adaptive-memory-multi-model-router 1.6.0 → 1.7.1
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.
- package/README.md +278 -23
- package/dist/index.js +91 -2
- package/docs/API.md +562 -0
- package/docs/INTEGRATIONS.md +420 -0
- package/docs/QUICKSTART.md +271 -0
- package/package.json +132 -55
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "adaptive-memory-multi-model-router",
|
|
3
|
-
"version": "1.
|
|
3
|
+
"version": "1.7.1",
|
|
4
4
|
"shortName": "A3M Router",
|
|
5
5
|
"displayName": "A3M Router - Adaptive Memory Multi-Model Router",
|
|
6
6
|
"description": "A3M Router - Adaptive Memory Multi-Model Router with learned routing (RouteLLM), prefix caching (RadixAttention), speculative decoding (Medusa), TokenJuice-style compression. 14 LLM providers, 10 integrations, Python bindings. 20x more adaptable for ML/AI developers.",
|
|
@@ -23,68 +23,145 @@
|
|
|
23
23
|
"./integrations": "./dist/integrations/index.js"
|
|
24
24
|
},
|
|
25
25
|
"keywords": [
|
|
26
|
-
"
|
|
27
|
-
"
|
|
28
|
-
"
|
|
29
|
-
"
|
|
30
|
-
"
|
|
31
|
-
"ai-native",
|
|
32
|
-
"ai-agents",
|
|
26
|
+
"llm",
|
|
27
|
+
"router",
|
|
28
|
+
"ai",
|
|
29
|
+
"language-model",
|
|
30
|
+
"openai",
|
|
33
31
|
"anthropic",
|
|
34
|
-
"batch-processing",
|
|
35
|
-
"caching",
|
|
36
|
-
"cerberas",
|
|
37
|
-
"circuit-breaker",
|
|
38
|
-
"claude",
|
|
39
|
-
"claude-router",
|
|
40
|
-
"cohere",
|
|
41
|
-
"context-aware",
|
|
42
|
-
"cost-optimization",
|
|
43
|
-
"deepseek",
|
|
44
|
-
"deepseek-chat",
|
|
45
|
-
"embeddable",
|
|
46
|
-
"fireworks",
|
|
47
|
-
"gemini",
|
|
48
|
-
"github-actions",
|
|
49
32
|
"gpt",
|
|
50
33
|
"gpt-4",
|
|
51
|
-
"
|
|
52
|
-
"
|
|
53
|
-
"
|
|
54
|
-
"langchain",
|
|
55
|
-
"llm",
|
|
56
|
-
"llm-fusion",
|
|
57
|
-
"llm-optimization",
|
|
58
|
-
"llm-router",
|
|
34
|
+
"claude",
|
|
35
|
+
"gemini",
|
|
36
|
+
"ai-routing",
|
|
59
37
|
"llm-routing",
|
|
60
|
-
"llmlingua",
|
|
61
|
-
"local-llm",
|
|
62
|
-
"memory",
|
|
63
|
-
"memory-based",
|
|
64
|
-
"memory-tree",
|
|
65
|
-
"mistral",
|
|
66
|
-
"mixtral",
|
|
67
|
-
"mllm",
|
|
68
|
-
"model-router",
|
|
69
38
|
"multi-model",
|
|
70
|
-
"
|
|
71
|
-
"
|
|
39
|
+
"model-router",
|
|
40
|
+
"llm-router",
|
|
41
|
+
"adaptive-router",
|
|
72
42
|
"openai",
|
|
73
|
-
"
|
|
43
|
+
"anthropic",
|
|
44
|
+
"google",
|
|
45
|
+
"groq",
|
|
46
|
+
"cerebras",
|
|
47
|
+
"deepseek",
|
|
48
|
+
"fireworks",
|
|
74
49
|
"perplexity",
|
|
50
|
+
"cohere",
|
|
51
|
+
"mistral",
|
|
52
|
+
"aws-bedrock",
|
|
53
|
+
"xai",
|
|
54
|
+
"ollama",
|
|
55
|
+
"openrouter",
|
|
56
|
+
"cost-optimization",
|
|
57
|
+
"latency-optimization",
|
|
58
|
+
"token-compression",
|
|
75
59
|
"prefix-caching",
|
|
76
|
-
"provider-router",
|
|
77
|
-
"python-bindings",
|
|
78
|
-
"quantization",
|
|
79
|
-
"radixattention",
|
|
80
|
-
"routellm",
|
|
81
|
-
"self-hosting",
|
|
82
60
|
"speculative-decoding",
|
|
83
|
-
"
|
|
84
|
-
"
|
|
85
|
-
"
|
|
86
|
-
"
|
|
87
|
-
"
|
|
61
|
+
"circuit-breaker",
|
|
62
|
+
"memory-tree",
|
|
63
|
+
"route-quality",
|
|
64
|
+
"batch-processing",
|
|
65
|
+
"parallel-execution",
|
|
66
|
+
"fallback",
|
|
67
|
+
"retry",
|
|
68
|
+
"load-balancing",
|
|
69
|
+
"github",
|
|
70
|
+
"slack",
|
|
71
|
+
"telegram",
|
|
72
|
+
"notion",
|
|
73
|
+
"linear",
|
|
74
|
+
"jira",
|
|
75
|
+
"gmail",
|
|
76
|
+
"discord",
|
|
77
|
+
"airtable",
|
|
78
|
+
"google-calendar",
|
|
79
|
+
"asana",
|
|
80
|
+
"trello",
|
|
81
|
+
"stripe",
|
|
82
|
+
"shopify",
|
|
83
|
+
"hubspot",
|
|
84
|
+
"salesforce",
|
|
85
|
+
"zendesk",
|
|
86
|
+
"intercom",
|
|
87
|
+
"sendgrid",
|
|
88
|
+
"mailchimp",
|
|
89
|
+
"segment",
|
|
90
|
+
"mixpanel",
|
|
91
|
+
"amplitude",
|
|
92
|
+
"posthog",
|
|
93
|
+
"datadog",
|
|
94
|
+
"sentry",
|
|
95
|
+
"pinecone",
|
|
96
|
+
"s3",
|
|
97
|
+
"dropbox",
|
|
98
|
+
"vercel",
|
|
99
|
+
"netlify",
|
|
100
|
+
"gitlab",
|
|
101
|
+
"bitbucket",
|
|
102
|
+
"chatbot",
|
|
103
|
+
"agent",
|
|
104
|
+
"ai-agent",
|
|
105
|
+
"automation",
|
|
106
|
+
"orchestration",
|
|
107
|
+
"mcp",
|
|
108
|
+
"tools",
|
|
109
|
+
"api-gateway",
|
|
110
|
+
"proxy",
|
|
111
|
+
"middleware",
|
|
112
|
+
"sdk",
|
|
113
|
+
"cli",
|
|
114
|
+
"typescript",
|
|
115
|
+
"javascript",
|
|
116
|
+
"nodejs",
|
|
117
|
+
"npm",
|
|
118
|
+
"python",
|
|
119
|
+
"developer-tools",
|
|
120
|
+
"developer-experience",
|
|
121
|
+
"dx",
|
|
122
|
+
"open-source",
|
|
123
|
+
"routellm",
|
|
124
|
+
"radix-attention",
|
|
125
|
+
"medusa",
|
|
126
|
+
"llmlingua",
|
|
127
|
+
"ai-agent-tools",
|
|
128
|
+
"llm-tools",
|
|
129
|
+
"agent-framework",
|
|
130
|
+
"autonomous-agents",
|
|
131
|
+
"machine-learning",
|
|
132
|
+
"nlp",
|
|
133
|
+
"natural-language-processing",
|
|
134
|
+
"transformer",
|
|
135
|
+
"huggingface",
|
|
136
|
+
"langchain",
|
|
137
|
+
"llamaindex",
|
|
138
|
+
"prompt-engineering",
|
|
139
|
+
"rag",
|
|
140
|
+
"retrieval-augmented-generation",
|
|
141
|
+
"vector-database",
|
|
142
|
+
"embedding",
|
|
143
|
+
"fine-tuning",
|
|
144
|
+
"inference",
|
|
145
|
+
"streaming",
|
|
146
|
+
"websocket",
|
|
147
|
+
"rest-api",
|
|
148
|
+
"graphql",
|
|
149
|
+
"serverless",
|
|
150
|
+
"edge-computing",
|
|
151
|
+
"cloud",
|
|
152
|
+
"devops",
|
|
153
|
+
"monitoring",
|
|
154
|
+
"observability",
|
|
155
|
+
"tracing",
|
|
156
|
+
"logging",
|
|
157
|
+
"testing",
|
|
158
|
+
"benchmark",
|
|
159
|
+
"performance",
|
|
160
|
+
"scalability",
|
|
161
|
+
"enterprise",
|
|
162
|
+
"production",
|
|
163
|
+
"real-time",
|
|
164
|
+
"high-availability"
|
|
88
165
|
],
|
|
89
166
|
"author": "Das-rebel <subho@example.com>",
|
|
90
167
|
"license": "MIT",
|
|
@@ -105,4 +182,4 @@
|
|
|
105
182
|
"dependencies": {
|
|
106
183
|
"nanoid": "^5.0.0"
|
|
107
184
|
}
|
|
108
|
-
}
|
|
185
|
+
}
|