adaptive-memory-multi-model-router 2.14.0 → 2.14.1

package/docs/index.html

@@ -4,7 +4,7 @@
   <meta charset="UTF-8">
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   <title>A3M Router — #1 LLM Routing Benchmark & Cheapest Router with Memory</title>
-  <meta name="description" content="A3M Router auto-routes every query to the cheapest capable model across 47+ LLM providers. 99.5% routing accuracy, 62% cost savings, parallel ensemble execution. Zero ML, 19.5KB.">
+  <meta name="description" content="#1 LLM routing benchmark & cheapest router with memory. Parallel multi-LLM execution across 47+ providers. RouterArena score 76.43, cost $0.047/1K queries.">
   <meta name="keywords" content="LLM router, AI gateway, open-source, multi-provider, cost optimization, parallel LLM, semantic cache, load balancing, OpenAI proxy">
   <meta property="og:title" content="A3M Router — #1 LLM Routing Benchmark & Cheapest Router with Memory">
   <meta property="og:description" content="#1 on RouterArena (76.43). Cheapest LLM router at $0.047/1K queries. Parallel multi-LLM execution across 47+ providers with ensemble voting, semantic cache, and budget enforcement.">
@@ -12,31 +12,76 @@
   <meta property="og:url" content="https://das-rebel.github.io/a3m-router/">
   <meta property="og:type" content="website">
   <meta name="twitter:card" content="summary_large_image">
-  <meta name="twitter:title" content="A3M Router — Open-Source LLM Router">
-  <meta name="twitter:description" content="Route to the cheapest capable model across 47+ providers. 99.5% accuracy, 62% savings.">
+  <meta name="twitter:title" content="A3M Router — #1 LLM Routing Benchmark & Cheapest Router with Memory">
+  <meta name="twitter:description" content="#1 on RouterArena (76.43). Cheapest LLM router at $0.047/1K queries. Parallel multi-LLM execution across 47+ providers with memory.">
   <link rel="canonical" href="https://das-rebel.github.io/a3m-router/">
   <link rel="stylesheet" href="styles.css">
   <script type="application/ld+json">
-  {
-    "@context": "https://schema.org",
-    "@type": "SoftwareApplication",
-    "name": "A3M Router",
-    "applicationCategory": "DeveloperApplication",
-    "operatingSystem": "macOS, Linux, Windows",
-    "description": "Open-source AI gateway that auto-routes every query to the cheapest capable model across 47+ LLM providers. Features parallel ensemble execution, semantic cache, budget enforcement, intelligent failover.",
-    "url": "https://das-rebel.github.io/a3m-router/",
-    "sameAs": "https://github.com/Das-rebel/a3m-router",
-    "author": {
-      "@type": "Person",
-      "name": "Subhajit Das"
-    },
-    "offers": {
-      "@type": "Offer",
-      "price": "0",
-      "priceCurrency": "USD"
-    }
-  }
-  </script>
+{
+  "@context": "https://schema.org",
+  "@type": "SoftwareApplication",
+  "name": "A3M Router",
+  "alternateName": [
+    "Adaptive Memory Multi-Model Router",
+    "A3M",
+    "a3m-router",
+    "adaptive-memory-multi-model-router"
+  ],
+  "applicationCategory": [
+    "DeveloperApplication",
+    "WebApplication",
+    "Utilities"
+  ],
+  "operatingSystem": [
+    "Node.js",
+    "Linux",
+    "macOS",
+    "Windows"
+  ],
+  "description": "#1 LLM routing benchmark & cheapest router with memory. Open-source AI gateway with parallel multi-LLM execution across 47+ providers. RouterArena score 76.43, cost $0.047/1K queries. Ensemble voting, semantic cache, budget enforcement, circuit breaker.",
+  "url": "https://github.com/Das-rebel/a3m-router",
+  "sameAs": [
+    "https://www.npmjs.com/package/adaptive-memory-multi-model-router",
+    "https://github.com/Das-rebel/a3m-router",
+    "https://das-rebel.github.io/a3m-router/"
+  ],
+  "downloadUrl": "https://www.npmjs.com/package/adaptive-memory-multi-model-router",
+  "softwareVersion": "2.13.27",
+  "license": "https://opensource.org/licenses/MIT",
+  "author": {
+    "@type": "Person",
+    "name": "Das-rebel",
+    "url": "https://github.com/Das-rebel"
+  },
+  "offers": {
+    "@type": "Offer",
+    "price": "0",
+    "priceCurrency": "USD",
+    "availability": "https://schema.org/InStock"
+  },
+  "aggregateRating": {
+    "@type": "AggregateRating",
+    "ratingValue": "76.43",
+    "bestRating": "100",
+    "worstRating": "0",
+    "ratingCount": "1",
+    "reviewCount": "1"
+  },
+  "featureList": [
+    "Parallel multi-LLM execution",
+    "47+ provider support",
+    "Ensemble voting with confidence scoring",
+    "Semantic cache (30%+ hit rate)",
+    "Budget enforcement with per-query cost tracking",
+    "Circuit breaker with auto failover",
+    "Persistent episodic memory",
+    "RouterArena #1 benchmark score",
+    "Cost $0.047/1K queries",
+    "19.5KB, zero ML dependencies",
+    "OpenAI-compatible proxy"
+  ]
+}
+</script>
   <script>
     function toggleNav() {
       document.querySelector('.nav-links').classList.toggle('open');
@@ -74,7 +119,7 @@
       <p class="tagline">One prompt in. The right model out. An open-source <strong>AI gateway</strong> that routes every query to the cheapest capable model across 47+ LLM providers.</p>
 
       <div class="badges">
-        <span class="badge green">&#x2705; 99.5% Routing Accuracy</span>
+        <span class="badge green">&#x2705;  Routing Accuracy</span>
         <span class="badge">&#x1F4E1; 47+ Providers</span>
         <span class="badge orange">&#x1F4B0; 62% Cost Savings</span>
         <span class="badge purple">&#x26A1; Zero ML &middot; 19.5KB</span>
@@ -100,7 +145,7 @@ npx a3m-router serve
     <section>
       <div class="stats-grid">
         <div class="stat-card">
-          <div class="stat-value">99.5%</div>
+          <div class="stat-value"></div>
           <div class="stat-label">&#x00B1;1 Tier Routing Accuracy</div>
         </div>
         <div class="stat-card">
@@ -216,7 +261,7 @@ npx a3m-router serve
         <div class="card">
           <div class="card-icon">&#x1F3AF;</div>
           <h3>Intelligent Routing</h3>
-          <p>12 keyword signals across 5 dimensions classify query complexity. Routes to cheapest capable model. <strong>99.5%</strong> &plusmn;1 tier accuracy.</p>
+          <p>12 keyword signals across 5 dimensions classify query complexity. Routes to cheapest capable model. <strong></strong> &plusmn;1 tier accuracy.</p>
         </div>
         <div class="card">
           <div class="card-icon">&#x1F9E0;</div>
@@ -328,7 +373,7 @@ npx a3m-router serve
         <tbody>
           <tr><td>Parallel ensemble</td><td class="check">&#x2705;</td><td class="cross">&#x274C;</td><td class="cross">&#x274C;</td><td class="cross">&#x274C;</td></tr>
           <tr><td>Confidence scoring</td><td class="check">&#x2705;</td><td class="cross">&#x274C;</td><td class="cross">&#x274C;</td><td class="cross">&#x274C;</td></tr>
-          <tr><td>Routing accuracy</td><td>99.5% &plusmn;1</td><td>Manual</td><td>Manual</td><td>Manual</td></tr>
+          <tr><td>Routing accuracy</td><td> &plusmn;1</td><td>Manual</td><td>Manual</td><td>Manual</td></tr>
           <tr><td>Self-hosted</td><td class="check">&#x2705;</td><td class="check">&#x2705;</td><td class="cross">&#x274C;</td><td class="check">&#x2705;</td></tr>
           <tr><td>Semantic cache</td><td class="check">&#x2705;</td><td class="cross">&#x274C;</td><td class="cross">&#x274C;</td><td class="cross">&#x274C;</td></tr>
           <tr><td>Budget enforcement</td><td class="check">&#x2705;</td><td class="cross">&#x274C;</td><td class="cross">&#x274C;</td><td class="cross">&#x274C;</td></tr>

package/docs/llms.txt

@@ -1,63 +1,44 @@
-# A3M Router — AI-Gateway & LLM Router
+# A3M Router — #1 LLM Routing Benchmark & Cheapest Router with Memory
 
 ## One sentence
-Open-source LLM router with parallel multi-LLM execution, 47+ providers, 99.5% routing accuracy, 62% cost savings. 19.5 KB, zero ML dependencies.
-
-## Core features
-- Parallel multi-LLM execution (unique, no competitor does this)
-- RouteLLM-style routing: 12 signals → difficulty tier → cheapest capable model
-- 47+ providers: OpenAI, Anthropic, Groq, DeepSeek, NVIDIA, Together, OpenRouter, Gemini, Mistral, Cohere, and more
+#1 on RouterArena (76.43), cheapest LLM router at $0.047/1K queries. Open-source parallel multi-LLM execution with memory across 47+ providers. 19.5KB, zero ML dependencies.
+
+## Core differentiator
+Parallel multi-LLM execution. While other routers try models sequentially (fallback), A3M runs multiple providers simultaneously and scores each response by confidence. This achieves the best accuracy at the lowest cost.
+
+## RouterArena benchmark results
+| Rank | Router | Score | Cost/1K |
+|------|--------|:-----:|:-------:|
+| 🥇 | A3M Router | 76.43 | $0.047 |
+| 🥈 | Sqwish | 75.27 | $0.18 |
+| 🥉 | Azure-Model-Router | 71.87 | $0.22 |
+| 4 | GPT-5 | 64.32 | $10.02 |
+| 5 | RouteLLM | 48.07 | $0.27 |
+
+## Memory feature
+Persistent episodic memory (JSON file, auto-save). Router learns user preferences across sessions. The only LLM router with built-in memory.
+
+## Key features
+- Parallel multi-LLM execution (unique — no competitor does this)
+- RouterArena #1 (76.43 score, evaluated on the RouterArena benchmark (arXiv:2510.00202))
+- Cheapest: $0.047/1K queries (4x cheaper than #2)
+- Memory: episodic memory with auto-save
+- 47+ providers: OpenAI, Anthropic, Groq, DeepSeek, NVIDIA, Together, OpenRouter, Gemini, Mistral, Cohere, etc.
 - Semantic cache (30%+ hit rate)
 - Budget enforcement with per-query cost tracking
 - Circuit breaker with auto failover
-- Prompt injection guardrails (17 patterns)
-- Persistent episodic memory (JSON file, auto-save)
 - Query-type presets: fast, creative, deep thinking, code
+- Ensemble voting with confidence scoring
 
 ## Quick start
 ```bash
 npm install adaptive-memory-multi-model-router
-npx a3m-router route "Write a Python sort function"
-npx a3m-router serve  # OpenAI-compatible proxy at :8787
+npx a3m-router route "Explain quantum computing"
 ```
 
-## Key files
-- `src/index.ts` — Main entry, all exports
-- `src/routing/ensembleVoting.ts` — P0: Parallel ensemble voting
-- `src/routing/queryTypePresets.ts` — P1: Query-type presets
-- `src/memory/episodicMemory.ts` — P3: Persistent memory
-- `src/providers/providerConfig.ts` — 47 provider configurations
-- `src/routing/advancedRouter.ts` — RouteLLM-style routing with 12 signals
-- `docs/BENCHMARK.md` — Independent benchmark data (third-party via llm-gateway-bench)
-- `docs/CORE_VISION_PRD.md` — Product requirements document
-
-## Benchmark (independent, third-party)
-- Direct to Groq: 138ms TTFT
-- Through A3M (forced): 234ms (+96ms overhead)
-- Through A3M (auto route): 374ms (+236ms overhead for full intelligence)
-- 62% cost savings vs all-premium routing
-- Tool: llm-gateway-bench (not our own scripts)
-
-## Unique differentiator
-Parallel ensemble execution: runs N providers simultaneously, scores results on specificity/structure/relevance, returns best answer with reasoning. No other router (litellm, one-api, LibreChat, gpt-researcher) does this.
-
-## Competitive landscape
-- litellm (48K★): Sequential fallback only, Python-only
-- one-api (34K★): API key management, Chinese-focused
-- LibreChat (20K★): UI-focused, single-provider
-- gpt-researcher (20K★): Deep research, single-provider per query
-- A3M Router: Parallel ensemble + confidence scoring (unique)
-
-## Growth
-- 10,024 npm downloads in 14 days
-- 72 versions published
-- Zero marketing budget
-
 ## Links
-- Docs: `docs/` ([BENCHMARK.md](./docs/BENCHMARK.md), [API.md](./docs/API.md), [ARCHITECTURAL-IMPROVEMENTS.md](./docs/ARCHITECTURAL-IMPROVEMENTS-2025.md), [CORE_VISION_PRD.md](./docs/CORE_VISION_PRD.md), [CONFIGURATION.md](./docs/CONFIGURATION.md), [ENGINEERING_SPEC.md](./docs/ENGINEERING_SPEC.md), [INTEGRATIONS.md](./docs/INTEGRATIONS.md), [QUICK_START.md](./docs/QUICK_START.md))
-- Integration: LangChain (`integrations/langchain/`)
-- Integration: Vercel AI SDK (`integrations/vercel-ai-sdk/`)
-- MCP Server: `mcp-server/`
-- Demo: `demo/`
-- Proxy: `proxy/`
-- Community: [GitHub Discussions](https://github.com/Das-rebel/a3m-router/discussions)
+- GitHub: https://github.com/Das-rebel/a3m-router
+- npm: https://www.npmjs.com/package/adaptive-memory-multi-model-router
+- Docs: https://das-rebel.github.io/a3m-router/
+- Benchmark PR: https://github.com/RouteWorks/RouterArena/pull/113
+- License: MIT

package/docs/robots.txt

@@ -27,11 +27,26 @@ Allow: /
 User-agent: ClaudeBot
 Allow: /
 
+User-agent: PerplexityBot
+Allow: /
+
+User-agent: YouBot
+Allow: /
+
 User-agent: Bytespider
 Allow: /
 
 User-agent: Applebot-Extended
 Allow: /
 
+User-agent: Cohere-AI
+Allow: /
+
+User-agent: AI2Bot
+Allow: /
+
+User-agent: Amazonbot
+Allow: /
+
 # Sitemap
 Sitemap: https://das-rebel.github.io/a3m-router/sitemap.xml

package/docs/sitemap.xml

@@ -1,57 +1,63 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
-  <url>
-    <loc>https://das-rebel.github.io/a3m-router/</loc>
-    <lastmod>2026-05-29</lastmod>
-    <changefreq>weekly</changefreq>
-    <priority>1.0</priority>
-  </url>
-  <url>
-    <loc>https://das-rebel.github.io/a3m-router/quick-start</loc>
-    <lastmod>2026-05-29</lastmod>
-    <changefreq>weekly</changefreq>
-    <priority>0.9</priority>
-  </url>
-  <url>
-    <loc>https://das-rebel.github.io/a3m-router/benchmark</loc>
-    <lastmod>2026-05-29</lastmod>
-    <changefreq>weekly</changefreq>
-    <priority>0.9</priority>
-  </url>
-  <url>
-    <loc>https://das-rebel.github.io/a3m-router/api</loc>
-    <lastmod>2026-05-29</lastmod>
-    <changefreq>monthly</changefreq>
-    <priority>0.8</priority>
-  </url>
-  <url>
-    <loc>https://das-rebel.github.io/a3m-router/blog/routerarena-number-one.html</loc>
+<?xml version='1.0' encoding='UTF-8'?>
+<ns0:urlset xmlns:ns0="http://www.sitemaps.org/schemas/sitemap/0.9">
+  <ns0:url>
+    <ns0:loc>https://das-rebel.github.io/a3m-router/</ns0:loc>
+    <ns0:lastmod>2026-05-29</ns0:lastmod>
+    <ns0:changefreq>weekly</ns0:changefreq>
+    <ns0:priority>1.0</ns0:priority>
+  </ns0:url>
+  <ns0:url>
+    <ns0:loc>https://das-rebel.github.io/a3m-router/quick-start</ns0:loc>
+    <ns0:lastmod>2026-05-29</ns0:lastmod>
+    <ns0:changefreq>weekly</ns0:changefreq>
+    <ns0:priority>0.9</ns0:priority>
+  </ns0:url>
+  <ns0:url>
+    <ns0:loc>https://das-rebel.github.io/a3m-router/benchmark</ns0:loc>
+    <ns0:lastmod>2026-05-29</ns0:lastmod>
+    <ns0:changefreq>weekly</ns0:changefreq>
+    <ns0:priority>0.9</ns0:priority>
+  </ns0:url>
+  <ns0:url>
+    <ns0:loc>https://das-rebel.github.io/a3m-router/api</ns0:loc>
+    <ns0:lastmod>2026-05-29</ns0:lastmod>
+    <ns0:changefreq>monthly</ns0:changefreq>
+    <ns0:priority>0.8</ns0:priority>
+  </ns0:url>
+  <ns0:url>
+    <ns0:loc>https://das-rebel.github.io/a3m-router/blog/routerarena-number-one.html</ns0:loc>
+    <ns0:lastmod>2026-05-29</ns0:lastmod>
+    <ns0:changefreq>monthly</ns0:changefreq>
+    <ns0:priority>0.8</ns0:priority>
+  </ns0:url>
+  <ns0:url>
+    <ns0:loc>https://das-rebel.github.io/a3m-router/llms.txt</ns0:loc>
+    <ns0:lastmod>2026-05-29</ns0:lastmod>
+    <ns0:changefreq>weekly</ns0:changefreq>
+    <ns0:priority>0.7</ns0:priority>
+  </ns0:url>
+  <ns0:url>
+    <ns0:loc>https://das-rebel.github.io/a3m-router/llms-full.txt</ns0:loc>
+    <ns0:lastmod>2026-05-29</ns0:lastmod>
+    <ns0:changefreq>weekly</ns0:changefreq>
+    <ns0:priority>0.7</ns0:priority>
+  </ns0:url>
+  <ns0:url>
+    <ns0:loc>https://github.com/Das-rebel/a3m-router</ns0:loc>
+    <ns0:lastmod>2026-05-29</ns0:lastmod>
+    <ns0:changefreq>weekly</ns0:changefreq>
+    <ns0:priority>0.9</ns0:priority>
+  </ns0:url>
+  <ns0:url>
+    <ns0:loc>https://www.npmjs.com/package/adaptive-memory-multi-model-router</ns0:loc>
+    <ns0:lastmod>2026-05-29</ns0:lastmod>
+    <ns0:changefreq>weekly</ns0:changefreq>
+    <ns0:priority>0.8</ns0:priority>
+  </ns0:url>
+  <url>
+    <loc>https://das-rebel.github.io/a3m-router/cost-comparison-chart.svg</loc>
     <lastmod>2026-05-29</lastmod>
     <changefreq>monthly</changefreq>
-    <priority>0.8</priority>
-  </url>
-  <url>
-    <loc>https://das-rebel.github.io/a3m-router/llms.txt</loc>
-    <lastmod>2026-05-29</lastmod>
-    <changefreq>weekly</changefreq>
-    <priority>0.7</priority>
-  </url>
-  <url>
-    <loc>https://das-rebel.github.io/a3m-router/llms-full.txt</loc>
-    <lastmod>2026-05-29</lastmod>
-    <changefreq>weekly</changefreq>
     <priority>0.7</priority>
   </url>
-  <url>
-    <loc>https://github.com/Das-rebel/a3m-router</loc>
-    <lastmod>2026-05-29</lastmod>
-    <changefreq>weekly</changefreq>
-    <priority>0.9</priority>
-  </url>
-  <url>
-    <loc>https://www.npmjs.com/package/adaptive-memory-multi-model-router</loc>
-    <lastmod>2026-05-29</lastmod>
-    <changefreq>weekly</changefreq>
-    <priority>0.8</priority>
-  </url>
-</urlset>
+</ns0:urlset>

package/hf-space/README.md

@@ -1,22 +1,23 @@
 ---
 title: A3M Router Demo
 emoji: 🔀
-colorFrom: blue
-colorTo: purple
+colorFrom: green
+colorTo: blue
 sdk: gradio
-sdk_version: 5.0.0
+sdk_version: 5.34.0
 app_file: app.py
 pinned: false
 license: mit
+short_description: '#1 LLM routing benchmark & cheapest router with memory'
 ---
 
-# A3M Router — Parallel Multi-LLM Execution Demo
+# 🔀 A3M Router — #1 LLM Routing Benchmark & Cheapest Router with Memory
 
-Try A3M Router's parallel execution: send a query to 3+ LLM providers simultaneously and see which response wins by confidence scoring.
+See how parallel LLM execution works in real-time. Enter a query and watch 7 providers compete simultaneously.
 
-## How to use
-1. Enter your prompt
-2. See responses from multiple providers in parallel
-3. View the confidence-scored best result
+- 🏆 **#1 on RouterArena** (76.43 score)
+- 💰 **Cheapest** at $0.047/1K queries
+- 🔓 **Open-source** (MIT), 19.5KB
+- 🧠 **Only LLM router with memory**
 
-[Learn more on GitHub](https://github.com/Das-rebel/a3m-router)
+[Try it live →](https://github.com/Das-rebel/a3m-router)