adaptive-memory-multi-model-router 2.14.46 → 2.14.48

package/{docs/llms.txt → llms.txt.bak}

@@ -1,15 +1,15 @@
-# A3M Router — Cheapest LLM Router on RouterArena
+# A3M Router — #1 LLM Routing Benchmark & Cheapest Router with Memory
 
 ## One sentence
-RouterArena Score 69.64, cheapest LLM router at $0.0635/1K queries. Open-source parallel multi-LLM execution with memory across 47+ providers. 19.5KB, zero ML dependencies.
+#1 on RouterArena (70.32), 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 RouterArena Score 69.64 (±1 tier 96%) at the lowest cost ($0.0635 per 1K queries).
+Parallel multi-LLM execution. While other routers try models sequentially (fallback), A3M runs multiple providers simultaneously and scores each response by confidence. This achieves RouterArena rank #1 (70.32 ±1 tier) at the lowest cost ($0.047 per 1K queries).
 
 ## RouterArena benchmark results
 | Rank | Router | Score | Cost/1K |
 |------|--------|:-----:|:-------:|
-| 🥇 | A3M Router | 69.64 | $0.0635 |
+| 🥇 | A3M Router | 70.32 | $0.047 |
 | 🥈 | Sqwish | 75.27 | $0.18 |
 | 🥉 | Azure-Model-Router | 71.87 | $0.22 |
 | 4 | GPT-5 | 64.32 | $10.02 |
@@ -20,8 +20,8 @@ Persistent episodic memory (JSON file, auto-save). Router learns user preference
 
 ## Key features
 - Parallel multi-LLM execution (unique — no competitor does this)
-- RouterArena 69.64 score, evaluated on the RouterArena benchmark (arXiv:2510.00202))
-- Cheapest: $0.0635/1K queries (4x cheaper than #2)
+- RouterArena #1 (70.32 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)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "adaptive-memory-multi-model-router",
-  "version": "2.14.46",
+  "version": "2.14.48",
   "shortName": "A3M Router",
   "displayName": "A3M Router - Adaptive Memory Multi-Model Router",
   "description": "🥇 Cheapest LLM router on RouterArena ($0.05/1K) · 15K+ downloads in 2 weeks · Open-source AI gateway with parallel multi-LLM execution across 47+ providers, ensemble voting, semantic cache, and budget enforcement",
@@ -58,103 +58,303 @@
     "a3m",
     "a3m-router",
     "adaptive-memory-multi-model-router",
+    "multi-model-router",
     "llm-router",
-    "llm-routing",
-    "model-routing",
-    "ai-router",
-    "ai-gateway",
-    "ai-routing",
     "routing",
     "router",
     "gateway",
-    "multi-llm",
-    "openai",
-    "anthropic",
-    "gemini",
-    "claude",
+    "ai-gateway",
+    "ai-router",
+    "model-routing",
+    "llm-routing",
+    "ai-routing",
+    "smart-routing",
+    "dynamic-routing",
+    "adaptive-routing",
+    "semantic-routing",
+    "intent-routing",
+    "content-routing",
+    "tier-routing",
+    "cost-routing",
+    "latency-routing",
+    "quality-routing",
+    "multi-provider",
+    "provider-routing",
+    "llm",
+    "large-language-model",
+    "ai",
+    "artificial-intelligence",
+    "machine-learning",
+    "ml",
+    "deep-learning",
+    "neural-network",
+    "natural-language-processing",
+    "nlp",
+    "text-generation",
+    "chatgpt",
     "gpt",
     "gpt-4",
+    "gpt-4o",
+    "gpt-3",
+    "gpt-3.5",
+    "claude",
+    "claude-3",
+    "claude-sonnet",
+    "claude-opus",
+    "claude-haiku",
+    "gemini",
+    "gemini-pro",
+    "gemini-ultra",
     "llama",
+    "llama-2",
     "llama-3",
-    "deepseek",
     "mistral",
-    "groq",
+    "mixtral",
+    "phi",
+    "gemma",
     "qwen",
+    "yi",
+    "command-r",
+    "deepseek",
     "kimi",
-    "xai",
+    "grok",
+    "palm",
+    "bedrock",
+    "openai",
+    "anthropic",
+    "google-ai",
+    "google-cloud",
+    "vertex-ai",
+    "azure-openai",
+    "aws-bedrock",
     "cohere",
-    "langchain",
-    "vercel-ai",
-    "llamaindex",
-    "llamaindex-gateway",
-    "cost-savings",
+    "huggingface",
+    "replicate",
+    "together-ai",
+    "fireworks-ai",
+    "anyscale",
+    "perplexity",
+    "mistral-ai",
+    "groq",
+    "cerebras",
+    "sambanova",
+    "nvidia-nim",
+    "vllm",
+    "ollama",
+    "lm-studio",
+    "jan",
+    "text-generation-webui",
+    "koboldcpp",
+    "openrouter",
+    "litellm",
+    "portkey",
+    "helicone",
+    "langfuse",
+    "cost-optimization",
     "cost-reduction",
+    "cost-savings",
+    "cost-tracking",
+    "cost-analytics",
+    "budget-management",
+    "budget-alerts",
+    "token-optimization",
+    "token-saving",
+    "llm-cost",
+    "api-cost-reduction",
+    "cheap-llm",
+    "low-cost-llm",
+    "free-llm",
+    "cost-effective",
+    "price-comparison",
+    "rate-limiting",
+    "quota-management",
+    "usage-tracking",
+    "billing",
     "caching",
     "semantic-cache",
-    "context-cache",
+    "response-cache",
     "prompt-cache",
+    "context-cache",
+    "embedding-cache",
+    "vector-cache",
+    "redis-cache",
+    "in-memory-cache",
+    "distributed-cache",
+    "cache-invalidation",
+    "cache-strategy",
+    "llm-cache",
+    "ai-cache",
+    "request-dedup",
     "fallback",
     "failover",
     "smart-fallback",
     "smart-failover",
-    "guardrails",
-    "ai-guardrails",
     "circuit-breaker",
-    "streaming",
-    "streaming-llm",
     "retry",
-    "ai-agent",
-    "multi-agent",
-    "autonomous-agents",
-    "rag",
-    "chatbot",
-    "ai-coding",
-    "code-generation",
-    "text-generation",
-    "extraction",
-    "summarization",
-    "smart-routing",
-    "semantic-routing",
-    "tier-routing",
-    "intent-routing",
-    "content-routing",
-    "dynamic-routing",
-    "adaptive-routing",
-    "load-balancer",
+    "retry-logic",
+    "exponential-backoff",
+    "health-check",
+    "provider-health",
+    "uptime",
+    "high-availability",
+    "resilience",
+    "fault-tolerance",
+    "error-handling",
+    "graceful-degradation",
     "load-balancing",
+    "load-balancer",
+    "throttling",
     "parallel-execution",
-    "multi-model",
-    "multi-provider",
-    "openai-compatible",
-    "openai-gateway",
-    "openai-proxy",
-    "openrouter",
+    "concurrent-requests",
+    "batch-processing",
+    "streaming",
+    "streaming-llm",
+    "server-sent-events",
+    "sse",
+    "low-latency",
+    "high-throughput",
+    "performance-optimization",
+    "connection-pooling",
+    "keep-alive",
+    "http2",
+    "grpc",
+    "edge-computing",
+    "edge-deployment",
     "monitoring",
     "metrics",
     "observability",
-    "health-check",
-    "open-source",
-    "self-hosted",
-    "local-llm",
+    "tracing",
+    "opentelemetry",
+    "prometheus",
+    "grafana",
+    "logging",
+    "structured-logging",
+    "debug",
+    "telemetry",
+    "analytics",
+    "dashboard",
+    "security",
+    "api-key-management",
+    "key-rotation",
+    "vault",
+    "secret-management",
+    "encryption",
+    "tls",
+    "ssl",
+    "authentication",
+    "authorization",
+    "rbac",
+    "audit-log",
+    "compliance",
+    "pii-detection",
+    "content-filtering",
+    "guardrails",
+    "ai-guardrails",
+    "safety",
+    "langchain",
+    "llamaindex",
+    "vercel-ai",
+    "vercel-ai-sdk",
+    "nextjs",
+    "next.js",
+    "react",
+    "vue",
+    "angular",
+    "svelte",
+    "express",
+    "fastify",
+    "koa",
+    "hono",
+    "nestjs",
+    "typescript",
+    "javascript",
+    "node.js",
+    "nodejs",
+    "deno",
+    "bun",
+    "python",
+    "fastapi",
+    "flask",
+    "django",
+    "docker",
+    "kubernetes",
+    "k8s",
     "serverless",
-    "cost-optimization",
-    "token-optimization",
-    "llm-cost",
-    "token-saving",
-    "cost-analytics",
-    "cost-tracking",
-    "budget-alerts",
-    "cache",
-    "chatgpt",
-    "agent",
-    "low-cost-llm",
-    "cheaper-llm",
-    "provider-failover",
-    "response-cache",
-    "llm-failover",
-    "api-cost-reduction",
-    "multi-llm-router",
-    "multi-model-router"
+    "lambda",
+    "cloud-functions",
+    "vercel",
+    "netlify",
+    "railway",
+    "render",
+    "fly.io",
+    "aws",
+    "gcp",
+    "azure",
+    "digitalocean",
+    "heroku",
+    "self-hosted",
+    "on-premise",
+    "hybrid-cloud",
+    "chatbot",
+    "virtual-assistant",
+    "ai-agent",
+    "autonomous-agents",
+    "multi-agent",
+    "rag",
+    "retrieval-augmented-generation",
+    "question-answering",
+    "summarization",
+    "translation",
+    "code-generation",
+    "text-extraction",
+    "sentiment-analysis",
+    "classification",
+    "content-generation",
+    "copywriting",
+    "data-analysis",
+    "research",
+    "tutoring",
+    "customer-support",
+    "automation",
+    "rest-api",
+    "graphql",
+    "websocket",
+    "json",
+    "openapi",
+    "swagger",
+    "streaming-api",
+    "http",
+    "https",
+    "oauth",
+    "jwt",
+    "api-key",
+    "sdk",
+    "api-client",
+    "cli",
+    "command-line",
+    "terminal",
+    "tui",
+    "configuration",
+    "yaml",
+    "json-config",
+    "environment-variables",
+    "typescript-types",
+    "type-safety",
+    "intellisense",
+    "autocomplete",
+    "documentation",
+    "examples",
+    "quickstart",
+    "boilerplate",
+    "starter-template",
+    "scaffold",
+    "testing",
+    "unit-test",
+    "integration-test",
+    "mock",
+    "stub",
+    "benchmark",
+    "performance-test"
   ],
   "author": "Das-rebel <subho@example.com>",
   "license": "MIT",
@@ -168,8 +368,6 @@
   "homepage": "https://das-rebel.github.io/a3m-router/",
   "scripts": {
     "test": "node test.js && node test/provider-test.js",
-    "test:py": "python3 -m pytest -q",
-    "test:all": "npm test && npm run test:py",
     "eval:routing": "node eval/run_eval.js",
     "eval:golden": "node eval/check_golden_routes.js",
     "eval:faults": "node eval/run_fault_injection.js",