create-snipara

One-command setup for Snipara MCP + RLM-Runtime - context optimization, semantic memory, and safe code execution for AI agents.

npx create-snipara

What It Does

• Installs snipara-mcp - MCP server for context-optimized documentation queries
• Installs rlm-runtime - Safe code execution with Docker isolation
• Configures .mcp.json - Ready for Claude Code, Cursor, Claude Desktop
• Sets up hooks - Session memory automation (Claude Code)
• Updates environment files - Adds API key configuration

Interactive Setup

npx create-snipara

You'll be prompted for:

| Prompt | Description | |--------|-------------| | Project slug | Auto-detected from git remote or directory name | | Project ID | Optional, for advanced use cases | | API key type | Project key, Team key, Sign up, or Skip | | API key | Your Snipara API key | | AI client | Claude Code, Cursor, Claude Desktop, or other | | Packages | Choose what to install | | LLM provider | OpenAI, Anthropic, or None (for rlm run/rlm agent CLI) | | Run rlm init | Optional - configure execution environment (sandbox/docker/local) |

API Key Requirements

| Tool | Snipara API Key | LLM API Key (OpenAI/Anthropic) | |------|-----------------|-------------------------------| | execute_python MCP | Not needed | Not needed (your AI client is the LLM) | | rlm_context_query MCP | Required | Not needed | | rlm_remember/rlm_recall | Required | Not needed | | rlm run / rlm agent CLI | Optional (for context) | Required |

Key Types

| Type | Description | |------|-------------| | Project API key | Access to a single project | | Team API key | Access to all projects in your team |

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
# (for execute_python MCP tool only)
npx create-snipara --runtime-only

# 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

# Full example with team key
npx create-snipara --team-key rlm_team_xxx --slug my-project --skip-hooks

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

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.

• execute_python    - Run Python in sandbox
• get_repl_context  - Get session variables
• set_repl_context  - Set session variables
• clear_repl_context - Clear session

Execution Environments:

| Environment | Description | Use Case | |-------------|-------------|----------| | sandbox | RestrictedPython, safe stdlib only | Default, most secure | | docker | Full Python in isolated container | Recommended for full features | | local | Full access, no isolation | Development only |

During setup, you can run rlm init to configure the default environment. Or configure later:

rlm init  # Interactive configuration

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

After setup, you have access to 43+ MCP tools:

| Category | Tools | |----------|-------| | Context | rlm_context_query, rlm_ask, rlm_search, rlm_sections | | Planning | rlm_plan, rlm_decompose, rlm_multi_query | | Memory | rlm_remember, rlm_recall, rlm_memories, rlm_forget | | Execution | execute_python, get_repl_context (via RLM-Runtime) | | Swarms | rlm_swarm_create, rlm_claim, rlm_task_create |

Requirements

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

Links

• Website: https://snipara.com
• Documentation: https://snipara.com/docs
• Dashboard: https://snipara.com/dashboard
• npm: https://www.npmjs.com/package/create-snipara
• Support: [email protected]

License

MIT