RLM-Runtime Integration

RLM-Runtime is a sandboxed Python execution environment that integrates with Snipara for context-aware code generation, autonomous agents, and multi-step task execution.

Installation

Or install manually:

pip install rlm-runtime[all]

Or install specific features:

Quick Start

rlm init

rlm run "Summarize the authentication flow"

rlm run --env docker "Parse and analyze logs"

rlm agent "Analyze all CSV files and generate a report"

Claude Code / Claude Desktop Setup

Add RLM-Runtime as an MCP server to get sandboxed Python execution in Claude. No API keys required for the runtime itself.

Step 1: Install with MCP support

pip install rlm-runtime[mcp]

Step 2: Add to your MCP configuration

Add to ~/.mcp.json (Claude Code) or ~/.claude/claude_desktop_config.json (Claude Desktop):

{

  "mcpServers": {

    "rlm": {

      "command": "rlm",

      "args": ["mcp-serve"]

    }

  }

}

Step 3: Add Snipara for context (optional but recommended)

Combine RLM-Runtime with Snipara for context-aware code execution:

{

  "mcpServers": {

    "rlm": {

      "command": "rlm",

      "args": ["mcp-serve"]

    },

    "snipara": {

      "type": "http",

      "url": "https://api.snipara.com/mcp/YOUR_PROJECT",

      "headers": {

        "X-API-Key": "rlm_YOUR_API_KEY"

      }

    }

  }

}

Available MCP Tools

Execution Environments

When to Use RLM-Runtime vs Direct MCP

Use Direct Snipara MCP Tools For:

• Documentation Q&A - "What's the tech stack?"
• Code lookup - "Where is auth handled?"
• Simple retrieval - "List all API endpoints"

Use RLM-Runtime For:

• Multi-step code tasks - "Implement OAuth integration"
• Complex reasoning - "Refactor auth to use JWT"
• Iterative refinement - "Optimize this function"
• Multi-file changes - "Add validation to all endpoints"

Python API

import asyncio

from rlm import RLM

async def main():

    rlm = RLM(

        model="gpt-4o-mini",

        environment="docker",

        max_depth=4,

    )

    result = await rlm.completion("Analyze and fix the auth bug")

    print(result.response)

asyncio.run(main())

Configuration

Create rlm.toml in your project:

[rlm]

backend = "litellm"

model = "gpt-4o-mini"

environment = "docker"

max_depth = 4

# Snipara integration

snipara_api_key = "rlm_..."

snipara_project_slug = "your-project"

# Docker settings

docker_image = "python:3.11-slim"

docker_memory = "512m"

Or use environment variables:

export RLM_MODEL=gpt-4o-mini

export RLM_ENVIRONMENT=docker

export SNIPARA_API_KEY=rlm_...

export SNIPARA_PROJECT_SLUG=my-project

CLI Commands

Safety Limits

Links

Next Steps