Skip to content
MCP server

Hicortex — AI Fleet Memory

Shared memory so every AI coding agent you run learns from what the others did

Runs locallyStatus and history
Pricing
Free
Platforms
self-hosted, CLI
Runs
Locally
Version
0.27.1
Listing updated
3 days ago

About Hicortex — AI Fleet Memory

Hicortex — AI Fleet Memory is a free MCP server for knowledge and memory. It runs locally on your machine and is started by your AI client.

Hicortex tackles the way agents forget decisions between sessions and when summarised context shrinks. It keeps one memory behind all agents, so a correction made in one session is available to the whole fleet. Supported agents named are Claude Code, Hermes, OpenClaw, Pi and OpenCode.

The registry description mentions nightly self-correction and recall on every prompt. It is self-hosted: raw sessions stay on the user's machine, and the site says it is free for personal use. A local server needs no token, while a remote server uses HICORTEX_SERVER_URL and a bearer token, shown by hicortex status. The npm package is @gamaze/hicortex.

It suits developers running several agents or models who want identity and history to survive a model swap.

Install

Run in a terminal

claude mcp add hicortex --env HICORTEX_AUTH_TOKEN='<HICORTEX_AUTH_TOKEN>' -- npx -y @gamaze/hicortex

Add to claude_desktop_config.json

{
  "mcpServers": {
    "hicortex": {
      "command": "npx",
      "args": [
        "-y",
        "@gamaze/hicortex"
      ],
      "env": {
        "HICORTEX_AUTH_TOKEN": "<HICORTEX_AUTH_TOKEN>"
      }
    }
  }
}

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "hicortex": {
      "command": "npx",
      "args": [
        "-y",
        "@gamaze/hicortex"
      ],
      "env": {
        "HICORTEX_AUTH_TOKEN": "<HICORTEX_AUTH_TOKEN>"
      }
    }
  }
}

Add to .vscode/mcp.json

{
  "servers": {
    "hicortex": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@gamaze/hicortex"
      ],
      "env": {
        "HICORTEX_AUTH_TOKEN": "<HICORTEX_AUTH_TOKEN>"
      }
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "hicortex": {
      "command": "npx",
      "args": [
        "-y",
        "@gamaze/hicortex"
      ],
      "env": {
        "HICORTEX_AUTH_TOKEN": "<HICORTEX_AUTH_TOKEN>"
      }
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "hicortex": {
      "command": "npx",
      "args": [
        "-y",
        "@gamaze/hicortex"
      ],
      "env": {
        "HICORTEX_AUTH_TOKEN": "<HICORTEX_AUTH_TOKEN>"
      }
    }
  }
}

Configuration

  • HICORTEX_AUTH_TOKENBearer token for a remote Hicortex server (server prints it via `hicortex status`). Optional — a local server needs no token.
  • HICORTEX_SERVER_URLURL of a remote Hicortex server (e.g. https://your-server:8787). Optional — omit for a local server on this machine.

What it does

Fleet-wide memory
One store behind every agent.
Per-prompt recall
Relevant history is surfaced on each prompt.
Nightly self-correction
Memory is refined overnight.
Local or remote
Run locally or point at a server with a token.
Model-independent
Memory persists when the model changes.

Good for

  • Keep decisions across Claude Code sessions
  • Share learnings between agents
  • Avoid re-asking answered questions
  • Run a team memory server

Pricing

Free

Free for personal use

Prices change. Check hicortex.gamaze.com before you buy.

Hicortex — AI Fleet Memory FAQ

Is it free?

The site says free for personal use.

Do sessions leave my machine?

Raw sessions do not; it is self-hosted.

How do I connect to a remote server?

Set HICORTEX_SERVER_URL and HICORTEX_AUTH_TOKEN.

Which agents?

Claude Code, Hermes, OpenClaw, Pi and OpenCode.

Is Hicortex — AI Fleet Memory free?

Yes. Hicortex — AI Fleet Memory is free to use.

How do I add Hicortex — AI Fleet Memory to Claude Code?

Run this command in your terminal: claude mcp add hicortex --env HICORTEX_AUTH_TOKEN='<HICORTEX_AUTH_TOKEN>' -- npx -y @gamaze/hicortex

What are the best alternatives to Hicortex — AI Fleet Memory?

The closest alternatives to Hicortex — AI Fleet Memory are Codebase Memory, XERJ, Claude Code Ultimate Guide, Nautilus Compass Memory and note1.

Alternatives to Hicortex — AI Fleet Memory

  1. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  2. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  3. MCP server for searching the Claude Code Ultimate Guide from any MCP client

    Runs locally
    • Open source
    • 6.5K GitHub stars
    • AI models and LLM tooling
  4. Local-first long-term memory layer for AI agents, served over MCP

    Not checked yet
    • 5 tools
    • Remote
    • Open source
    • 1.3K GitHub stars
    • Knowledge and memory
  5. note1

    MCP server

    MCP server giving AI assistants search and summaries across your note1 meetings

    • 4 tools
    • Remote
    • Free trial
    • 1 GitHub star
    • Productivity