sage — Claude Code MCP server: what it does, how to install
A local MCP server that stores agent experience, checks new records, and recalls context in later sessions. Built for work that continues over time.
claude mcp add sage -- docker run -i --rm ghcr.io/l33tdawg/sage:11.24.2What sage does
sage connects an MCP client to a local memory node. An agent can save design choices, failed approaches, and lessons for later sessions, then retrieve context related to the current work. New records go through an admission check, carry an agent identity and access rules, and can be inspected in the local CEREBRUM dashboard.
Memory stays local by default. A personal setup uses one validator, while a multi-validator network relies on a BFT quorum. These checks decide whether a record is accepted; they do not establish that every remembered claim is true or alter model weights. Recall depends on recorded content, configuration, and whether the agent uses its tools.
The server connects to Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, and Zed. The command-line setup needs Docker because it starts ghcr.io/l33tdawg/sage:11.24.2. Developers can also integrate through the Python SDK or a signed REST API.
What it helps with
- carry decisions across agent sessions
- retrieve earlier context for a task
- control which agents can use a memory
- trace who created a record
- review the history of stored experience
Example prompts for the agent
- Save the decision about this library so it is available in later sessions.
- Recall which approach to this task already failed.
- Show me in
CEREBRUMwhat the agent stored for this project.
How to install sage
Platform CLI
claude mcp add sage -- docker run -i --rm ghcr.io/l33tdawg/sage:11.24.2Platform CLI
codex mcp add sage -- docker run -i --rm ghcr.io/l33tdawg/sage:11.24.2Config file
{
"mcpServers": {
"sage": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/l33tdawg/sage:11.24.2"
]
}
}
}Config file
{
"servers": {
"sage": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/l33tdawg/sage:11.24.2"
]
}
}
}Platform CLI
gemini mcp add sage docker run -i --rm ghcr.io/l33tdawg/sage:11.24.2Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about sage
How do I install sage in Claude Code?
Run claude mcp add sage -- docker run -i --rm ghcr.io/l33tdawg/sage:11.24.2.
What does sage do?
It gives AI agents local memory for storing experience and retrieving relevant context later. Records pass through an admission check, use access rules, and keep an action history.
What is required to install sage with the command?
Docker is required because the command starts the ghcr.io/l33tdawg/sage:11.24.2 container image. The MCP client also needs access to the running local node.
