adaptive-memory-multi-model-router 2.5.5 → 2.7.0

package/dist/sdk.js

@@ -5,118 +5,127 @@
  * Clean wrapper class providing a better DX than raw exports.
  *
  * Usage:
- *   const { A3MRouter } = require('adaptive-memory-multi-model-router/sdk');
+ *   import { A3MRouter } from 'adaptive-memory-multi-model-router/sdk';
+ *
  *   const router = new A3MRouter();
+ *
+ *   // Route a query (no execution, just model selection)
  *   const decision = router.route("What is 2+2?");
  *   console.log(decision.model, decision.tier, decision.cost);
+ *
+ *   // Start the OpenAI-compatible proxy server
+ *   const proxyURL = await router.serve(8787);
+ *
+ *   // Use with any OpenAI SDK
+ *   import OpenAI from 'openai';
+ *   const client = new OpenAI({ baseURL: router.proxyURL });
+ *   const response = await client.chat.completions.create({
+ *     model: 'auto',
+ *     messages: [{ role: 'user', content: 'Hello' }]
+ *   });
  */
-
-const advancedRouter = require("./routing/advancedRouter");
-const proxyServer = require("./server/proxyServer");
-
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.A3MRouter = void 0;
+exports.createSDK = createSDK;
+const advancedRouter_1 = require("./routing/advancedRouter");
+const proxyServer_1 = require("./server/proxyServer");
 // ============================================================
 // A3MRouter SDK Class
 // ============================================================
-
 class A3MRouter {
-  constructor(config = {}) {
-    this.config = config;
-    this._proxyURL = null;
-  }
-
-  /**
-   * Route a query — returns model selection without executing it.
-   *
-   * @param {string} query - The user prompt to route
-   * @returns {object} Routing decision with model, tier, cost, complexity
-   */
-  route(query) {
-    const features = advancedRouter.extractQueryFeatures(query);
-    const result = advancedRouter.routeQuery(query, this.config.providers);
-
-    return {
-      model: result.primary_model || 'unknown',
-      tier: this.classifyTier(features.complexity),
-      cost: result.estimated_cost || 0,
-      complexity: features.complexity,
-      reasoning: result.reasoning || '',
-      fallbackModels: result.fallback_models || [],
-      isFree: (result.estimated_cost || 0) === 0,
-      isExpert: features.complexity >= 0.65,
-    };
-  }
-
-  /**
-   * Route multiple queries in batch.
-   *
-   * @param {string[]} queries - Array of user prompts
-   * @returns {object[]} Array of routing decisions
-   */
-  routeBatch(queries) {
-    advancedRouter.routeBatch(queries); // warm the internal cache
-    return queries.map((q) => this.route(q));
-  }
-
-  /**
-   * Get model recommendation for a task description.
-   *
-   * @param {string} task - Task description
-   * @returns {object} Routing decision
-   */
-  recommend(task) {
-    advancedRouter.recommendForTask(task);
-    return this.route(task);
-  }
-
-  /**
-   * Start the OpenAI-compatible proxy server.
-   *
-   * @param {number} port - Port to listen on (default: 8787)
-   * @returns {Promise<string>} The proxy base URL
-   */
-  async serve(port = 8787) {
-    proxyServer.createProxyServer(port);
-    this._proxyURL = `http://localhost:${port}/v1`;
-    return this._proxyURL;
-  }
-
-  /**
-   * Get the proxy URL. Available after serve() is called.
-   */
-  get proxyURL() {
-    return this._proxyURL || 'http://localhost:8787/v1';
-  }
-
-  /**
-   * Extract features from a query for debugging or analysis.
-   *
-   * @param {string} query - The user prompt to analyze
-   * @returns {object} Detailed feature breakdown
-   */
-  analyze(query) {
-    return advancedRouter.extractQueryFeatures(query);
-  }
-
-  /**
-   * Classify a complexity score into a named tier.
-   */
-  classifyTier(complexity) {
-    if (complexity < 0.20) return 'free';
-    if (complexity < 0.45) return 'cheap';
-    if (complexity < 0.65) return 'mid';
-    return 'premium';
-  }
+    config;
+    _proxyURL = null;
+    constructor(config = {}) {
+        this.config = config;
+    }
+    /**
+     * Route a query — returns model selection without executing it.
+     *
+     * @param query - The user prompt to route
+     * @returns Routing decision with model, tier, cost, complexity
+     */
+    route(query) {
+        const features = (0, advancedRouter_1.extractQueryFeatures)(query);
+        const result = (0, advancedRouter_1.routeQuery)(query, this.config.providers);
+        return {
+            model: result.primary_model || 'unknown',
+            tier: this.classifyTier(features.complexity),
+            cost: result.estimated_cost || 0,
+            complexity: features.complexity,
+            reasoning: result.reasoning || '',
+            fallbackModels: result.fallback_models || [],
+            isFree: (result.estimated_cost || 0) === 0,
+            isExpert: features.complexity >= 0.65,
+        };
+    }
+    /**
+     * Route multiple queries in batch.
+     *
+     * @param queries - Array of user prompts
+     * @returns Array of routing decisions
+     */
+    routeBatch(queries) {
+        (0, advancedRouter_1.routeBatch)(queries); // warm the internal cache
+        return queries.map((q) => this.route(q));
+    }
+    /**
+     * Get model recommendation for a task description.
+     *
+     * @param task - Task description (e.g. "code generation", "summarization")
+     * @returns Routing decision
+     */
+    recommend(task) {
+        (0, advancedRouter_1.recommendForTask)(task);
+        return this.route(task);
+    }
+    /**
+     * Start the OpenAI-compatible proxy server.
+     *
+     * @param port - Port to listen on (default: 8787)
+     * @returns The proxy base URL (e.g. "http://localhost:8787/v1")
+     */
+    async serve(port = 8787) {
+        (0, proxyServer_1.createProxyServer)(port);
+        this._proxyURL = `http://localhost:${port}/v1`;
+        return this._proxyURL;
+    }
+    /**
+     * Get the proxy URL. Available after serve() is called,
+     * otherwise returns the default.
+     */
+    get proxyURL() {
+        return this._proxyURL || 'http://localhost:8787/v1';
+    }
+    /**
+     * Extract features from a query for debugging or analysis.
+     *
+     * @param query - The user prompt to analyze
+     * @returns Detailed feature breakdown
+     */
+    analyze(query) {
+        return (0, advancedRouter_1.extractQueryFeatures)(query);
+    }
+    /**
+     * Classify a complexity score into a named tier.
+     */
+    classifyTier(complexity) {
+        if (complexity < 0.20)
+            return 'free';
+        if (complexity < 0.45)
+            return 'cheap';
+        if (complexity < 0.65)
+            return 'mid';
+        return 'premium';
+    }
 }
-
+exports.A3MRouter = A3MRouter;
 /**
  * Convenience: create an A3MRouter instance.
  *
- * @param {object} config - Optional configuration
- * @returns {A3MRouter} Configured instance
+ * @param config - Optional configuration
+ * @returns Configured A3MRouter instance
  */
 function createSDK(config) {
-  return new A3MRouter(config);
+    return new A3MRouter(config);
 }
-
-module.exports = { A3MRouter, createSDK };
-module.exports.default = A3MRouter;
+//# sourceMappingURL=sdk.js.map

package/docs/UPDATE_TOPICS.md

@@ -0,0 +1,15 @@
+# GitHub Topics Update Script
+
+Run this to update GitHub repository topics:
+
+```bash
+curl -X PATCH "https://api.github.com/repos/Das-rebel/adaptive-memory-multi-model-router" \
+  -H "Authorization: token YOUR_GITHUB_TOKEN" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "topics": ["ai-agents", "ai-gateway", "ai-routing", "baichuan", "chinese-llm", "cost-optimization", "deepseek", "langchain", "llamaindex", "llm-gateway", "llm-router", "mcp", "minimax", "moonshot", "multi-llm", "openai-proxy", "proxy-server", "python", "qwen", "semantic-cache"],
+    "description": "🔀 Open-source LLM router with 99.5% routing accuracy — auto-routes to cheapest capable model (Groq, DeepSeek, Kimi, Qwen + 36+ providers). Semantic cache, guardrails, 62% cost savings. 19.5KB, zero ML. TypeScript + Python SDK. MIT license."
+  }'
+```
+
+Note: The topics and description are now properly optimized for discoverability.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "adaptive-memory-multi-model-router",
-  "version": "2.5.5",
+  "version": "2.7.0",
   "shortName": "A3M Router",
   "displayName": "A3M Router - Adaptive Memory Multi-Model Router",
   "description": "LLM router & AI gateway — 99.5% routing accuracy, 47 providers (DeepSeek, Kimi/Moonshot, Qwen, Zhipu GLM, Yi + more). Semantic cache, guardrails, cost analytics. Built on 30+ arXiv papers (SGLang, Medusa, MemoRAG). Zero ML, 19.5KB. TypeScript + Python SDK. MIT.",
@@ -480,7 +480,167 @@
     "semantic-routing",
     "smart-llm-router",
     "task-routing",
-    "traffic-routing"
+    "traffic-routing",
+    "smart-router",
+    "quality-routing",
+    "cross-provider-routing",
+    "provider-fallback-routing",
+    "http-proxy",
+    "network-proxy",
+    "gateway-proxy",
+    "cluster-llm",
+    "multi-region",
+    "health-check",
+    "automatic-failover",
+    "smart-failover",
+    "provider-failover",
+    "low-cost-llm",
+    "cost-saving",
+    "cost-reduction",
+    "budget-friendly",
+    "affordable-ai",
+    "cheaper-llm",
+    "llm-pricing",
+    "token-optimization",
+    "token-saving",
+    "api-cost",
+    "inference-cost",
+    "llm-cost",
+    "cost-effective-llm",
+    "pay-less-llm",
+    "llm-expense-management",
+    "api-budget",
+    "cost-control",
+    "spend-tracking",
+    "azure-openai",
+    "deepseek-v3",
+    "qwen2.5",
+    "qwen2.5-coder",
+    "moonshot-api",
+    "zhipu-api",
+    "glm-4v",
+    "glm-api",
+    "智谱ai",
+    "yi",
+    "yi-api",
+    "yi-34b",
+    "零一ai",
+    "minimax-abab",
+    "baichuan-api",
+    "baichuan4",
+    "stepfun-api",
+    "groq-api",
+    "groq-llama",
+    "groq-mixtral",
+    "cerebras-api",
+    "cerebras-qwen",
+    "mistral-api",
+    "mistral-7b",
+    "llama-api",
+    "llama-proxy",
+    "llama-3",
+    "llama-3.1",
+    "llama-3.3",
+    "openrouter-api",
+    "together-api",
+    "fireworks-api",
+    "perplexity-api",
+    "cohere-api",
+    "ai21",
+    "ai21-api",
+    "replicate",
+    "replicate-api",
+    "chinese-api",
+    "chinese-gateway",
+    "chinese-model",
+    "字节跳动",
+    "中文api",
+    "国产llm",
+    "中国llm",
+    "openai-gateway",
+    "openai-endpoint",
+    "openai-format",
+    "langchain-gateway",
+    "llamaindex-gateway",
+    "mcp-gateway",
+    "anthropic-mcp",
+    "vercel-ai-sdk",
+    "nextjs-ai",
+    "conversational-ai",
+    "pii-redaction",
+    "prompt-security",
+    "data-security",
+    "gdpr-llm",
+    "soc2",
+    "hipaa",
+    "fast-llm",
+    "low-latency",
+    "high-throughput",
+    "streaming-llm",
+    "batching",
+    "context-caching",
+    "flash-attention",
+    "smart-fallback",
+    "memory",
+    "routing-quality",
+    "routing-benchmark",
+    "node",
+    "npm-package",
+    "pypi-package",
+    "pip",
+    "json-api",
+    "client",
+    "server",
+    "microservices",
+    "api-management",
+    "workflow-automation",
+    "tree-search",
+    "monte-carlo",
+    "uct",
+    "performance-testing",
+    "llm-comparison",
+    "model-comparison",
+    "llm-evaluation",
+    "quality-metrics",
+    "latency-benchmark",
+    "throughput-testing",
+    "router-proxy",
+    "api-proxy",
+    "provider-management",
+    "provider-selection",
+    "automatic-selection",
+    "retrieval-augmented",
+    "text-generation",
+    "summarization",
+    "translation",
+    "sentiment-analysis",
+    "classification",
+    "extraction",
+    "named-entity-recognition",
+    "reliability",
+    "uptime",
+    "sla",
+    "metrics",
+    "alerting",
+    "docker",
+    "kubernetes",
+    "helm",
+    "aws",
+    "gcp",
+    "azure",
+    "self-hosted",
+    "self-host",
+    "on-premise",
+    "cloud-native",
+    "openai-relay",
+    "anthropic-relay",
+    "llm-relay",
+    "relay-server",
+    "api-relay",
+    "api-forwarder",
+    "api-aggregator",
+    "llm-middleware",
+    "api-middleware"
   ],
   "author": "Das-rebel <subho@example.com>",
   "license": "MIT",
@@ -496,7 +656,8 @@
     "test": "node test.js && node test/provider-test.js",
     "test:providers": "node test/provider-test.js",
     "benchmark": "node test/benchmark.js",
-    "benchmark:verbose": "node test/benchmark.js --verbose"
+    "benchmark:verbose": "node test/benchmark.js --verbose",
+    "build": "npx tsc -p tsconfig.build.json"
   },
   "engines": {
     "node": ">=18.0.0"