A specialized integration bringing MiniMax-M2.7 large language model capabilities and extended context handling to OpenClaw.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install openspace-llm-xiaowei
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install openspace-llm-xiaowei using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is OpenSpace LLM Integration?
OpenSpace LLM Integration is a technical bridge that adapts the HKUDS OpenSpace project into a high-performance skill for the OpenClaw ecosystem. It specifically leverages the MiniMax-M2.7 model, which provides a massive 204k context window, enabling the agent to handle complex reasoning and long-form content generation with ease. This Openclaw Skills addition is designed for developers who need reliable, long-context LLM support within their automated workflows.
The skill addresses several technical hurdles found in standard API implementations, such as connection stability and timeout management. By providing built-in proxy support and a robust retry mechanism, it ensures that long-running tasks—like generating 3000-word articles or deep-dive code analysis—remain consistent and successful even in challenging network environments.
OpenSpace LLM Integration Use Cases
- Generating long-form technical articles and documentation ranging from 1000 to 3000 words.
- Analyzing massive text datasets or codebases within a 204k context window.
- Implementing stable AI workflows in environments requiring local HTTP/HTTPS proxies.
- Adding specialized writing, coding, and analysis capabilities to your existing Openclaw Skills library.
How OpenSpace LLM Integration Works
- The skill initializes by reading environment variables for the MiniMax API key, model selection, and proxy settings.
- When a command like chat, write, or analyze is triggered, the system formats the prompt for the MiniMax-M2.7 engine.
- The request is routed through a localized proxy (if configured) to ensure a stable connection to the API base.
- If the API experiences a transient failure or timeout, an automatic retry logic executes up to three times to recover the session.
- The skill processes the long-context response and returns the generated content, code, or analysis directly to the OpenClaw workspace.
OpenSpace LLM Integration Setup
First, install the required library dependency:
pip install openspace
Next, configure your environment variables in your .env file or system environment to enable the Openclaw Skills functionality:
# MiniMax API Settings
OPENSPACE_MODEL=minimax/MiniMax-M2.7
OPENSPACE_API_BASE=https://api.minimax.chat/v1
OPENSPACE_API_KEY=your_minimax_api_key
# Proxy Settings (Optional)
HTTP_PROXY=http://127.0.0.1:10810
HTTPS_PROXY=http://127.0.0.1:10810
# Timeout Configuration
OPENSPACE_TIMEOUT=300
OPENSPACE_MAX_RETRIES=3
Finally, verify the connection by running the test script:
cd workspace/skills/openspace-llm
python openspace_llm.py test
OpenSpace LLM Integration Data Schema & Taxonomy
The skill manages its operations through the following configuration schema:
| Variable | Default | Purpose |
|---|---|---|
| OPENSPACE_MODEL | minimax/MiniMax-M2.7 | Defines the specific LLM model to be called |
| OPENSPACE_API_BASE | https://api.minimax.chat/v1 | The official endpoint for the MiniMax API |
| OPENSPACE_TIMEOUT | 300 | Maximum allowed time for generation in seconds |
| OPENSPACE_MAX_RETRIES | 3 | Number of times the skill will attempt to reconnect on failure |
OpenSpace LLM Integration Advanced Features
- Support for MiniMax-M2.7 with a 204k context window for comprehensive data ingestion.
- Automatic proxy detection and support for HTTP/HTTPS local tunnels.
- Extended generation capabilities allowing for articles exceeding 3000 words without timeout errors.
- Specialized task modes: Chat (Q&A), Write (Long-form), Analyze (Structural analysis), and Code (Programming tasks).
- Stabilized integration fixes for FastMCP, ensuring compatibility with modern Openclaw Skills deployments.
SKILL.md
Loading
Related Openclaw Skills
Vehicle Survival Kit
An essential guide for drivers to master roadside repairs, emergency response, and proactive vehicle maintenance.
PDF Label Data Extractor
An intelligent PDF data extraction tool that transforms complex product labels into structured Excel spreadsheets with high precision.
Skill Security Checker
A comprehensive security auditor designed to scan and verify the safety of third-party AI agent skills before deployment.
Smart Model Selector
An intelligent routing system that automatically selects the most efficient Qwen model based on task complexity to optimize performance and cost.
Polaroid Photo Generator
An AI-powered tool that generates retro instant-film photos with authentic vintage aesthetics using the Neta AI API.
Image Pro Visual Designer
A professional AI visual design agent that autonomously analyzes content to generate sophisticated illustration prompts and high-quality images.
Featured*
