboarding, code exploration, and change-impact analysis through AI coding platforms.
GitNexus: Map Codebases for AI-Assisted Analysis
GitNexus indexes a codebase as a knowledge graph and exposes its relationships through CLI and MCP tools. It helps developers and AI coding agents trace dependencies, understand execution flows, and assess change impact.