adaptive-memory-multi-model-router 2.9.2 → 2.11.0

package/README.md

@@ -15,26 +15,30 @@ OpenAI-compatible **LLM gateway & router** that auto-routes every query to the c
 ### Architecture
 
 ```
-┌─────────────────────────────────────────────────────────────────┐
-│                     A3M Router — Generative Engine               │
-├─────────────────────────────────────────────────────────────────┤
-│                                                                  │
-│  ┌──────────────┐    ┌──────────────┐    ┌──────────────────┐  │
-│  │  Guardrails  │ → │  Semantic    │ → │  Routing Engine   │  │
-│  │  (Security)   │    │  Cache       │    │  (Multi-signal   │  │
-│  │ 17 patterns   │    │  (30% hit)   │    │   + MCTS)         │  │
-│  └──────────────┘    └──────────────┘    └────────┬─────────┘  │
-│                                                      │            │
-│         ┌──────────────────────┬──────────────────────┼────────┐ │
-│         │                      │                      │        │ │
-│         ↓                      ↓                      ↓        │ │
-│  ┌─────────────┐      ┌─────────────┐      ┌─────────────────┐│ │
-│  │  MemoryTree │      │ CostTracker│      │ Circuit Breaker ││ │
-│  │  (History)   │      │ (Budgets)   │      │  (Failover)      ││ │
-│  └─────────────┘      └─────────────┘      └─────────────────┘│ │
-│                                                              │ │
-│  47+ Providers: Groq, DeepSeek, Kimi, Qwen, Zhipu, OpenAI, Anthropic + more  │ │
-└─────────────────────────────────────────────────────────────────┘
+╔══════════════════════════════════════════════════════════════════╗
+║                     A3M Router — LLM Gateway                      ║
+╠══════════════════════════════════════════════════════════════════╣
+║                                                                   ║
+║  ┌─────────────┐      ┌─────────────┐      ┌─────────────────┐  ║
+║  │  Guardrails │ ──▶  │    Cache     │ ──▶  │   Router        │  ║
+║  │   🔒 17x     │      │   💾 30%+   │      │   🎯 MCTS       │  ║
+║  │  Injection   │      │    Hit      │      │  Multi-Signal   │  ║
+║  │  PII Detect  │      │  Semantic   │      │  12 Signals     │  ║
+║  └─────────────┘      └─────────────┘      └────────┬────────┘  ║
+║                                                      │           ║
+║        ┌─────────────────┬──────────────────────────┴──────┐   ║
+║        │                 │                                    │   ║
+║        ▼                 ▼                                    ▼   ║
+║  ┌─────────────┐  ┌─────────────┐                    ┌─────────────┐║
+║  │  MemoryTree  │  │  CostTrack  │                    │ Circuit     │║
+║  │    🧠        │  │    💰       │                    │ Breaker 🔄  │║
+║  │   EMA        │  │   Budget    │                    │ 3 Fails →   │║
+║  │   Learning   │  │   Alerts    │                    │ 60s Cooldown│║
+║  └─────────────┘  └─────────────┘                    └─────────────┘║
+║                                                                   ║
+║  47+ Providers: Groq · DeepSeek · Kimi · Qwen · Zhipu · Yi · +  ║
+║                   OpenAI · Anthropic · Google · Mistral · +      ║
+╚══════════════════════════════════════════════════════════════════╝
 ```
 
 
@@ -168,6 +172,61 @@ curl -s http://localhost:8787/v1/chat/completions \
 
 ---
 
+
+### Terminal Demo
+
+```bash
+$ 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 / $50.00 budget
+```
+
+```bash
+$ 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 ($2.50/1M tokens)
+   🔄 Fallback: anthropic/claude-3.5-sonnet
+   
+   💡 Signals: medical(+0.35) + design(+0.20) + multi-step(+0.15)
+```
+
+```bash
+$ 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)
+```
+
+---
+
 ## How It Works — Routing Engine
 
 A3M Router combines multi-signal routing, semantic caching, and load balancing to route queries to the cheapest capable model with 99.5% accuracy.
@@ -237,6 +296,73 @@ User Query
 Result: { model, tier, cost, complexity, reasoning[], fallbackModels[] }
 ```
 
+### Visual Routing Flow
+
+```
+                    User Query
+                         │
+                         ▼
+              ┌─────────────────────┐
+              │   Guardrails Check  │
+              │  🔒 PII / Injection │
+              └──────────┬──────────┘
+                         │
+                    ✅ Pass?
+                    /        \
+                 No          Yes
+                  │            │
+                  ▼            ▼
+             [BLOCK]     ┌─────────────────┐
+                         │  Semantic Cache │
+                         │    💾 Lookup    │
+                         └────────┬────────┘
+                                  │
+                             Cache Hit?
+                             /        \
+                          Yes          No
+                           │            │
+                           ▼            ▼
+                     [RETURN]     ┌─────────────────┐
+                         │        │  Route Query    │
+                         │        │  🎯 12 Signals  │
+                         │        │  Complexity →  │
+                         │        │  Tier          │
+                         │        └────────┬────────┘
+                         │                 │
+                         │                 ▼
+                         │        ┌─────────────────┐
+                         │        │ Provider Health │
+                         │        │  📊 Scoring     │
+                         │        └────────┬────────┘
+                         │                 │
+                         │                 ▼
+                         │        ┌─────────────────┐
+                         │        │  Best Provider │
+                         │        │  + Fallbacks   │
+                         │        └────────┬────────┘
+                         │                 │
+                         │                 ▼
+                         │        ┌─────────────────┐
+                         │        │  Execute LLM   │
+                         │        │    Call        │
+                         │        └────────┬────────┘
+                         │                 │
+                         │                 ▼
+                         │        ┌─────────────────┐
+                         │        │  Update Memory  │
+                         │        │  🧠 EMA Update │
+                         │        └────────┬────────┘
+                         │                 │
+                         │                 ▼
+                         │        [RETURN RESPONSE]
+                         │                 │
+                         └─────────────────┘
+```
+
+---
+
+
+
 ### Complexity Examples
 
 | Query | Signals Detected | Score | Tier | Route To |
@@ -366,6 +492,54 @@ Router assigns each sub-task to optimal agent, tracks outcomes, learns preferenc
 
 ## Features in Detail
 
+### Feature Overview
+
+```
+┌────────────────────────────────────────────────────────────────────────────┐
+│                         A3M Router Features                               │
+├────────────────────────────────────────────────────────────────────────────┤
+│                                                                            │
+│  🧠 ADAPTIVE MEMORY          │  🎯 INTELLIGENT ROUTING                     │
+│  ───────────────────         │  ─────────────────────                     │
+│  • MemoryTree storage        │  • 12-keyword signal detection              │
+│  • EMA quality scoring       │  • 99.5% ±1 tier accuracy                  │
+│  • Learns from history       │  • <1ms routing latency                     │
+│  • No retraining needed      │  • MCTS for complex workflows              │
+│                                                                            │
+├────────────────────────────────────────────────────────────────────────────┤
+│                                                                            │
+│  💰 HARD BUDGET ENFORCEMENT  │  🛡️ GUARDRAILS                             │
+│  ───────────────────────     │  ───────────────────                       │
+│  • Per-user/team budgets     │  • 17-pattern injection detection           │
+│  • Real-time spend tracking  │  • PII redaction                           │
+│  • Alerts at 50/80/100%      │  • Content filtering                        │
+│  • Hard caps (reject when exceeded)  │ • Hallucination checks              │
+│                                                                            │
+├────────────────────────────────────────────────────────────────────────────┤
+│                                                                            │
+│  🔄 INTELLIGENT FAILOVER     │  💾 SEMANTIC CACHE                         │
+│  ───────────────────────     │  ───────────────────                        │
+│  • Provider health scoring   │  • Embedding-based lookup                   │
+│  • Circuit breaker (3 fails) │  • Configurable similarity threshold       │
+│  • Automatic fallback chain  │  • Per-route TTL                           │
+│  • Chinese provider handling │  • 30%+ cache hit rate                      │
+│                                                                            │
+├────────────────────────────────────────────────────────────────────────────┤
+│                                                                            │
+│  ⚡ PER-PROVIDER RETRY       │  📊 COST ANALYTICS                         │
+│  ─────────────────────       │  ───────────────────                       │
+│  • Custom timeout per model  │  • Per-provider breakdown                    │
+│  • Exponential backoff       │  • Budget vs actual dashboard               │
+│  • 429 rate limit handling   │  • Projected savings                        │
+│  • Jitter to prevent storms  │  • Monthly/yearly reports                   │
+│                                                                            │
+└────────────────────────────────────────────────────────────────────────────┘
+```
+
+---
+
+
+
 ### 🧠 Adaptive Memory & Learning
 
 **How Memory Works**

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "adaptive-memory-multi-model-router",
-  "version": "2.9.2",
+  "version": "2.11.0",
   "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.",
@@ -53,113 +53,520 @@
     }
   },
   "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",
     "agent",
+    "agent-codegen",
+    "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",
+    "ai-guardrails",
+    "ai-load-balancer",
+    "ai-native",
+    "ai-orchestration",
+    "ai-proxy",
+    "ai-router",
     "ai-routing",
+    "ai-sdk",
+    "ai21",
+    "ai21-api",
     "airtable",
+    "ai路由",
+    "aleph-alpha",
+    "alerting",
+    "aliyun",
     "amplitude",
+    "anthropic",
+    "anthropic-mcp",
+    "anthropic-proxy",
+    "anthropic-relay",
+    "api-aggregator",
+    "api-budget",
+    "api-cost",
+    "api-cost-reduction",
+    "api-forwarder",
     "api-gateway",
+    "api-management",
+    "api-middleware",
+    "api-proxy",
+    "api-relay",
+    "arxiv",
     "asana",
+    "autogen",
+    "automatic-failover",
+    "automatic-selection",
     "automation",
     "autonomous-agents",
+    "aws",
     "aws-bedrock",
+    "azure",
+    "azure-openai",
+    "backoff",
+    "baichuan",
+    "baichuan-ai",
+    "baichuan-api",
+    "baichuan2",
+    "baichuan2-flash",
+    "baichuan4",
+    "baiducloud",
     "batch-processing",
+    "batching",
+    "benchmark",
     "bitbucket",
+    "budget-alerts",
+    "budget-cap",
+    "budget-dashboard",
+    "budget-friendly",
+    "cache",
+    "cache-hit-rate",
+    "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",
+    "chinese-models",
+    "chinese-nlp",
+    "chinesellm",
+    "chinesellm-routing",
     "circuit-breaker",
+    "classification",
+    "claude",
     "claude-code",
+    "claude-proxy",
     "cli",
+    "client",
     "cloud",
+    "cloud-native",
+    "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",
+    "cosine-similarity",
     "cost-analytics",
+    "cost-attribution",
+    "cost-based-routing",
+    "cost-cap",
+    "cost-control",
+    "cost-effective-llm",
+    "cost-estimation",
+    "cost-optimization",
+    "cost-prediction",
+    "cost-reduction",
+    "cost-saving",
+    "cost-tracking",
+    "crewai",
+    "cross-context-memory",
+    "cross-provider-routing",
+    "data-security",
     "datadog",
+    "deadline",
     "deepinfra",
+    "deepseek",
+    "deepseek-ai",
+    "deepseek-api",
+    "deepseek-chat",
+    "deepseek-coder",
+    "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",
+    "embed-text",
     "embedding",
+    "embedding-cache",
+    "embedding-model",
     "enterprise",
+    "enterprise-ready",
+    "episodic-memory",
+    "episodic-memory-router",
+    "expense-management",
+    "exponential-backoff",
+    "extraction",
+    "failover",
     "fallback",
+    "fallback-chain",
+    "fast-llm",
     "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",
     "gpt-4",
+    "grafana",
     "graphql",
+    "groq",
+    "groq-api",
+    "groq-llama",
+    "groq-mixtral",
+    "groq-proxy",
+    "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",
+    "llama-3.3",
+    "llama-api",
+    "llama-proxy",
     "llamaindex",
+    "llamaindex-cn",
+    "llamaindex-gateway",
+    "llm",
+    "llm-caching",
+    "llm-cluster",
+    "llm-comparison",
+    "llm-cost",
+    "llm-evaluation",
+    "llm-expense-management",
+    "llm-failover",
+    "llm-gateway",
+    "llm-gateway-cn",
     "llm-intent",
+    "llm-load-balancer",
+    "llm-management",
+    "llm-manager",
+    "llm-memory-router",
+    "llm-middleware",
+    "llm-orchestration",
+    "llm-pricing",
+    "llm-proxy",
+    "llm-relay",
+    "llm-router",
+    "llm-routing",
     "llm-tools",
     "llmlingua",
+    "lmstudio",
+    "load-balancer",
     "load-balancing",
+    "local-llm",
+    "local-model",
     "logging",
+    "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",
+    "metrics-api",
+    "metrics-collector",
+    "metrics-endpoint",
+    "microservices",
     "middleware",
+    "minimax",
+    "minimax-abab",
+    "minimax-ai",
+    "minimax-api",
+    "minimax-chat",
+    "minimax-turbo",
+    "mistral",
+    "mistral-7b",
+    "mistral-api",
+    "mistral-proxy",
     "mixpanel",
+    "model-comparison",
+    "model-management",
+    "model-router",
+    "model-routing",
+    "model-selection",
     "monitoring",
-    "multi-model",
-    "natural-language-processing",
-    "netlify",
-    "nodejs",
-    "notion",
-    "npm",
-    "observability",
-    "open-source",
-    "orchestration",
+    "monte-carlo",
+    "monte-carlo-tree-search",
+    "monthly-budget",
+    "moonshot",
+    "moonshot-ai",
+    "moonshot-api",
+    "moonshot-kimi",
+    "moonshot-v1",
+    "moonshot-v1-128k",
+    "moonshot-v1-32k",
+    "moonshot-v1-8k",
+    "multi-agent",
+    "multi-agent-debate",
+    "multi-llm",
+    "multi-llm-router",
+    "multi-model",
+    "multi-model-router",
+    "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",
+    "ollama",
+    "ollama-proxy",
+    "on-premise",
+    "open-source",
+    "openai",
+    "openai-api",
+    "openai-compatible",
+    "openai-endpoint",
+    "openai-format",
+    "openai-gateway",
+    "openai-proxy",
+    "openai-relay",
+    "openai-sdk",
+    "openrouter",
+    "openrouter-api",
+    "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",
+    "production-ready",
+    "prometheus-client",
+    "prometheus-format",
+    "prometheus-metrics",
+    "prompt-cache",
     "prompt-engineering",
     "prompt-injection",
+    "prompt-security",
+    "provider-failover",
+    "provider-fallback",
+    "provider-fallback-routing",
+    "provider-health",
+    "provider-management",
     "provider-registry",
+    "provider-selection",
+    "provider-selector",
     "proxy",
     "proxy-server",
+    "pypi",
+    "pypi-package",
     "python",
+    "python-bindings",
+    "qianwen",
+    "quality-metrics",
+    "quality-routing",
+    "query-cache",
+    "query-routing",
+    "qwen",
+    "qwen-long",
+    "qwen-max",
+    "qwen-plus",
+    "qwen-turbo",
+    "qwen2",
+    "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",
+    "response-cache",
     "rest-api",
+    "retrieval-augmented",
     "retrieval-augmented-generation",
     "retry",
+    "retry-after",
+    "retry-logic",
+    "retry-policy",
+    "retry-proxy",
+    "reverse-proxy",
     "route-quality",
     "routellm",
+    "routellm-alternative",
     "router",
+    "router-proxy",
+    "routing-accuracy",
+    "routing-benchmark",
+    "routing-quality",
     "s3",
     "salesforce",
     "sanitization",
@@ -167,480 +574,148 @@
     "sdk",
     "security",
     "segment",
+    "self-consistency",
+    "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",
+    "smart-fallback",
+    "smart-llm-router",
+    "smart-router",
+    "smart-routing",
+    "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",
+    "tier-routing",
+    "timeout",
     "together-ai",
+    "together-api",
     "token-compression",
+    "token-counter",
+    "token-counting",
+    "token-optimization",
+    "token-saving",
+    "tongji",
+    "tongyi",
+    "tongyi-qianwen",
     "tools",
+    "trace-id",
     "tracing",
+    "traffic-routing",
     "transformer",
+    "transformers",
+    "translation",
+    "tree-search",
+    "treequest",
     "trello",
     "typescript",
+    "ucb1",
+    "uct",
+    "uptime",
+    "vector-cache",
     "vector-database",
     "vercel",
+    "vercel-ai",
+    "vercel-ai-sdk",
+    "vision-model",
+    "volcengine",
     "websocket",
+    "workflow-automation",
+    "workflow-optimization",
+    "wu-yuan",
+    "wuyuan",
     "xai",
+    "yi",
+    "yi-34b",
+    "yi-ai",
+    "yi-api",
+    "yi-large",
+    "yi-lightning",
+    "yi-llm",
+    "yi-medium",
+    "zai",
+    "zai-glm",
+    "zai-glm-4",
     "zendesk",
-    "llm-proxy",
-    "claude",
-    "ai",
-    "openai-compatible",
-    "no-gpu",
-    "openai",
-    "routing-accuracy",
-    "minimax",
-    "portkey-alternative",
+    "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",
-    "provider-fallback",
-    "nlp",
-    "ollama",
-    "cerebras",
-    "openai-sdk",
-    "ai-sdk",
-    "openai-proxy",
-    "cerebras-proxy",
+    "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",
-    "anthropic",
-    "ai-cost-optimization",
-    "model-router",
-    "model-routing",
-    "chinese-ai",
-    "vercel-ai",
-    "ai-load-balancer",
-    "deepseek",
-    "llm-routing",
-    "mistral",
-    "ollama-proxy",
-    "moonshot",
-    "stepfun",
-    "cost-optimization",
-    "keyword-routing",
-    "zhipu",
-    "llm-manager",
-    "ai-router",
-    "multi-provider",
-    "yi-llm",
-    "chinese-llm",
-    "glms",
-    "llm",
-    "llm-load-balancer",
-    "language-model",
-    "claude-proxy",
-    "lightweight",
-    "chatgpt",
-    "smart-routing",
+    "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",
-    "zh-llm",
-    "中文ai",
-    "benchmark",
-    "helicone",
-    "mistral-proxy",
-    "llm-orchestration",
-    "openrouter",
-    "kimi",
-    "moonshot-kimi",
-    "guardrails",
-    "ai-agent",
-    "baichuan",
-    "routellm-alternative",
-    "anthropic-proxy",
-    "token-counter",
-    "deepseek-proxy",
-    "llm-gateway",
-    "multi-llm",
-    "ai-gateway",
-    "groq",
-    "litellm-alternative",
-    "ai-proxy",
-    "llm-router",
-    "domain-routing",
-    "groq-proxy",
-    "qwen",
-    "gpt",
-    "openai-api",
-    "query-routing",
-    "aleph-alpha",
-    "semantic-cache",
-    "langchain",
-    "ai-guardrails",
-    "chatbot",
-    "a3m",
-    "a3m-router",
-    "adaptive",
-    "memory-based",
-    "multi-model-router",
-    "memory-based-router",
-    "treequest",
-    "parallel-ai",
-    "agent-orchestration",
-    "multi-agent",
-    "parallel",
-    "cost-tracking",
-    "cache",
-    "caching",
-    "exponential-backoff",
-    "mcts",
-    "monte-carlo-tree-search",
-    "workflow-optimization",
-    "hierarchical-planning",
-    "halo",
-    "episodic-memory",
-    "semantic-memory",
-    "agent-memory",
-    "python-bindings",
-    "pypi",
-    "autogen",
-    "crewai",
-    "transformers",
-    "agent-codegen",
-    "ai-coding",
-    "zai",
-    "llama",
-    "ai-agents",
-    "memory-based-llm-router",
-    "multi-llm-router",
-    "llm-memory-router",
-    "adaptive-llm-router",
-    "intelligent-router",
-    "intelligent-llm-router",
-    "learning-router",
-    "contextual-router",
-    "context-aware-router",
-    "task-aware-router",
-    "memory-augmented",
-    "memory-augmented-llm",
-    "episodic-memory-router",
-    "semantic-memory-router",
-    "task-memory",
-    "cross-context-memory",
-    "context-compression",
-    "ison-format",
-    "message-truncation",
-    "context-management",
-    "local-llm",
-    "lmstudio",
-    "local-model",
-    "privacy-llm",
-    "priority-queue",
-    "token-counting",
-    "cost-estimation",
-    "cost-prediction",
-    "intelligent-failover",
-    "kv-cache",
-    "pagedattention",
-    "kv-cache-quantization",
-    "streamingllm",
-    "multimodel-orchestration",
-    "multi-agent-debate",
-    "self-consistency",
-    "tensor-parallelism",
-    "continuous-batching",
-    "arxiv",
-    "research-backed",
-    "icml",
-    "neurips",
-    "iclr",
-    "pi-extension",
-    "pi",
-    "pi-package",
-    "pi-coding-agent",
-    "pi-agent",
-    "agent-discoverable",
-    "ai-native",
-    "01-ai",
-    "01ai",
-    "128k上下文",
-    "ai-gateway-cn",
-    "ai路由",
-    "aliyun",
-    "baichuan-ai",
-    "baichuan2",
-    "baichuan2-flash",
-    "baiducloud",
-    "chinese-ai-proxy",
-    "chinese-api-gateway",
-    "chinese-chatgpt",
-    "chinese-language-model",
-    "chinese-llm-proxy",
-    "chinese-models",
-    "chinese-nlp",
-    "chinesellm",
-    "chinesellm-routing",
-    "deepseek-ai",
-    "deepseek-api",
-    "deepseek-chat",
-    "deepseek-coder",
-    "deepseek-reasoner",
-    "embedding-model",
-    "glm-4",
-    "glm-4-air",
-    "glm-4-flash",
-    "glm-4-long",
-    "glm-4-plus",
-    "huawei-cloud",
-    "langchain-cn",
-    "lingyi",
-    "lingyi-wanwu",
-    "llamaindex-cn",
-    "llm-gateway-cn",
-    "long-context-model",
-    "minimax-ai",
-    "minimax-api",
-    "minimax-chat",
-    "minimax-turbo",
-    "moonshot-ai",
-    "moonshot-v1",
-    "moonshot-v1-128k",
-    "moonshot-v1-32k",
-    "moonshot-v1-8k",
-    "multimodal",
-    "qianwen",
-    "qwen-long",
-    "qwen-max",
-    "qwen-plus",
-    "qwen-turbo",
-    "qwen2",
-    "qwen3",
-    "step-1",
-    "step-1v",
-    "step-2",
-    "tencentcloud",
-    "tongji",
-    "tongyi",
-    "tongyi-qianwen",
-    "vision-model",
-    "volcengine",
-    "wu-yuan",
-    "wuyuan",
-    "yi-ai",
-    "yi-large",
-    "yi-lightning",
-    "yi-medium",
-    "zai-glm",
-    "zai-glm-4",
-    "zhipu-ai",
-    "中国ai",
-    "中国大模型",
-    "中文chatgpt",
-    "中文embedding",
-    "中文langchain",
-    "中文llamaindex",
-    "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",
-    "国产大模型",
-    "多模型路由",
-    "多模态",
-    "大模型路由",
-    "字节ai",
-    "智能路由",
-    "火山引擎",
-    "百度ai",
-    "百度云",
-    "腾讯ai",
-    "腾讯云",
-    "长上下文",
-    "阿里ai",
     "阿里云",
-    "adaptive-routing",
-    "ai-orchestration",
-    "content-routing",
-    "cost-based-routing",
-    "distributed-llm",
-    "dynamic-routing",
-    "failover",
-    "intelligent-load-balancer",
-    "intent-routing",
-    "llm-caching",
-    "llm-cluster",
-    "llm-failover",
-    "llm-management",
-    "load-balancer",
-    "model-management",
-    "model-selection",
-    "provider-selector",
-    "rate-limiter",
-    "request-routing",
-    "retry-proxy",
-    "reverse-proxy",
-    "semantic-routing",
-    "smart-llm-router",
-    "task-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"
+    "零一ai"
   ],
   "author": "Das-rebel <subho@example.com>",
   "license": "MIT",