← Back to directory

DreamGraph

Community

A graph-governed architecture cognition layer for MCP-enabled software projects.

GitHub source repository ↗

★ 114 Stars Category · Dev Tools Popular Source revision d64e853f1dce

58FMRS · C

Reliability

8/20

Security and permissions

8/20

Maintenance

14/20

Documentation

16/20

Setup experience

12/20

DreamGraph is a complex, feature-rich MCP server that provides graph-based architecture cognition. It is well-suited for growing projects requiring persistent memory and governance, but has a steep learning curve. It is recommended to test in an isolated environment and pay attention to security configuration.

Read the FMRS scoring method →

DreamGraph is a governed architecture cognition layer for MCP-enabled software projects. It combines an instance-scoped daemon, CLI, architect beta, VS Code extension, dashboard, and a persistent knowledge graph so project understanding is grounded in source, ADRs, workflows, tests, runtime observations, and human review rather than any single file read or isolated chat turn. It maintains a structured graph of features, workflows, data-model entities, architecture decisions, UI registry elements, tensions, and candidate hypotheses, enabling cross-repo reasoning, live database schema introspection, dream cycles, temporal/causal analysis, and an Adaptive Future Engine.

Tools

The tool list has not been reviewed yet.

Setup

To install from source:

Clone the repository: git clone https://github.com/mmethodz/dreamgraph.git
Change directory: cd dreamgraph
Run the installer script:

- Windows PowerShell: ./scripts/install.ps1 -Force
- Linux/macOS Bash: bash scripts/install.sh --force

Or manually build: npm install and npm run build.
Create an instance with dg init, and start the daemon with dg start my-project --foreground for stdio or --http for HTTP.

Fit and risk

Best for

Developers whose codebases have grown beyond short-term memory, seeking AI that understands the system and explains changes.
Architects, system engineers, and product builders needing an architecture intelligence layer.
Projects using MCP clients like Claude Desktop or VS Code that benefit from persistent graph memory.

Not for

Users seeking a lightweight chat assistant rather than a complex knowledge graph system.
Projects preferring simple tooling without persistent state or architecture governance.
Environments without Node.js 20+ or a compatible shell.

Required permissions

Read project files to build the knowledge graph (scan, enrich).
Read and write instance configuration and database (SQLite by default, optional PostgreSQL).
Execute `dg` CLI commands to manage daemon lifecycle.
VS Code extension permissions: file access, editor integration, daemon connection.
Potential network access (via HTTP daemon) and LLM API or local model server connections.

Risks and side effects

Cognitive outputs are advisory until backed by governed evidence or explicit review; expired or rejected ideas remain inspectable but not authoritative.
Ensure instance configuration is secured, especially when using HTTP transport; do not expose the daemon on untrusted networks.
Plugins (when enabled) must be trusted; untrusted plugins may pose risks, but mechanisms for gating and trust banners exist.
Backup data before major upgrades, as migration scripts may be needed for older versions (e.g., pre-v8.2.6).

Troubleshooting

Verify Node.js 20+ and npm are installed: `node --version`, `npm --version`.
Check daemon status: `dg status my-project`, ensure the port is available and not occupied.
Restart the daemon and reload VS Code window if connection issues occur.
For LLM setup, verify environment variables (e.g., Ollama/LM Studio URL) are correctly configured.
Check firewall or proxy settings if connections fail.

Use cases

Understanding large codebases: ask 'Where does auth really happen?', 'What breaks if I change this?'

Making large changes safer by using graph context, ADRs, tool traces, and multi-repo awareness.

Bridging vibe coding and serious engineering: prototype quickly while accumulating structure, provenance, and lifecycle history.

Multi-repo systems: build graph links across repositories that share workflows, APIs, databases, and ownership.

Architect work: project-bound chat, selected-plan scope, runtime provenance, and auditable tool traces.

Supported clients

Claude DesktopFull support

VS CodeFull support

Related MCP servers

Compare with other MCP servers