Downloads

MemQ downloads and public artifacts.

Use this page for ZIP packages, local starter files, raw MCP metadata, and public config artifacts. If you want setup steps by editor, start with the editor setup guide.

Learn setup steps Download artifacts

Raw MCP config artifact

Copy this when you already know where your client stores MCP config

API-Key MCP Config

{
  "mcpServers": {
    "memq": {
      "type": "http",
      "url": "https://mcp.multinex.ai/mcp/v1",
      "transport": "streamable-http",
      "headers": {
        "Authorization": "Bearer $MEMQ_API_KEY"
      }
    }
  }
}

Agent-ready discovery

Agents can now discover MemQ before a human copies the config: the homepage and MemQ page advertise RFC 8288 Link headers, the API catalog points to service docs and OpenAPI descriptions, the MCP server card exposes the hosted MemQ endpoint, and protected-resource metadata points back to Billing Manager for auth.

API catalog MCP server card OAuth resource metadata

Config file locations

Claude Code~/.claude/mcp.json

Cursor~/.cursor/mcp.json

VS Code.vscode/mcp.json (workspace) or User Settings

Claude Desktop~/Library/Application Support/Claude/claude_desktop_config.json

AntigravitySettings → MCP Servers

Create the API key

Billing Manager activates access and usage meters

Start checkout, then create a MemQ API key in the Billing Dashboard.

The key activates the right plan, namespace access, AI call meters, memory read/write limits, blocked-attempt reporting, and tool activity visibility.

Start Checkout API Keys

You're connected

Verify first recall before adding real project context

That's it. Write one small decision, ask your agent to find it, and confirm the namespace. Then add real code patterns, decisions, debugging sessions, and team runbooks.

35 hosted MCP tools auto-discoveredFirst recall test completeWorks across sessionsTeam-wide knowledge sharingNo SDK required

Agent skills

Download the MemQ Operations skill for the agent runtime you use. Each package teaches REUNION-first startup, shared-knowledge lookup, event-aware memory usage, checkpointing, and degraded mode behavior.

Codex

MemQ Operations for Codex

Official Codex skill package with SKILL.md, OpenAI UI metadata, and package metadata.

Install target: ~/.codex/skills/memq-operations

Download ZIP View SKILL.md

Claude Code

MemQ Operations for Claude Code

Claude skill that teaches REUNION-first startup, shared-knowledge lookup, checkpoints, and event-aware usage.

Install target: Included with memq-brain or install from ZIP

Download ZIP View SKILL.md

OpenClaw / Open Skills

MemQ Operations for OpenClaw

Portable Open Skills markdown for OpenClaw and compatible agent runtimes.

Install target: Point BORICLAW_OPEN_SKILLS_DIR at the extracted folder

Download ZIP View markdown

Starter repos

Each starter repo includes a 10-minute setup, MCP config, .env.example, save/recall examples, and a smoke test proving save -> fresh request -> recall.

First install proof

memq-mcp-starter

Minimal MCP memory setup with a save, restart, and recall continuity test.

GitHub Local files

Team memory

memq-team-handoff-starter

Team namespace handoff flow for developer teams that need shared agent context.

GitHub Local files

Editor onboarding

memq-cursor-claude-starter

Editor-focused setup for Cursor, Claude, VS Code, and Antigravity.

GitHub Local files

Workflow agents

memq-n8n-agent-starter

Workflow-agent memory example for n8n MCP Client and MCP Client Tool nodes.

GitHub Local files

MCP snippets

Copy the exact server block for your client. All snippets use MEMQ_API_KEY from the environment so secrets stay out of config files.

Claude Desktop / Claude Code~/.claude/mcp.json or claude_desktop_config.json

{
  "mcpServers": {
    "memq": {
      "type": "http",
      "url": "https://mcp.multinex.ai/mcp/v1",
      "transport": "streamable-http",
      "headers": {
        "Authorization": "Bearer $MEMQ_API_KEY"
      }
    }
  }
}

Cursor~/.cursor/mcp.json

{
  "mcpServers": {
    "memq": {
      "type": "http",
      "url": "https://mcp.multinex.ai/mcp/v1",
      "transport": "streamable-http",
      "headers": {
        "Authorization": "Bearer $MEMQ_API_KEY"
      }
    }
  }
}

VS Code.vscode/mcp.json

{
  "mcp": {
    "servers": {
      "memq": {
        "type": "http",
        "url": "https://mcp.multinex.ai/mcp/v1",
        "transport": "streamable-http",
        "headers": {
          "Authorization": "Bearer $MEMQ_API_KEY"
        }
      }
    }
  }
}

Antigravity / Gemini-style.gemini/mcp.json or Antigravity MCP settings

{
  "mcpServers": {
    "memq": {
      "type": "http",
      "url": "https://mcp.multinex.ai/mcp/v1",
      "transport": "streamable-http",
      "headers": {
        "Authorization": "Bearer $MEMQ_API_KEY"
      }
    }
  }
}

n8n MCP ClientMCP Client node credentials

{
  "serverUrl": "https://mcp.multinex.ai/mcp/v1",
  "transport": "streamable-http",
  "headers": {
    "Authorization": "Bearer $MEMQ_API_KEY"
  }
}

Generic Streamable HTTP MCPClient-specific MCP server registry

{
  "name": "memq",
  "type": "http",
  "url": "https://mcp.multinex.ai/mcp/v1",
  "transport": "streamable-http",
  "headers": {
    "Authorization": "Bearer $MEMQ_API_KEY"
  }
}

Browser OAuth fallback

API keys are recommended for headless agents and repeatable setup. Interactive clients that prefer browser approval can use OAuth instead. Start from checkout →

OAuth Config

{
  "mcpServers": {
    "memq": {
      "type": "http",
      "url": "https://mcp.multinex.ai/mcp/v1",
      "transport": "streamable-http",
      "auth": {
        "type": "oauth2",
        "discoveryUrl": "https://billing.multinex.ai/.well-known/oauth-authorization-server"
      }
    }
  }
}

Discovery Probe

curl -I https://multinex.ai/
curl -I https://multinex.ai/memq/
curl -L https://multinex.ai/.well-known/api-catalog
curl -L https://multinex.ai/.well-known/oauth-protected-resource
curl -L https://multinex.ai/.well-known/mcp/server-card.json