adaptive-memory-multi-model-router 2.12.0 → 2.12.1

package/package.json

@@ -1,12 +1,13 @@
 {
   "name": "adaptive-memory-multi-model-router",
-  "version": "2.12.0",
+  "version": "2.12.1",
   "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.",
+  "description": "One prompt in. The right model out. Open-source LLM router with 100% routing accuracy, 47+ providers. 6.1k monthly downloads. Budget enforcement, semantic cache, intelligent failover. Zero ML, 19.5KB. MIT.",
   "main": "dist/index.js",
   "bin": {
     "a3m-router": "dist/cli.js",
+    "a3m": "dist/cli/tui.js",
     "adaptive-memory-multi-model-router": "dist/cli.js"
   },
   "exports": {
@@ -54,17 +55,10 @@
   },
   "keywords": [
     "01-ai",
-    "01ai",
-    "128k上下文",
-    "19kb",
     "429-handling",
     "a3m",
     "a3m-router",
-    "active-active",
-    "active-passive",
-    "active-standby",
     "adaptive",
-    "adaptive-llm-router",
     "adaptive-router",
     "adaptive-routing",
     "affordable-ai",
@@ -73,14 +67,12 @@
     "agent-discoverable",
     "agent-framework",
     "agent-memory",
-    "agent-orchestration",
     "ai",
     "ai-agent",
     "ai-agent-tools",
     "ai-agents",
     "ai-assistant",
     "ai-coding",
-    "ai-cost-optimization",
     "ai-discoverability",
     "ai-gateway",
     "ai-gateway-cn",
@@ -93,13 +85,9 @@
     "ai-routing",
     "ai-sdk",
     "ai21",
-    "ai21-api",
-    "airtable",
-    "ai路由",
     "aleph-alpha",
     "alerting",
     "aliyun",
-    "amplitude",
     "anthropic",
     "anthropic-mcp",
     "anthropic-proxy",
@@ -114,11 +102,9 @@
     "api-middleware",
     "api-proxy",
     "api-relay",
-    "arxiv",
-    "asana",
+    "auto-recovery",
     "autogen",
     "automatic-failover",
-    "automatic-selection",
     "automation",
     "autonomous-agents",
     "aws",
@@ -127,16 +113,10 @@
     "azure-openai",
     "backoff",
     "baichuan",
-    "baichuan-ai",
-    "baichuan-api",
-    "baichuan2",
-    "baichuan2-flash",
-    "baichuan4",
     "baiducloud",
     "batch-processing",
     "batching",
     "benchmark",
-    "bitbucket",
     "budget-alerts",
     "budget-cap",
     "budget-dashboard",
@@ -146,20 +126,15 @@
     "cache-ttl",
     "caching",
     "cerebras",
-    "cerebras-api",
-    "cerebras-proxy",
-    "cerebras-qwen",
     "chatbot",
     "chatgpt",
     "cheaper-llm",
     "chinese-ai",
     "chinese-ai-proxy",
     "chinese-api",
-    "chinese-api-gateway",
     "chinese-api-retry",
     "chinese-chatgpt",
     "chinese-gateway",
-    "chinese-language-model",
     "chinese-llm",
     "chinese-llm-proxy",
     "chinese-model",
@@ -179,17 +154,13 @@
     "cluster-llm",
     "code-generation",
     "cohere",
-    "cohere-api",
     "complexity-scoring",
     "content-filtering",
     "content-routing",
-    "context-aware-router",
     "context-cache",
     "context-caching",
-    "context-compression",
     "context-management",
     "contextual-router",
-    "continuous-batching",
     "conversational-ai",
     "cooldown",
     "copilot",
@@ -207,8 +178,6 @@
     "cost-saving",
     "cost-tracking",
     "crewai",
-    "cross-context-memory",
-    "cross-provider-routing",
     "data-security",
     "datadog",
     "deadline",
@@ -221,15 +190,11 @@
     "deepseek-proxy",
     "deepseek-reasoner",
     "deepseek-v3",
-    "developer-experience",
     "developer-tools",
     "devops",
-    "discord",
     "distributed-llm",
-    "distributed-tracing",
     "docker",
     "domain-routing",
-    "dropbox",
     "dx",
     "dynamic-routing",
     "edge-computing",
@@ -240,36 +205,25 @@
     "enterprise",
     "enterprise-ready",
     "episodic-memory",
-    "episodic-memory-router",
     "expense-management",
-    "exponential-backoff",
     "extraction",
     "failover",
     "fallback",
     "fallback-chain",
     "fast-llm",
+    "fault-tolerance",
     "fine-tuning",
     "fireworks",
-    "fireworks-api",
-    "flash-attention",
     "gateway",
     "gateway-proxy",
     "gcp",
     "gdpr-llm",
     "gemini",
-    "generative-engine-optimization",
     "geo",
-    "github",
-    "gitlab",
     "glm-4",
-    "glm-4-air",
-    "glm-4-flash",
-    "glm-4-long",
-    "glm-4-plus",
     "glm-4v",
     "glm-api",
     "glms",
-    "gmail",
     "google",
     "google-calendar",
     "gpt",
@@ -284,58 +238,40 @@
     "guardrails",
     "ha-cluster",
     "halo",
-    "hard-budget-enforcement",
     "health-check",
     "health-scoring",
     "helicone",
-    "helm",
-    "hierarchical-planning",
     "high-availability",
     "high-throughput",
     "hipaa",
     "http-proxy",
     "huawei-cloud",
-    "hubspot",
-    "huggingface",
     "iclr",
-    "icml",
     "inference",
     "inference-cost",
-    "inference-optimization",
     "input-validation",
-    "intelligent-failover",
-    "intelligent-llm-router",
-    "intelligent-load-balancer",
     "intelligent-router",
     "intent-detection",
     "intent-mapping",
     "intent-routing",
     "intercom",
-    "ison-format",
     "jaeger",
     "javascript",
-    "jira",
     "jitter",
     "json-api",
     "keyword-routing",
     "kimi",
     "kimi-api",
-    "kubernetes",
-    "kv-cache",
-    "kv-cache-quantization",
     "langchain",
     "langchain-cn",
     "langchain-gateway",
     "langfuse",
     "language-model",
     "latency-benchmark",
-    "latency-optimization",
     "learning-router",
     "lightweight",
-    "linear",
     "lingyi",
     "lingyi-wanwu",
-    "litellm-alternative",
     "llama",
     "llama-3",
     "llama-3.1",
@@ -351,7 +287,6 @@
     "llm-comparison",
     "llm-cost",
     "llm-evaluation",
-    "llm-expense-management",
     "llm-failover",
     "llm-gateway",
     "llm-gateway-cn",
@@ -378,20 +313,14 @@
     "long-context-model",
     "low-cost-llm",
     "low-latency",
-    "lru-cache",
     "machine-learning",
-    "mailchimp",
     "max-retries",
     "mcp",
     "mcp-gateway",
     "mcts",
-    "medusa",
     "memory",
     "memory-augmented",
-    "memory-augmented-llm",
     "memory-based",
-    "memory-based-llm-router",
-    "memory-based-router",
     "memory-tree",
     "message-truncation",
     "metrics",
@@ -410,15 +339,15 @@
     "mistral-7b",
     "mistral-api",
     "mistral-proxy",
-    "mixpanel",
     "model-comparison",
     "model-management",
+    "model-picker",
     "model-router",
     "model-routing",
     "model-selection",
+    "model-selector",
     "monitoring",
     "monte-carlo",
-    "monte-carlo-tree-search",
     "monthly-budget",
     "moonshot",
     "moonshot-ai",
@@ -437,19 +366,13 @@
     "multi-provider",
     "multi-region",
     "multimodal",
-    "multimodel-orchestration",
-    "named-entity-recognition",
-    "natural-language-processing",
-    "netlify",
     "network-proxy",
-    "neurips",
     "nextjs-ai",
     "nlp",
     "no-gpu",
     "node",
     "nodejs",
     "nomic-embed",
-    "notion",
     "npm",
     "npm-package",
     "observability",
@@ -471,31 +394,18 @@
     "opentelemetry",
     "orchestration",
     "otel",
-    "pagedattention",
     "parallel",
     "parallel-ai",
     "parallel-execution",
     "pay-less-llm",
-    "per-provider-timeout",
     "per-team-budget",
     "per-user-budget",
     "performance",
-    "performance-testing",
     "perplexity",
-    "perplexity-api",
-    "pi",
-    "pi-agent",
-    "pi-coding-agent",
-    "pi-extension",
-    "pi-package",
     "pii-detection",
     "pii-redaction",
     "pinecone",
     "pip",
-    "portkey-alternative",
-    "posthog",
-    "prefix-cache",
-    "prefix-caching",
     "priority-queue",
     "privacy-llm",
     "production",
@@ -509,9 +419,7 @@
     "prompt-security",
     "provider-failover",
     "provider-fallback",
-    "provider-fallback-routing",
     "provider-health",
-    "provider-management",
     "provider-registry",
     "provider-selection",
     "provider-selector",
@@ -535,24 +443,19 @@
     "qwen2.5",
     "qwen2.5-coder",
     "qwen3",
-    "radix-attention",
     "rag",
-    "rate-limit-handling",
     "rate-limiter",
     "rate-limiting",
     "real-time",
     "relay-server",
     "reliability",
-    "replicate",
-    "replicate-api",
     "request-routing",
     "request-timeout",
     "request-tracing",
     "research-backed",
+    "resilience",
     "response-cache",
     "rest-api",
-    "retrieval-augmented",
-    "retrieval-augmented-generation",
     "retry",
     "retry-after",
     "retry-logic",
@@ -561,34 +464,27 @@
     "reverse-proxy",
     "route-quality",
     "routellm",
-    "routellm-alternative",
     "router",
     "router-proxy",
     "routing-accuracy",
     "routing-benchmark",
     "routing-quality",
-    "s3",
     "salesforce",
     "sanitization",
     "scalability",
     "sdk",
     "security",
-    "segment",
     "self-consistency",
+    "self-healing",
     "self-host",
     "self-hosted",
     "semantic-cache",
     "semantic-memory",
-    "semantic-memory-router",
     "semantic-routing",
-    "semantic-similarity",
-    "sendgrid",
     "sentiment-analysis",
     "sentry",
     "server",
     "serverless",
-    "shopify",
-    "similarity-threshold",
     "sla",
     "slack",
     "smart-failover",
@@ -596,28 +492,19 @@
     "smart-llm-router",
     "smart-router",
     "smart-routing",
+    "smart-selection",
     "soc2",
     "span",
-    "speculative-decoding",
     "spend-tracking",
     "spending-limit",
-    "step-1",
-    "step-1v",
-    "step-2",
-    "stepfun",
-    "stepfun-api",
     "streaming",
     "streaming-llm",
     "streamingllm",
-    "stripe",
     "summarization",
     "task-aware-router",
-    "task-classification",
     "task-memory",
     "task-routing",
-    "telegram",
     "tencentcloud",
-    "tensor-parallelism",
     "testing",
     "text-generation",
     "throughput-testing",
@@ -641,8 +528,6 @@
     "transformers",
     "translation",
     "tree-search",
-    "treequest",
-    "trello",
     "typescript",
     "ucb1",
     "uct",
@@ -654,9 +539,6 @@
     "vercel-ai-sdk",
     "vision-model",
     "volcengine",
-    "websocket",
-    "workflow-automation",
-    "workflow-optimization",
     "wu-yuan",
     "wuyuan",
     "xai",
@@ -671,51 +553,22 @@
     "zai",
     "zai-glm",
     "zai-glm-4",
-    "zendesk",
     "zero-ml",
     "zh-llm",
     "zhipu",
     "zhipu-ai",
     "zhipu-api",
-    "中国ai",
-    "中国llm",
-    "中国大模型",
-    "中文ai",
-    "中文api",
-    "中文chatgpt",
-    "中文embedding",
-    "中文langchain",
-    "中文llamaindex",
-    "中文llm",
-    "中文nlp",
-    "中文seo",
-    "中文多模态",
-    "中文大模型",
-    "中文搜索引擎优化",
-    "中文模型",
-    "华为云",
-    "向量化",
-    "国产ai",
-    "国产llm",
-    "国产大模型",
-    "多模型路由",
-    "多模态",
-    "大模型路由",
-    "字节ai",
-    "字节跳动",
-    "智能路由",
-    "智谱ai",
-    "深度求索",
-    "火山引擎",
-    "百度ai",
-    "百度云",
-    "腾讯ai",
-    "腾讯云",
-    "长上下文",
-    "阿里ai",
-    "阿里qwen",
-    "阿里云",
-    "零一ai"
+    "99-accuracy",
+    "no-gpu-required",
+    "starts-in-100ms",
+    "3-failure-trigger",
+    "60-second-cooldown",
+    "12-signal-routing",
+    "domain-detection",
+    "learns-from-history",
+    "mcts-workflow",
+    "ucb1-selection",
+    "62-percent-cost-savings"
   ],
   "author": "Das-rebel <subho@example.com>",
   "license": "MIT",

package/docs/assets/cost-comparison.svg

@@ -1,134 +0,0 @@
-<svg xmlns="http://www.w3.org/2000/svg" width="780" height="520" viewBox="0 0 780 520">
-  <defs>
-    <linearGradient id="gpt4bar" x1="0" y1="0" x2="1" y2="0">
-      <stop offset="0%" stop-color="#f85149"/>
-      <stop offset="100%" stop-color="#da3633"/>
-    </linearGradient>
-    <linearGradient id="a3mbar" x1="0" y1="0" x2="1" y2="0">
-      <stop offset="0%" stop-color="#3fb950"/>
-      <stop offset="100%" stop-color="#238636"/>
-    </linearGradient>
-    <linearGradient id="header" x1="0" y1="0" x2="0" y2="1">
-      <stop offset="0%" stop-color="#161b22"/>
-      <stop offset="100%" stop-color="#0d1117"/>
-    </linearGradient>
-  </defs>
-  
-  <!-- Background -->
-  <rect width="780" height="520" rx="12" fill="#0d1117" stroke="#30363d" stroke-width="1"/>
-  
-  <!-- Header -->
-  <rect width="780" height="56" rx="12" fill="url(#header)"/>
-  <rect y="44" width="780" height="12" fill="url(#header)"/>
-  <text x="24" y="28" font-family="-apple-system,system-ui,sans-serif" font-size="18" fill="#c9d1d9" font-weight="700">💰 Cost Comparison</text>
-  <text x="24" y="46" font-family="-apple-system,system-ui,sans-serif" font-size="12" fill="#8b949e">10,000 queries/month · Real provider pricing · Mixed query complexity</text>
-  
-  <!-- Legend -->
-  <rect x="580" y="16" width="14" height="14" rx="3" fill="url(#gpt4bar)"/>
-  <text x="600" y="27" font-family="-apple-system,system-ui,sans-serif" font-size="12" fill="#f85149">All → GPT-4o</text>
-  <rect x="680" y="16" width="14" height="14" rx="3" fill="url(#a3mbar)"/>
-  <text x="700" y="27" font-family="-apple-system,system-ui,sans-serif" font-size="12" fill="#3fb950">A3M Routed</text>
-  
-  <!-- Chart rows -->
-  <g font-family="'SF Mono','Fira Code',monospace" font-size="12">
-    
-    <!-- Row 1: Simple Q&A -->
-    <text x="24" y="82" fill="#8b949e">Simple Q&A</text>
-    <text x="24" y="96" fill="#484f58" font-size="10">47% of traffic · "What is 2+2?"</text>
-    <rect x="140" y="78" width="200" height="20" rx="4" fill="url(#gpt4bar)" opacity="0.9">
-      <animate attributeName="width" from="0" to="200" dur="0.6s" fill="freeze"/>
-    </rect>
-    <text x="346" y="93" fill="#f85149" font-size="11">$4.94</text>
-    <rect x="140" y="100" width="2" height="14" rx="2" fill="url(#a3mbar)">
-      <animate attributeName="width" from="0" to="2" dur="0.4s" fill="freeze"/>
-    </rect>
-    <text x="148" y="112" fill="#3fb950" font-size="11">$0.00 → CommandCode (FREE)</text>
-    <text x="720" y="96" fill="#3fb950" font-weight="bold" font-size="13">100% ✓</text>
-    
-    <!-- Row 2: Code generation -->
-    <text x="24" y="148" fill="#8b949e">Code generation</text>
-    <text x="24" y="162" fill="#484f58" font-size="10">15% of traffic · "Write Python sort"</text>
-    <rect x="140" y="144" width="198" height="20" rx="4" fill="url(#gpt4bar)" opacity="0.9">
-      <animate attributeName="width" from="0" to="198" dur="0.6s" begin="0.15s" fill="freeze"/>
-    </rect>
-    <text x="344" y="159" fill="#f85149" font-size="11">$4.88</text>
-    <rect x="140" y="166" width="7" height="14" rx="2" fill="url(#a3mbar)">
-      <animate attributeName="width" from="0" to="7" dur="0.4s" begin="0.15s" fill="freeze"/>
-    </rect>
-    <text x="153" y="178" fill="#3fb950" font-size="11">$0.17 → DeepSeek v3</text>
-    <text x="720" y="162" fill="#3fb950" font-weight="bold" font-size="13">97% ✓</text>
-    
-    <!-- Row 3: Summarization -->
-    <text x="24" y="214" fill="#8b949e">Summarization</text>
-    <text x="24" y="228" fill="#484f58" font-size="10">18% of traffic · "Summarize this doc"</text>
-    <rect x="140" y="210" width="292" height="20" rx="4" fill="url(#gpt4bar)" opacity="0.9">
-      <animate attributeName="width" from="0" to="292" dur="0.6s" begin="0.3s" fill="freeze"/>
-    </rect>
-    <text x="438" y="225" fill="#f85149" font-size="11">$7.20</text>
-    <rect x="140" y="232" width="17" height="14" rx="2" fill="url(#a3mbar)">
-      <animate attributeName="width" from="0" to="17" dur="0.4s" begin="0.3s" fill="freeze"/>
-    </rect>
-    <text x="163" y="244" fill="#3fb950" font-size="11">$0.43 → GPT-4o-mini</text>
-    <text x="720" y="228" fill="#3fb950" font-weight="bold" font-size="13">94% ✓</text>
-    
-    <!-- Row 4: Complex reasoning -->
-    <text x="24" y="280" fill="#8b949e">Complex reasoning</text>
-    <text x="24" y="294" fill="#484f58" font-size="10">12% of traffic · "Analyze economics of..."</text>
-    <rect x="140" y="276" width="352" height="20" rx="4" fill="url(#gpt4bar)" opacity="0.9">
-      <animate attributeName="width" from="0" to="352" dur="0.6s" begin="0.45s" fill="freeze"/>
-    </rect>
-    <text x="498" y="291" fill="#f85149" font-size="11">$8.70</text>
-    <rect x="140" y="298" width="136" height="14" rx="2" fill="url(#a3mbar)">
-      <animate attributeName="width" from="0" to="136" dur="0.4s" begin="0.45s" fill="freeze"/>
-    </rect>
-    <text x="282" y="310" fill="#3fb950" font-size="11">$3.36 → Claude Haiku</text>
-    <text x="720" y="294" fill="#ffa657" font-weight="bold" font-size="13">61% ✓</text>
-    
-    <!-- Row 5: Expert analysis -->
-    <text x="24" y="346" fill="#8b949e">Expert analysis</text>
-    <text x="24" y="360" fill="#484f58" font-size="10">8% of traffic · "Legal contract review"</text>
-    <rect x="140" y="342" width="340" height="20" rx="4" fill="url(#gpt4bar)" opacity="0.9">
-      <animate attributeName="width" from="0" to="340" dur="0.6s" begin="0.6s" fill="freeze"/>
-    </rect>
-    <text x="486" y="357" fill="#f85149" font-size="11">$8.40</text>
-    <rect x="140" y="364" width="340" height="14" rx="2" fill="url(#a3mbar)" opacity="0.5">
-      <animate attributeName="width" from="0" to="340" dur="0.4s" begin="0.6s" fill="freeze"/>
-    </rect>
-    <text x="486" y="376" fill="#8b949e" font-size="11">$8.40 → GPT-4o (no shortcut)</text>
-    <text x="720" y="360" fill="#8b949e" font-weight="bold" font-size="13">0%</text>
-  </g>
-  
-  <!-- Divider -->
-  <line x1="24" y1="396" x2="756" y2="396" stroke="#30363d" stroke-width="1"/>
-  
-  <!-- Total -->
-  <g font-family="-apple-system,system-ui,sans-serif">
-    <text x="24" y="418" fill="#c9d1d9" font-size="16" font-weight="700">Total: 10,000 queries</text>
-    <text x="380" y="418" fill="#f85149" font-size="16" font-weight="700">$34.11/mo</text>
-    <text x="470" y="418" fill="#484f58" font-size="16">→</text>
-    <text x="498" y="418" fill="#3fb950" font-size="16" font-weight="700">$12.36/mo</text>
-    <text x="600" y="418" fill="#3fb950" font-size="20" font-weight="800">Save 64%</text>
-  </g>
-  
-  <!-- Scale projections -->
-  <g font-family="'SF Mono','Fira Code',monospace" font-size="11">
-    <text x="24" y="448" fill="#8b949e">At scale:</text>
-    <text x="24" y="468" fill="#484f58">  100K queries/mo</text>
-    <text x="200" y="468" fill="#f85149">$341</text>
-    <text x="240" y="468" fill="#484f58">→</text>
-    <text x="260" y="468" fill="#3fb950">$124</text>
-    <text x="310" y="468" fill="#3fb950">save $218/mo</text>
-    
-    <text x="420" y="468" fill="#484f58">  1M queries/mo</text>
-    <text x="580" y="468" fill="#f85149">$3,411</text>
-    <text x="630" y="468" fill="#484f58">→</text>
-    <text x="650" y="468" fill="#3fb950">$1,236</text>
-    <text x="700" y="468" fill="#3fb950">save $2,175/mo</text>
-  </g>
-  
-  <!-- Bottom note -->
-  <rect x="16" y="488" width="748" height="24" rx="4" fill="#161b22"/>
-  <text x="390" y="504" text-anchor="middle" font-family="-apple-system,system-ui,sans-serif" font-size="11" fill="#8b949e">
-    Based on real provider pricing from providerConfig.ts · RouteLLM query distribution (47% simple) · Savings vary by usage
-  </text>
-</svg>