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.
Follow the repository instructions for this skill and your agent. Review the files and dependencies before adding it to your workflow.
SkillHub CLI
skillhub install cutechicken99/marl-middlewareInspect the source and compatibility requirements, then follow its installation steps.
Give your agent the source link and ask it to inspect instructions and dependencies before explaining the installation steps.
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.
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).
docker run -p 8080:8080 vidraft/marl
pip install marl-middleware
python -m marl serve --port 8080
Use https://huggingface.co/spaces/VIDraft/MARL directly in your browser.
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.
Switch modes by appending ::mode to any model name:
| model value | Engine | What it does |
|---|---|---|
| `g... |
These signals come from indexed source analysis and may lag behind changes. Check the current source files.
# 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.
[](https://pypi.org/project/marl-middleware/)
[](https://github.com/Vidraft/MARL)
[](https://huggingface.co/spaces/VIDraft/MARL)
[](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...Bambu Lab 3D printer control and automation. Activate when user mentions: printer status, 3D printing, slice, analyze model, generate 3D, AMS filament, print monitor, Bambu Lab, or any 3D printing task. Full pi...
Generative Engine Optimization (GEO) for AI search visibility. Optimize content to appear in ChatGPT, Perplexity, Claude, and Google AI Overviews. Use when optimizing websites, pages, or content for LLM discove...
Agents can sign plugins, rotate credentials without losing identity, and publicly attest to behavior.
Send and receive P2P messages using disposable numbers and PINs. No servers, no accounts. Use for human notifications, approval flows, and agent-to-agent communication.