# Send Mixture of Agents to your agent
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
## Fast path
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
## Suggested prompts
### New install

```text
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
```
### Upgrade existing

```text
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
```
## Machine-readable fields
```json
{
  "schemaVersion": "1.0",
  "item": {
    "slug": "moa",
    "name": "Mixture of Agents",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/jscianna/moa",
    "canonicalUrl": "https://clawhub.ai/jscianna/moa",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadUrl": "/downloads/moa",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=moa",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "packageFormat": "ZIP package",
    "primaryDoc": "SKILL.md",
    "includedAssets": [
      "SKILL.md",
      "manifest.json",
      "scripts/moa-paid.js",
      "scripts/moa.js"
    ],
    "downloadMode": "redirect",
    "sourceHealth": {
      "source": "tencent",
      "slug": "moa",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-02T10:36:55.062Z",
      "expiresAt": "2026-05-09T10:36:55.062Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=moa",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=moa",
        "contentDisposition": "attachment; filename=\"moa-1.2.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "moa"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/moa"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    }
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/moa",
    "downloadUrl": "https://openagent3.xyz/downloads/moa",
    "agentUrl": "https://openagent3.xyz/skills/moa/agent",
    "manifestUrl": "https://openagent3.xyz/skills/moa/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/moa/agent.md"
  }
}
```
## Documentation

### Mixture of Agents (MoA)

TL;DR: Make 3 AI models argue with each other. Get an answer better than any single model. Cost: ~$0.03.

### A. Standalone CLI (Node.js)

export OPENROUTER_API_KEY="your-key"
node scripts/moa.js "Your complex question"

### B. OpenClaw Skill (Agent-orchestrated)

# Install
clawhub install moa

# Or copy to ~/clawd/skills/moa/

The agent can then invoke MoA for complex analysis tasks.

### Origin Story

The concept of "Mixture of Agents" comes from research showing LLMs can improve each other's outputs through collaboration. I built this for VC deal analysis—when evaluating startups, you want multiple perspectives, not one model's opinion.

The journey:

Started with 5 free OpenRouter models (Llama, Gemini, Mistral, Qwen, Nemotron)
Rate limits killed me at 2am during peak hours
Switched to 3 paid frontier specialists
Result: ~$0.03/query, answers better than any single model

### When to Use

Complex analysis — due diligence, market research, technical evaluation
Brainstorming — get diverse ideas, synthesize the best
Fact-checking — cross-reference across models with different training data
High-stakes decisions — when one model's blind spots could hurt you
Contrarian thinking — different models have different biases

When NOT to use:

Quick Q&A (too slow, 30-90s latency)
Real-time chat (not designed for streaming)
Simple lookups (overkill)

### Paid Tier (Default) — Recommended

RoleModel~LatencyStrengthProposer 1moonshotai/kimi-k2.523sLong context, strong reasoningProposer 2z-ai/glm-536sTechnical depth, different training corpusProposer 3minimax/minimax-m2.564sNuance catching, thorough analysisAggregatormoonshotai/kimi-k2.515sFast synthesis

Why these models?

Frontier-class but less congested than GPT-4/Claude
Different training data = genuinely different perspectives
Chinese models excel at certain reasoning tasks
Combined cost still cheaper than single Opus call

Cost breakdown:

3 proposers × ~$0.008 = $0.024
1 aggregator × ~$0.005 = $0.005
─────────────────────────────
Total: ~$0.029/query

### Free Tier (Fallback)

5 models: Llama 3.3 70B, Gemini 2.0 Flash, Mistral Small, Nemotron 70B, Qwen 2.5 72B

⚠️ Warning: Free tier hits rate limits during peak hours. Use --free flag only for testing.

### How It Works

┌─────────────┐
        │   PROMPT    │
        └──────┬──────┘
               │
    ┌──────────┼──────────┐
    ▼          ▼          ▼
┌────────┐ ┌────────┐ ┌────────┐
│Kimi 2.5│ │ GLM 5  │ │MiniMax │  ← Parallel (they "argue")
│(reason)│ │(depth) │ │(nuance)│
└───┬────┘ └───┬────┘ └───┬────┘
    │          │          │
    └──────────┼──────────┘
               ▼
       ┌──────────────┐
       │  AGGREGATOR  │
       │  (Kimi 2.5)  │
       │              │
       │ • Best of 3  │
       │ • Resolve    │
       │   conflicts  │
       │ • Synthesize │
       └──────┬───────┘
              ▼
       ┌──────────────┐
       │ FINAL ANSWER │
       │ (Synthesized)│
       └──────────────┘

### Function Signature

interface MoAOptions {
  prompt: string;           // Required: The question to analyze
  tier?: 'paid' | 'free';   // Default: 'paid'
}

interface MoAResult {
  synthesis: string;        // The final aggregated answer
}

// Throws on complete failure (all models down, invalid key)
// Returns partial synthesis if 1-2 models fail
async function handle(options: MoAOptions): Promise<string>

### CLI Usage

# Paid tier (default)
node scripts/moa.js "Your complex question"

# Free tier
node scripts/moa.js "Your question" --free

### Programmatic Usage

const { handle } = require('./scripts/moa.js');

const synthesis = await handle({ 
  prompt: "Analyze the competitive moats in AI code generation",
  tier: 'paid'
});

console.log(synthesis);

### Failure Modes

ScenarioBehavior1 proposer failsSynthesis from remaining 2 models2 proposers failSynthesis from 1 model (degraded)All proposers failReturns error messageInvalid API keyImmediate error with setup instructionsRate limit (free tier)Returns rate limit error

The system is designed to degrade gracefully. A 2/3 response is still valuable.

### VC Due Diligence

node scripts/moa.js "Analyze the competitive landscape for AI code generation. \\
Who has defensible moats? Who's likely to be commoditized? Be specific."

### Technical Evaluation

node scripts/moa.js "Compare RLHF vs DPO vs RLAIF for LLM alignment. \\
Which scales better? What are the failure modes of each?"

### Market Research

node scripts/moa.js "What are the emerging use cases for embodied AI in 2026? \\
Focus on robotics, drones, and autonomous systems. Include specific companies."

### Performance Expectations

MetricPaid TierFree TierP50 Latency~45s~60sP95 Latency~90s~120s+Success Rate>99%~80% (rate limits)Cost/Query~$0.03$0.00

### Tips

Be specific — Vague prompts get vague synthesis
Ask for structure — "Give me pros/cons" or "List top 5" helps the aggregator
Use for analysis, not chat — MoA shines for complex reasoning
Batch your queries — 30-90s per query, so plan accordingly

### Via ClawHub (Recommended)

clawhub install moa

### Manual

Copy skills/moa/ to your ~/clawd/skills/ directory
Set OPENROUTER_API_KEY in your environment
The agent can now invoke MoA for complex queries

### Environment Variables

VariableRequiredDescriptionOPENROUTER_API_KEYYesYour OpenRouter API key

Get your key at: https://openrouter.ai/keys

### Credits

MoA concept: Together AI Research
Implementation: @Scianna
Built for: OpenClaw
## Trust
- Source: tencent
- Verification: Indexed source record
- Publisher: jscianna
- Version: 1.2.0
## Source health
- Status: healthy
- Item download looks usable.
- Yavira can redirect you to the upstream package for this item.
- Health scope: item
- Reason: direct_download_ok
- Checked at: 2026-05-02T10:36:55.062Z
- Expires at: 2026-05-09T10:36:55.062Z
- Recommended action: Download for OpenClaw
## Links
- [Detail page](https://openagent3.xyz/skills/moa)
- [Send to Agent page](https://openagent3.xyz/skills/moa/agent)
- [JSON manifest](https://openagent3.xyz/skills/moa/agent.json)
- [Markdown brief](https://openagent3.xyz/skills/moa/agent.md)
- [Download page](https://openagent3.xyz/downloads/moa)