Dreamgraph

v1.0.0Knowledge & Memorystable

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.

agent-memoryai-agentsautonomous-agentscausal-discoverycausal-inference
Share:
85
Stars
0
Downloads
0
Weekly
0/5

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

Knowledge graph reasoning and validation
Persistent cognitive architecture
Documentation generation from graphs
mmethodz

Maintainer

LicenseNOASSERTION
Languagetypescript
Versionv1.0.0
UpdatedMay 21, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx dreamgraph

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

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
1

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 build
2

Run 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 -Force
3

Initialize 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 8100
4

Start 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 --foreground
5

Bootstrap the knowledge graph

Run the initial scan to analyze your repository and build the knowledge graph.

dg scan my-project
6

Add 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.

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.

Quick Config Preview

{ "mcpServers": { "dreamgraph": { "command": "npx", "args": ["-y", "dreamgraph"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

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.

33,000+ ServersFree & Open SourceStep-by-Step Guides