Dreamgraph
DreamGraph is a graph-first cognitive layer (graph → MCP → CLI → dashboard → extension) that builds a persistent knowledge graph to reason, validate changes, and generate docs.
What is Dreamgraph?
Dreamgraph is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to dreamgraph is a graph-first cognitive layer (graph → mcp → cli → dashboard → extension) that builds a persistent knowledge graph to reason, validate changes, and generate docs.
DreamGraph is a graph-first cognitive layer (graph → MCP → CLI → dashboard → extension) that builds a persistent knowledge graph to reason, validate changes, and generate docs.
This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- DreamGraph is a graph-first cognitive layer (graph → MCP → C
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx dreamgraphConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Dreamgraph
DreamGraph is a graph-first cognitive layer that builds a persistent knowledge graph of your codebase and surfaces it through an MCP server, CLI, dashboard, and browser extension. It performs causal discovery, validates changes against the graph, captures architectural decision records (ADRs), and generates documentation from the accumulated knowledge. AI agents connected via MCP can query the graph, run enrichment cycles, inspect source relationships, and trigger remediation workflows to keep their reasoning grounded in the actual state of the project.
Prerequisites
- Node.js 18 or later and npm (for building from source)
- Git 2.x or later
- A running codebase or repository for DreamGraph to index
- Optional: Ollama or LM Studio for local LLM integration
- An MCP client such as Claude Desktop or Cursor
Clone the repository and install dependencies
Clone DreamGraph from GitHub and install Node.js dependencies.
git clone https://github.com/mmethodz/dreamgraph.git
cd dreamgraph
npm install && npm run buildRun the platform installer
Use the provided install script for your platform to set up the dg CLI and all required components.
# Linux/macOS
bash scripts/install.sh --force
# Windows (PowerShell)
./scripts/install.ps1 -ForceInitialize a DreamGraph instance for your project
Create a named DreamGraph instance pointing at your repository. Choose stdio or http transport depending on your MCP client.
dg init --name my-project --project /path/to/your/repo --transport http --port 8100Start the DreamGraph instance
Start the instance in HTTP mode (for remote clients) or in the foreground for debugging.
dg start my-project --http
# Or in foreground:
dg start my-project --foregroundBootstrap the knowledge graph
Run the initial scan to analyze your repository and build the knowledge graph.
dg scan my-projectAdd DreamGraph to your MCP client configuration
Register the DreamGraph MCP endpoint in your Claude Desktop or Cursor configuration.
{
"mcpServers": {
"dreamgraph": {
"command": "dg",
"args": ["start", "my-project", "--foreground"],
"env": {
"DG_ALLOW_INPROCESS_PLUGINS": "true"
}
}
}
}Dreamgraph Examples
Client configuration
Claude Desktop JSON config for a DreamGraph instance running in foreground stdio mode.
{
"mcpServers": {
"dreamgraph": {
"command": "dg",
"args": ["start", "my-project", "--foreground"],
"env": {
"DG_ALLOW_INPROCESS_PLUGINS": "true"
}
}
}
}Prompts to try
Example prompts that exercise DreamGraph's knowledge graph and reasoning capabilities.
- "Show me the current status of the my-project knowledge graph, including tension and ADR counts."
- "What are the causal dependencies between the UserService and the PaymentService modules?"
- "Run an enrichment cycle on my-project and report any new insights."
- "Capture an ADR for the decision to migrate from REST to GraphQL."
- "Generate documentation for the authentication module from the knowledge graph."Troubleshooting Dreamgraph
dg command not found after running the installer
Reload your shell profile with 'source ~/.bashrc' (Linux) or open a new PowerShell session (Windows). The installer adds the dg binary to your PATH, but the current session may not have picked it up yet.
Plugin support is unavailable or plugins fail to load
Set DG_ALLOW_INPROCESS_PLUGINS=true in the environment before starting the instance. Also verify that plugin trust settings are configured in the instance's instance.json file as described in the docs/setup-llm.md guide.
LLM enrichment cycles produce no results
DreamGraph uses local LLMs (Ollama at http://localhost:11434 or LM Studio at http://localhost:1234/v1) for enrichment. Ensure one of these services is running and a model is loaded. Refer to guide/04-llm-setup.md for complete LLM configuration blocks.
Frequently Asked Questions about Dreamgraph
What is Dreamgraph?
Dreamgraph is a Model Context Protocol (MCP) server that dreamgraph is a graph-first cognitive layer (graph → mcp → cli → dashboard → extension) that builds a persistent knowledge graph to reason, validate changes, and generate docs. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Dreamgraph?
Follow the installation instructions on the Dreamgraph GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Dreamgraph?
Dreamgraph works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Dreamgraph free to use?
Yes, Dreamgraph is open source and available under the NOASSERTION license. You can use it freely in both personal and commercial projects.
Dreamgraph Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to Dreamgraph? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.
MemPalace
★ 52.6kA local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically
Kratos
★ 25.7k🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.
Context Mode
★ 15.4kAn MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm
Memu
★ 13.7kMemory for 24/7 proactive agents like OpenClaw.
MemOS
★ 9.3kMemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u
Everos
★ 5.4kBuild, evaluate, and integrate long-term memory for self-evolving agents.
Browse More Knowledge & Memory MCP Servers
Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Dreamgraph in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Dreamgraph?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.