create-snipara (NPX)

One-command setup and maintenance for Snipara MCP + snipara-companion, with optional RLM-Runtime for local execution.

npx create-snipara

Interactive Setup

Run npx create-sniparain your project directory. You'll be prompted for:

Maintenance Commands

npx create-snipara doctor

npx create-snipara repair

Execution Environments

When you select RLM-Runtime during setup, you'll be asked if you want to run rlm init to configure the execution environment:

You can also configure the environment later by running rlm init manually.

API Key Requirements

Key Types

Command Line Options

Basic usage

npx create-snipara

With project API key

npx create-snipara --api-key rlm_your_project_key

With team API key (access all team projects)

npx create-snipara --team-key rlm_your_team_key

Specify project slug

npx create-snipara --slug my-project

Runtime only - no Snipara API key needed

npx create-snipara --runtime-only

Skip local companion CLI

npx create-snipara --skip-companion

Skip specific installations

npx create-snipara --skip-mcp # Skip snipara-mcp

npx create-snipara --skip-runtime # Skip rlm-runtime

npx create-snipara --skip-hooks # Skip Claude Code hooks

npx create-snipara --skip-test # Skip connection test

Accept all defaults (non-interactive)

npx create-snipara -y --api-key rlm_xxx --slug my-project

What Gets Created

.mcp.json

{

  "mcpServers": {

    "snipara": {

      "type": "http",

      "url": "https://api.snipara.com/mcp/your-project",

      "headers": {

        "X-API-Key": "rlm_your_key"

      }

    },

    "rlm-runtime": {

      "type": "http",

      "url": "http://localhost:8765/mcp",

      "headers": {}

    }

  }

}

Claude Code Hooks (if selected)

• snipara-startup.sh - Restores session context
• snipara-session.sh — Auto-remembers commits
• snipara-compact.sh — Saves context before compaction

Local Companion Pack

If you install the local companion, create-snipara also generates a small project-local starter pack under .snipara/companion.

• README.md - client-aware usage guidance and starter commands
• commands.json - machine-readable command presets for local workflows

Companion Workflows

The companion CLI is a thin local facade over hosted Snipara workflows. It is useful when you want repeatable local commands in addition to MCP access.

rlm-hook query --query "recent auth decisions"

rlm-hook plan --query "implement webhook retry hardening"

rlm-hook multi-query --queries "recent incidents" "open decisions"

rlm-hook orchestrate --query "map auth architecture"

rlm-hook load-document --path docs/architecture/auth.md

rlm-hook events recent --limit 20

rlm-hook task-commit --summary "Shipped retry hardening"

These commands print human-readable output by default. Add --json when you need the raw hosted response.

Environment Files

Updates .env.example and .env.local with:

Snipara Configuration

SNIPARA_API_KEY=your_api_key

SNIPARA_PROJECT_SLUG=your-project

RLM-Runtime LLM Provider (if configured)

OPENAI_API_KEY=sk-...

or

ANTHROPIC_API_KEY=sk-ant-...

After Installation

For Claude Code / Cursor

1. Restart your AI client
2. MCP tools are automatically available

For Claude Desktop

1. Restart Claude Desktop
2. Config is at ~/Library/Application Support/Claude/claude_desktop_config.json

RLM-Runtime Usage

MCP Tools (no LLM API key needed):

Your AI client (Claude, GPT, etc.) provides the LLM — no additional API key required.

CLI Commands (requires LLM API key):

For rlm run and rlm agent, you need an LLM provider API key:

Set your LLM provider

export OPENAI_API_KEY=sk-...

or

export ANTHROPIC_API_KEY=sk-ant-...

Run commands

rlm init # Initialize configuration

rlm run --env docker # Run with Docker isolation

rlm agent "task" # Autonomous agent mode

rlm visualize # Launch trajectory dashboard

Available MCP Tools

If you enable hook-compatible local tooling, the install can also forward canonical lifecycle events into Snipara's automation API. That lets local adapters feel closer to a local-memory workflow while keeping review and persistence centralized.

After setup, you have access to the current 102-tool MCP contract across context, memory, automation, analytics, and orchestration:

Requirements

• Node.js 18+
• Python 3.10+ (for snipara-mcp and rlm-runtime)
• Docker (optional, for RLM-Runtime isolation)

Links

Next Steps