What is the Context Graph?
The Context Graph is a persistent context graph that gives your AI agents memory across conversations. Without it, your agent forgets everything between sessions. With it, your agent can:- Remember facts, decisions, preferences, and context across sessions
- Recall past information by searching the context graph
- Relate entities to each other (e.g. “John works at Acme Corp”)
- Invalidate outdated information when things change
When to use it
- Your agent needs to recall past interactions or user preferences
- You want structured knowledge (entities + relationships) instead of flat text
- You need cross-session memory for coding assistants, support agents, or project tools
- You want to plug memory into any MCP-compatible client (Cursor, Claude, VS Code)
How it works
Your AI assistant (Cursor, Claude, etc.)
Calls tools like
remember, recall, relate automatically during conversations.MCP (Model Context Protocol)
The open transport protocol that connects AI assistants to the Context Graph. Think of MCP as the pipe. The Context Graph is what flows through it.
Example
Here is an interactive live environment where you can test the comparison. On the left, a standard agent without memory. On the right, the same agent with a real Context Graph via the playground proxy. For this Overview demo, the right side is preloaded with code best practices. Try asking: “How should I format a React component?”Next steps
Quickstart
Get the Context Graph running in your MCP client in minutes
Configuration
Self-hosted setup, transport modes, environment variables
Tools & Resources
All 7 tools and 4 resources your AI assistant can use
Try it yourself
Test the Context Graph interactively in our playground