OpenClaw

marl-middleware

Multi-stage multi-agent reasoning middleware that reduces LLM hallucination by 70%+. 9 specialized emergence engines for invention, creative, pharma, genomics, chemistry, ecology, law, recipe, and document generation.

cutechicken990 来源安装数☆ 0 仓库 Stars

查看来源 ↗安装与使用 SKILL.md ↗

安装与使用

请根据来源仓库和你的 AI 工具说明安装此技能。先阅读技能文件和依赖要求，再添加到工作流。

SkillHub CLI

skillhub install cutechicken99/marl-middleware

打开来源仓库，查看说明和兼容环境后，按来源提供的命令或步骤安装。

将来源链接提供给你的 Agent，让它先读取说明、核对依赖，并向你说明将执行的安装步骤。

查看来源 ↗使用指南

技能说明

MARL Enhance — Brain Upgrade for Your Agent

The 3rd approach after fine-tuning & RAG. MARL restructures how LLMs reason at runtime — not their weights. One line to integrate, 70%+ hallucination reduction, 9 domain-specific emergence engines.

What It Does

Before MARL: Your agent calls the LLM once → gets an answer (might hallucinate).

After MARL: Your agent calls MARL → MARL runs a multi-stage expert pipeline → hypothesis, solving, auditing, adversarial verification, synthesis → returns a deeply verified answer.

Your Agent → MARL → Multi-stage Pipeline → Any LLM → Verified Answer

Results: 70%+ hallucination reduction · 94.8% of improvement from self-correction · Verified on FINAL Bench (HuggingFace Global Top 5 dataset).

Setup

Option A: Docker (Recommended — all platforms)

docker run -p 8080:8080 vidraft/marl

Option B: pip (Linux x86_64)

pip install marl-middleware
python -m marl serve --port 8080

Option C: HuggingFace Space (No install — try instantly)

Use https://huggingface.co/spaces/VIDraft/MARL directly in your browser.

Connect to OpenClaw

Set your config.json:

{
  "llm": {
    "baseURL": "http://localhost:8080/v1",
    "model": "gpt-5.4"
  }
}

That's it. Every LLM call now passes through MARL's multi-stage reasoning pipeline.

9 Emergence Modes

Switch modes by appending ::mode to any model name:

model value	Engine	What it does
`g...

来源信息

Source: github
Repository: openclaw/skills
Path: skills/cutechicken99/marl-middleware
Version: —
Commit: dfca7433707d2ab99f40a3bbc0b1da33b2a4ae99
分类来源: rules
状态: active
可见性: public

这些信息来自收录时的来源分析，可能滞后；使用前请核对最新来源文件。

来源内容

SKILL.md

# MARL Enhance — Brain Upgrade for Your Agent

**The 3rd approach after fine-tuning & RAG.** MARL restructures how LLMs reason at runtime — not their weights. One line to integrate, 70%+ hallucination reduction, 9 domain-specific emergence engines.

[![PyPI](https://img.shields.io/pypi/v/marl-middleware?color=6366f1&label=PyPI)](https://pypi.org/project/marl-middleware/)
[![GitHub](https://img.shields.io/badge/GitHub-Repository-24292e?logo=github)](https://github.com/Vidraft/MARL)
[![Demo](https://img.shields.io/badge/🤗%20Demo-HuggingFace-ff9d00)](https://huggingface.co/spaces/VIDraft/MARL)
[![FINAL Bench](https://img.shields.io/badge/🏆%20FINAL%20Bench-Global%20%235-16a34a)](https://huggingface.co/spaces/FINAL-Bench/Leaderboard)

## What It Does

Before MARL: Your agent calls the LLM once → gets an answer (might hallucinate).

After MARL: Your agent calls MARL → MARL runs a multi-stage expert pipeline → hypothesis, solving, auditing, adversarial verification, synthesis → returns a deeply verified answer.

```
Your Agent → MARL → Multi-stage Pipeline → Any LLM → Verified Answer
```

**Results:** 70%+ hallucination reduction · 94.8% of improvement from self-correction · Verified on FINAL Bench (HuggingFace Global Top 5 dataset).

## Setup

### Option A: Docker (Recommended — all platforms)

```bash
docker run -p 8080:8080 vidraft/marl
```

### Option B: pip (Linux x86_64)

```bash
pip install marl-middleware
python -m marl serve --port 8080
```

### Option C: HuggingFace Space (No install — try instantly)

Use `https://huggingface.co/spaces/VIDraft/MARL` directly in your browser.

## Connect to OpenClaw

Set your `config.json`:

```json
{
  "llm": {
    "baseURL": "http://localhost:8080/v1",
    "model": "gpt-5.4"
  }
}
```

That's it. Every LLM call now passes through MARL's multi-stage reasoning pipeline.

## 9 Emergence Modes

Switch modes by appending `::mode` to any model name:

| model value | Engine | What it does |
|-------------|--------|-------------|
| `g...

搜索