
sage
MCP server by github.com/l33tdawg/sage
Persistent, consensus-validated institutional memory for AI agents. Runs locally.
About sage
sage is an MCP (Model Context Protocol) server published by l33tdawg in the official MCP registry, listed under Autonomous Agents on Loomal. Persistent, consensus-validated institutional memory for AI agents. Runs locally.
It ships as a Docker image (ghcr.io/l33tdawg/sage:4.0.0), so any MCP client that can launch a local process can run it.
Development happens in the open at github.com/l33tdawg/sage, where the project has earned 229 GitHub stars.
Use sage with your agent
claude mcp add sage -- docker run -i --rm ghcr.io/l33tdawg/sage:4.0.0{
"mcpServers": {
"sage": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/l33tdawg/sage:4.0.0"
]
}
}
}ghcr.io/l33tdawg/sage:4.0.0Frequently asked questions
- What is sage?
- sage is an MCP (Model Context Protocol) server by l33tdawg in the Autonomous Agents category. Persistent, consensus-validated institutional memory for AI agents. Runs locally.
- How do I connect sage to Claude, Cursor, or another MCP client?
- Install sage from its oci package (ghcr.io/l33tdawg/sage:4.0.0) and register it under "mcpServers" in your client's MCP configuration — for example claude_desktop_config.json or Cursor's mcp.json — then restart the client.
- Is sage open source?
- Yes — the source code is public at github.com/l33tdawg/sage, with 229 GitHub stars.
- Can AI agents pay to use sage?
- Not yet through Loomal — sage is listed as a free directory entry. If its maintainer verifies ownership, they can set per-call USDC pricing that agents pay over x402, with settlement on Base.
More Autonomous Agents MCP servers

claude-flow
59.1k
AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.

tldraw
47.7k
Draw and visually collaborate with your agents on tldraw's canvas.

OpenMetadata
14.2k
Official OpenMetadata MCP: governed context and business semantics for AI assistants and agents.

PraisonAI
8.1k
AI Agents Framework with Self Reflection and MCP support

Azure MCP Server
3.3k
All Azure MCP tools to create a seamless connection between AI agents and Azure services.

agent-device
2.7k
Let AI agents inspect, control, and debug real iOS, Android, desktop, and TV apps
Listing data from the official MCP registry and GitHub, refreshed periodically. Not affiliated with the maintainer unless claimed. Maintain sage? Claim this listing free by verifying GitHub ownership, or contact us.