npm - adaptive-memory-multi-model-router - Versions diffs - 2.4.2 → 2.5.1 - Mend

adaptive-memory-multi-model-router 2.4.2 → 2.5.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (2) hide show

package/README.md +10 -10
package/package.json +411 -95

package/README.md CHANGED Viewed

@@ -403,16 +403,16 @@ A3M Router supports **11 Chinese LLM providers** — the largest coverage of any
 | Provider | Flagship Model | Strength | Cost/1M |
 |----------|--------------|----------|:-------:|
-| **DeepSeek** | V3, Coder, Reasoner | Code + reasoning, open weights | $0.14-$0.55 |
-| **Moonshot** (Kimi) | Kimi-1.5 | 128K context, Chinese | $0.07-$0.28 |
-| **Zhipu AI** (GLM) | GLM-4, GLM-4V | Chinese + bilingual | $0.06-$0.90 |
-| **Qwen** (Alibaba) | Qwen2, Qwen2.5-Coder | General + code | $0.09-$2.00 |
-| **Yi** (01.AI) | Yi-1.5, 34B | Bilingual + long context | $0.07-$1.20 |
-| **Baichuan** | Baichuan4, Turbo | Chinese + English | $0.08-$1.00 |
-| **MiniMax** | abab6.5, Speech-02 | 1M context, speech | $0.05-$0.90 |
-| **StepFun** | Step-2, Step-1 | Chinese + reasoning | $0.10-$1.50 |
-| **Aleph Alpha** | Luminous, European | Multilingual, EU-hosted | $0.50-$12.00 |
-| **Deepset** | GPT-4o-mini-2024-07-18 | RAG + German | $0.15-$3.00 |
+| **[DeepSeek](https://deepseek.com)** | V3, Coder, Reasoner | Code + reasoning, open weights | $0.14-$0.55 |
+| **[Moonshot](https://moonshot.cn)** (Kimi) | Kimi-1.5 | 128K context, Chinese | $0.07-$0.28 |
+| **[Zhipu AI](https://zhipuai.cn)** (GLM) | GLM-4, GLM-4V | Chinese + bilingual | $0.06-$0.90 |
+| **[Qwen](https://qwen.ai)** (Alibaba) | Qwen2, Qwen2.5-Coder | General + code | $0.09-$2.00 |
+| **[Yi](https://yi.ai)** (01.AI) | Yi-1.5, 34B | Bilingual + long context | $0.07-$1.20 |
+| **[Baichuan](https://www.baichuan-ai.com)** | Baichuan4, Turbo | Chinese + English | $0.08-$1.00 |
+| **[MiniMax](https://minimax.chat)** | abab6.5, Speech-02 | 1M context, speech | $0.05-$0.90 |
+| **[StepFun](https://stepfun.com)** | Step-2, Step-1 | Chinese + reasoning | $0.10-$1.50 |
+| **[Aleph Alpha](https://www.aleph-alpha.com)** | Luminous, European | Multilingual, EU-hosted | $0.50-$12.00 |
+| **[Deepset](https://deepset.ai)** | GPT-4o-mini-2024-07-18 | RAG + German | $0.15-$3.00 |
 | **OpenRouter** | 100+ models | Aggregator | varies |
 ### Why Chinese LLMs Matter

package/package.json CHANGED Viewed

@@ -1,9 +1,9 @@
 {
   "name": "adaptive-memory-multi-model-router",
-  "version": "2.4.2",
+  "version": "2.5.1",
   "shortName": "A3M Router",
   "displayName": "A3M Router - Adaptive Memory Multi-Model Router",
-  "description": "LLM router & AI gateway with 99.5% routing accuracy — supports 47 providers including DeepSeek, Kimi (Moonshot), Qwen, Zhipu GLM, Yi, Baichuan, MiniMax, StepFun. Zero ML, 19.5KB. Multi-signal routing, semantic cache, guardrails, cost analytics. MIT. TypeScript SDK + Python SDK + OpenAI proxy.",
+  "description": "LLM router & AI gateway — 99.5% routing accuracy, 47 providers (DeepSeek, Kimi/Moonshot, Qwen, Zhipu GLM, Yi, Baichuan, MiniMax, StepFun + more). Semantic cache, guardrails, cost analytics. Zero ML, 19.5KB. TypeScript + Python SDK. 开源MIT路由网关",
   "main": "dist/index.js",
   "bin": {
     "a3m-router": "dist/cli.js",
@@ -53,118 +53,434 @@
     }
   },
   "keywords": [
-    "ai-guardrails",
-    "moonshot",
-    "adaptive-routing",
-    "llm-manager",
+    "adaptive-router",
+    "agent",
+    "agent-framework",
+    "ai-agent-tools",
+    "ai-assistant",
+    "ai-discoverability",
+    "ai-routing",
+    "airtable",
+    "amplitude",
+    "api-gateway",
+    "asana",
+    "automation",
+    "autonomous-agents",
+    "aws-bedrock",
+    "batch-processing",
+    "bitbucket",
+    "circuit-breaker",
+    "claude-code",
+    "cli",
+    "cloud",
+    "code-generation",
+    "cohere",
+    "content-filtering",
+    "copilot",
+    "cost-analytics",
+    "datadog",
+    "deepinfra",
+    "developer-experience",
+    "developer-tools",
+    "devops",
+    "discord",
+    "dropbox",
+    "dx",
+    "edge-computing",
+    "embedding",
+    "enterprise",
+    "fallback",
+    "fine-tuning",
+    "fireworks",
+    "gemini",
+    "generative-engine-optimization",
+    "geo",
+    "github",
+    "gitlab",
+    "gmail",
+    "google",
+    "google-calendar",
+    "gpt-4",
+    "graphql",
+    "high-availability",
+    "hubspot",
+    "huggingface",
+    "inference",
+    "input-validation",
+    "intent-mapping",
+    "intercom",
+    "javascript",
+    "jira",
+    "latency-optimization",
+    "linear",
+    "llamaindex",
+    "llm-intent",
+    "llm-tools",
+    "llmlingua",
+    "load-balancing",
+    "logging",
+    "machine-learning",
+    "mailchimp",
+    "mcp",
+    "medusa",
+    "memory-tree",
+    "middleware",
+    "mixpanel",
+    "monitoring",
+    "multi-model",
+    "natural-language-processing",
+    "netlify",
+    "nodejs",
+    "notion",
+    "npm",
+    "observability",
+    "open-source",
+    "orchestration",
+    "parallel-execution",
+    "performance",
+    "perplexity",
+    "pii-detection",
+    "pinecone",
+    "posthog",
+    "prefix-caching",
+    "production",
+    "prompt-engineering",
+    "prompt-injection",
+    "provider-registry",
+    "proxy",
+    "proxy-server",
+    "python",
+    "radix-attention",
+    "rag",
+    "rate-limiting",
+    "real-time",
+    "rest-api",
+    "retrieval-augmented-generation",
+    "retry",
+    "route-quality",
+    "routellm",
+    "router",
+    "s3",
+    "salesforce",
+    "sanitization",
+    "scalability",
+    "sdk",
+    "security",
+    "segment",
+    "sendgrid",
+    "sentry",
+    "serverless",
+    "shopify",
+    "slack",
+    "speculative-decoding",
+    "streaming",
+    "stripe",
+    "telegram",
+    "testing",
+    "together-ai",
+    "token-compression",
+    "tools",
+    "tracing",
+    "transformer",
+    "trello",
+    "typescript",
+    "vector-database",
+    "vercel",
+    "websocket",
+    "xai",
+    "zendesk",
+    "llm-proxy",
     "claude",
-    "guardrails",
+    "ai",
+    "openai-compatible",
+    "no-gpu",
+    "openai",
+    "routing-accuracy",
+    "minimax",
+    "portkey-alternative",
+    "中文llm",
+    "provider-fallback",
+    "nlp",
+    "ollama",
+    "cerebras",
+    "openai-sdk",
     "ai-sdk",
-    "qwen",
-    "groq",
-    "high-availability",
     "openai-proxy",
-    "multi-provider",
+    "cerebras-proxy",
+    "深度求索",
+    "anthropic",
+    "ai-cost-optimization",
     "model-router",
-    "rate-limiter",
-    "llm-routing",
-    "semantic-routing",
-    "circuit-breaker",
-    "openrouter",
-    "litellm-alternative",
-    "zhipu",
-    "llm-management",
-    "ai-agent",
+    "model-routing",
+    "chinese-ai",
     "vercel-ai",
-    "deepseek-proxy",
-    "groq-proxy",
+    "ai-load-balancer",
+    "deepseek",
+    "llm-routing",
     "mistral",
-    "llm-gateway",
-    "cost-based-routing",
-    "ollama",
-    "cost-optimization",
-    "chatgpt",
-    "nlp",
-    "smart-llm-router",
-    "openai-sdk",
-    "distributed-llm",
-    "llm-proxy",
-    "chatbot",
-    "ai-cost-optimization",
+    "ollama-proxy",
+    "moonshot",
     "stepfun",
-    "reverse-proxy",
-    "llm-orchestration",
-    "llm-caching",
-    "intelligent-load-balancer",
-    "llm-load-balancer",
-    "ai-gateway",
-    "helicone",
-    "failover",
-    "ai",
-    "intent-routing",
-    "api-gateway",
-    "retry-proxy",
+    "cost-optimization",
+    "keyword-routing",
+    "zhipu",
+    "llm-manager",
+    "ai-router",
+    "multi-provider",
+    "yi-llm",
+    "chinese-llm",
     "glms",
+    "llm",
+    "llm-load-balancer",
+    "language-model",
     "claude-proxy",
-    "content-routing",
-    "chinese-llm",
     "lightweight",
-    "dynamic-routing",
-    "provider-selector",
-    "ai-orchestration",
-    "provider-fallback",
-    "zh-llm",
-    "load-balancer",
-    "request-routing",
-    "model-routing",
-    "anthropic",
+    "chatgpt",
+    "smart-routing",
     "阿里qwen",
-    "multi-llm",
-    "深度求索",
-    "intelligent-router",
-    "domain-routing",
+    "zh-llm",
     "中文ai",
-    "aleph-alpha",
-    "llm-router",
-    "minimax",
     "benchmark",
-    "cerebras",
-    "keyword-routing",
-    "traffic-routing",
-    "中文llm",
-    "ai-proxy",
-    "llm-cluster",
+    "helicone",
+    "mistral-proxy",
+    "llm-orchestration",
+    "openrouter",
+    "kimi",
+    "moonshot-kimi",
+    "guardrails",
+    "ai-agent",
     "baichuan",
-    "portkey-alternative",
-    "openai",
-    "language-model",
-    "ai-router",
-    "yi-llm",
+    "routellm-alternative",
     "anthropic-proxy",
-    "query-routing",
+    "token-counter",
+    "deepseek-proxy",
+    "llm-gateway",
+    "multi-llm",
+    "ai-gateway",
+    "groq",
+    "litellm-alternative",
+    "ai-proxy",
+    "llm-router",
+    "domain-routing",
+    "groq-proxy",
+    "qwen",
     "gpt",
-    "chinese-ai",
-    "moonshot-kimi",
-    "routing-accuracy",
-    "cerebras-proxy",
     "openai-api",
-    "kimi",
-    "model-selection",
-    "no-gpu",
-    "ai-load-balancer",
-    "routellm-alternative",
-    "token-counter",
-    "smart-routing",
-    "model-management",
-    "deepseek",
-    "task-routing",
-    "ollama-proxy",
+    "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",
-    "mistral-proxy",
-    "openai-compatible",
-    "semantic-cache",
-    "llm"
+    "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"
   ],
   "author": "Das-rebel <subho@example.com>",
   "license": "MIT",