AI路由器

Quick Start

Terminal Demo

$ npx a3m-router serve
╔════════════════════════════════════════════════════════════╗
║                     A3M Router v2.9.2                      ║
║                🔀 Intelligent LLM Gateway                 ║
╠════════════════════════════════════════════════════════════╣
║  ✅ Proxy:     http://localhost:8787                      ║
║  ✅ Dashboard: http://localhost:8787/dashboard             ║
║  ✅ Health:    http://localhost:8787/health               ║
╚════════════════════════════════════════════════════════════╝

[GROQ]  ✅ 145ms  |  [DEEPSEEK]  ✅ 230ms  |  [KIMI]  ✅ 312ms
[ANTHROPIC]  ✅ 520ms  |  [OPENAI]  ✅ 480ms  |  [QWEN]  ✅ 290ms

🧠 Memory: 1,247 queries cached | 💰 Today: $2.34 / $50.00 budget

$ npx a3m-router route "Design a clinical trial for oncology"

🔀 Routing Decision:
   Query: "Design a clinical trial for oncology"
   
   📊 Complexity: 1.00 (premium)
   🏷️  Tier: premium
   
   ✅ Route to: openai/gpt-4o ($2.50/1M tokens)
   🔄 Fallback: anthropic/claude-3.5-sonnet
   
   💡 Signals: medical(+0.35) + design(+0.20) + multi-step(+0.15)

$ npx a3m-router cost

💰 Cost Analytics (May 2024)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 Total Spend:     $127.45 / $500.00 budget
 Daily Average:   $4.27
 Queries:         28,392
 
📈 By Provider:          📊 By Tier:
 Groq:        $42.30  ████████ 33%   premium:   $89.10  70%
 DeepSeek:    $51.20  █████████ 40%   mid:       $28.90  23%
 Claude:      $28.90  █████     23%   cheap:     $7.45    6%
 GPT-4o-mini: $5.05   █         4%    free:      $2.00    1%

🚨 Budget Alert: Engineering team at 80% ($160 / $200)

---

TypeScript SDK

adaptive-memory-multi-model-router/sdk';

const router = new A3MRouter();

// Route a query — returns model + tier + cost + complexity
const decision = router.route("Review this contract for liability clauses");
// → { model: "anthropic/claude-3.5-sonnet", tier: "premium",
//     cost: 0.008, complexity: 0.87, isExpert: true }

// Analyze why it chose that model
const features = router.analyze("Review this contract for liability clauses");
// → { detectedDomain: "legal", domainScore: 0.35, hasCode: false,
//     requiresReasoning: true, complexity: 0.87 }

Python SDK

from a3m import A3MRouter

async with A3MRouter() as router:
    # Route without executing
    decision = await router.route("Write a Python function to sort an array")
    print(decision.model, decision.tier, decision.cost)
    # → groq/llama-3.3-70b cheap 0.0004

    # Execute via OpenAI-compatible chat
    response = await router.chat("What is 2+2?", model="auto")
    print(response["choices"][0]["message"]["content"])

Works with ANY OpenAI SDK — zero code changes

from openai import OpenAI client = OpenAI(base_url="http://localhost:8787/v1", api_key="not-needed")

response = client.chat.completions.create( model="auto", # ← intelligent routing kicks in messages=[{"role": "user", "content": "Hello!"}] ) ```

REST API

```bash

API Reference

Full API docs: docs/API.md

---

Package Exports

// Main — everything
adaptive-memory-multi-model-router';

// SDK — clean high-level API
adaptive-memory-multi-model-router/sdk';

// Individual modules
adaptive-memory-multi-model-router/cache';
adaptive-memory-multi-model-router/guardrails';
adaptive-memory-multi-model-router/cost';
adaptive-memory-multi-model-router/analytics';
adaptive-memory-multi-model-router/memory';
adaptive-memory-multi-model-router/langchain';
adaptive-memory-multi-model-router/providers';
adaptive-memory-multi-model-router/server';

// Ensemble (P0) — core differentiator
adaptive-memory-multi-model-router/ensemble';

// Query-type presets (P1)
adaptive-memory-multi-model-router/presets';

// Persistent memory (P3)
adaptive-memory-multi-model-router/memory';

---

When to Use MCTS vs Heuristic Scoring

MCTS vs Rule-Based Assignment

A3M Router (per-query routing)
└── Multi-signal scoring → fast (<1ms)
    └── Tier selection → cheapest available

TMLPD Orchestration (multi-agent workflows)
└── MCTS → optimal agent assignment
    ├── UCB1 selection
    ├── State tree expansion
    └── Reward backpropagation

Example workflow:

User: "Research AI safety, write a report, have experts review it, then publish"

MCTS decomposes into:
  research → deepseek (cost-effective for research)
  write → claude (best for structured long-form)
  review → expert-agents (human-in-loop or specialist LLM)
  publish → codex (can handle deployment code)

Router assigns each sub-task to optimal agent, tracks outcomes, learns preferences.

---

Comparison

Also consider: 9router, ClawRouter, Plano, Helicone

---