adaptive-memory-multi-model-router 2.13.3 → 2.13.5
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/.github/ISSUE_TEMPLATE/config.yml +2 -2
- package/.well-known/ai-plugin.json +1 -1
- package/CONTRIBUTING.md +1 -1
- package/LAUNCH-PAIN-DRIVEN.md +3 -3
- package/LAUNCH.md +7 -7
- package/POPULARITY_BOOSTERS.md +6 -6
- package/README.md +214 -143
- package/README_ja.md +1 -1
- package/README_zh.md +1 -1
- package/SUBMISSIONS.md +2 -2
- package/articles/DEVTO_COST_GUIDE.md +2 -2
- package/articles/DEVTO_FINAL.md +6 -6
- package/articles/DEVTO_MULTI_PROVIDER.md +4 -4
- package/articles/DEVTO_V2_ANNOUNCEMENT.md +2 -2
- package/articles/DEVTO_VIRAL_GROWTH.md +5 -5
- package/articles/FRESH_devto.md +1 -1
- package/articles/FRESH_hackernews.md +1 -1
- package/articles/FRESH_reddit_ml.md +1 -1
- package/articles/FRESH_reddit_node.md +2 -2
- package/articles/FRESH_reddit_sideproject.md +2 -2
- package/articles/FRESH_reddit_webdev.md +2 -2
- package/articles/HN_10X_BETTER.md +2 -2
- package/articles/HN_CHINESE_STYLE.md +5 -5
- package/articles/HN_FINAL.md +1 -1
- package/articles/HN_POSTED_VERSION.md +1 -1
- package/articles/PAIN-DRIVEN-devto-v2.md +2 -2
- package/articles/PAIN-DRIVEN-devto-v3.md +2 -2
- package/articles/PAIN-DRIVEN-devto.md +2 -2
- package/articles/PAIN-DRIVEN-hackernews-v2.md +2 -2
- package/articles/PAIN-DRIVEN-hackernews-v3.md +3 -3
- package/articles/PAIN-DRIVEN-hackernews.md +2 -2
- package/articles/PAIN-DRIVEN-reddit-v2.md +2 -2
- package/articles/PAIN-DRIVEN-reddit-v3.md +2 -2
- package/articles/PAIN-DRIVEN-reddit.md +2 -2
- package/articles/PAIN-DRIVEN-twitter-v2.md +2 -2
- package/articles/PAIN-DRIVEN-twitter-v3.md +2 -2
- package/articles/PAIN-DRIVEN-twitter.md +2 -2
- package/articles/REDDIT_FINAL.md +2 -2
- package/articles/TWITTER_FINAL.md +1 -1
- package/articles/ai-discoverability-llm-routing.md +1 -1
- package/articles/devto-llm-routing.md +2 -2
- package/articles/hackernews-show-hn.md +1 -1
- package/articles/hashnode-llm-cost-optimization.md +1 -1
- package/articles/medium-building-llm-router.md +1 -1
- package/articles/reddit-ml.md +1 -1
- package/articles/twitter-thread-cost-savings.md +1 -1
- package/articles/youtube-tutorial-script.md +1 -1
- package/benchmark-provider-results.json +120 -41
- package/benchmark-results.json +46 -620
- package/demo.html +1 -1
- package/dist/cli/setupWizard.js +1 -1
- package/dist/cli.js +1 -1
- package/dist/geo/generativeEngineOptimization.js +1 -1
- package/dist/tui/index.js +0 -0
- package/docs/BENCHMARK.md +96 -0
- package/docs/HN_CHECKLIST.md +2 -2
- package/docs/HN_SUBMISSION_FINAL.md +2 -2
- package/docs/HN_SUBMISSION_V3.md +3 -3
- package/docs/SEO_AUDIT.md +1 -1
- package/docs/UPDATE_TOPICS.md +1 -1
- package/docs/benchmark-chart.png +0 -0
- package/docs/demo-auto.html +1 -1
- package/docs/demo.html +1 -1
- package/docs/index.html +1 -1
- package/docs/openapi.json +1 -1
- package/docs-site/index.html +7 -7
- package/index.html +4 -4
- package/llms-full.txt +1 -1
- package/llms.txt +1 -1
- package/package.json +21 -6
- package/playground/README.md +4 -4
- package/public/robots.txt +1 -1
- package/python/pyproject.toml +1 -1
- package/scripts/routing-benchmark-v3.js +118 -0
- package/src/cli/setupWizard.ts +1 -1
- package/tmlpd-pi-extension/README.md +1 -1
|
@@ -1,83 +1,162 @@
|
|
|
1
1
|
{
|
|
2
2
|
"meta": {
|
|
3
|
-
"date": "2026-05-
|
|
3
|
+
"date": "2026-05-26T20:20:48.824Z",
|
|
4
4
|
"questions": 10
|
|
5
5
|
},
|
|
6
6
|
"results": {
|
|
7
7
|
"groq-llama-3.3-70b": {
|
|
8
8
|
"name": "Groq Llama 3.3 70B",
|
|
9
9
|
"successRate": 1,
|
|
10
|
-
"avgLatency":
|
|
11
|
-
"avgOutputLen":
|
|
10
|
+
"avgLatency": 325,
|
|
11
|
+
"avgOutputLen": 277,
|
|
12
12
|
"inputCostPer1M": 0,
|
|
13
13
|
"questions": [
|
|
14
14
|
{
|
|
15
15
|
"id": 1,
|
|
16
16
|
"success": true,
|
|
17
|
-
"latency":
|
|
17
|
+
"latency": 262,
|
|
18
18
|
"content": "2 + 2 = 4.",
|
|
19
19
|
"status": 200
|
|
20
20
|
},
|
|
21
21
|
{
|
|
22
22
|
"id": 2,
|
|
23
23
|
"success": true,
|
|
24
|
-
"latency":
|
|
25
|
-
"content": "**Checking
|
|
24
|
+
"latency": 414,
|
|
25
|
+
"content": "**Checking Primality in Python**\n================================\n\nBelow is an example of a Python function that checks whether a given number is prime.\n\n```python\ndef is_prime(n: int) -> bool:\n \"\"\"\n Checks if a number is prime.\n\n Args:\n n (int): The number to check.\n\n Returns:\n bool: True if the number is prime, False otherwise.\n \"\"\"\n if n <= 1:\n return False\n if n == 2:\n return",
|
|
26
26
|
"status": 200
|
|
27
27
|
},
|
|
28
28
|
{
|
|
29
29
|
"id": 3,
|
|
30
30
|
"success": true,
|
|
31
|
-
"latency":
|
|
32
|
-
"content": "An
|
|
31
|
+
"latency": 233,
|
|
32
|
+
"content": "An Application Programming Interface (API) is a set of defined rules and protocols that allows different software systems, applications, or services to communicate and exchange data with each other in a standardized and secure manner.",
|
|
33
33
|
"status": 200
|
|
34
34
|
},
|
|
35
35
|
{
|
|
36
36
|
"id": 4,
|
|
37
37
|
"success": true,
|
|
38
|
-
"latency":
|
|
39
|
-
"content": "Climate change is a complex and multifaceted
|
|
38
|
+
"latency": 430,
|
|
39
|
+
"content": "Climate change is a complex and multifaceted phenomenon, and there are several factors that contribute to it. The main causes of climate change can be divided into two categories: natural and human-induced.\n\n**Natural Causes:**\n\n1. **Volcanic Eruptions**: Volcanic eruptions can release large amounts of ash, sulfur dioxide, and other gases into the atmosphere, which can reflect sunlight and cool the planet.\n2. **Changes in Earth's Orbit**: Changes in Earth's orbit around the",
|
|
40
40
|
"status": 200
|
|
41
41
|
},
|
|
42
42
|
{
|
|
43
43
|
"id": 5,
|
|
44
44
|
"success": true,
|
|
45
|
-
"latency":
|
|
46
|
-
"content": "Code flows like a stream\nLogic
|
|
45
|
+
"latency": 176,
|
|
46
|
+
"content": "Code flows like a stream\nLogic dancing on the screen\nBeauty in the bug",
|
|
47
47
|
"status": 200
|
|
48
48
|
},
|
|
49
49
|
{
|
|
50
50
|
"id": 6,
|
|
51
51
|
"success": true,
|
|
52
|
-
"latency":
|
|
53
|
-
"content": "
|
|
52
|
+
"latency": 541,
|
|
53
|
+
"content": "**Improving AI Models with Data**\n\nArtificial Intelligence (AI) models are only as good as the data they're trained on. The quality, quantity, and diversity of data have a direct impact on the performance and accuracy of AI models. Here's why data is crucial for improving AI models:\n\n* **Training and Validation**: AI models learn from data by identifying patterns, relationships, and trends. The more data available, the better the model can learn and generalize to new, unseen situations.\n*",
|
|
54
54
|
"status": 200
|
|
55
55
|
},
|
|
56
56
|
{
|
|
57
57
|
"id": 7,
|
|
58
58
|
"success": true,
|
|
59
|
-
"latency":
|
|
60
|
-
"content": "1.
|
|
59
|
+
"latency": 144,
|
|
60
|
+
"content": "1. Java\n2. Python\n3. C++",
|
|
61
61
|
"status": 200
|
|
62
62
|
},
|
|
63
63
|
{
|
|
64
64
|
"id": 8,
|
|
65
65
|
"success": true,
|
|
66
|
-
"latency":
|
|
67
|
-
"content": "**Machine Learning
|
|
66
|
+
"latency": 482,
|
|
67
|
+
"content": "**Machine Learning Overview**\n===============\n\nMachine learning (ML) is a subset of artificial intelligence (AI) that involves the use of algorithms and statistical models to enable machines to perform tasks without being explicitly programmed. It allows systems to learn from data, identify patterns, and make decisions or predictions based on that data.\n\n**Key Characteristics**\n--------------------\n\n1. **Data-Driven**: Machine learning relies on large amounts of data to learn and improve its performance.\n2. **Algorithm-Based**: ML uses",
|
|
68
68
|
"status": 200
|
|
69
69
|
},
|
|
70
70
|
{
|
|
71
71
|
"id": 9,
|
|
72
72
|
"success": true,
|
|
73
73
|
"latency": 417,
|
|
74
|
-
"content": "**Reversing a String in Python**\n
|
|
74
|
+
"content": "**Reversing a String in Python**\n=====================================\n\nYou can reverse a string in Python using slicing. Here is a simple function that accomplishes this:\n\n```python\ndef reverse_string(input_str):\n \"\"\"\n Reverses the input string.\n\n Args:\n input_str (str): The string to be reversed.\n\n Returns:\n str: The reversed string.\n \"\"\"\n return input_str[::-1]\n\n# Example usage:\nif __name__ == \"__main__\":\n input_str",
|
|
75
75
|
"status": 200
|
|
76
76
|
},
|
|
77
77
|
{
|
|
78
78
|
"id": 10,
|
|
79
79
|
"success": true,
|
|
80
|
-
"latency":
|
|
80
|
+
"latency": 154,
|
|
81
|
+
"content": "The capital of Japan is Tokyo.",
|
|
82
|
+
"status": 200
|
|
83
|
+
}
|
|
84
|
+
]
|
|
85
|
+
},
|
|
86
|
+
"groq-llama-3.1-8b": {
|
|
87
|
+
"name": "Groq Llama 3.1 8B",
|
|
88
|
+
"successRate": 1,
|
|
89
|
+
"avgLatency": 286,
|
|
90
|
+
"avgOutputLen": 280,
|
|
91
|
+
"inputCostPer1M": 0,
|
|
92
|
+
"questions": [
|
|
93
|
+
{
|
|
94
|
+
"id": 1,
|
|
95
|
+
"success": true,
|
|
96
|
+
"latency": 364,
|
|
97
|
+
"content": "2 + 2 = 4.",
|
|
98
|
+
"status": 200
|
|
99
|
+
},
|
|
100
|
+
{
|
|
101
|
+
"id": 2,
|
|
102
|
+
"success": true,
|
|
103
|
+
"latency": 319,
|
|
104
|
+
"content": "**Prime Number Checker Function**\n=====================================\n\nHere's a Python function to check if a given number is prime or not.\n\n```python\ndef is_prime(n):\n \"\"\"\n Checks if a number is prime.\n\n Args:\n n (int): The number to check.\n\n Returns:\n bool: True if the number is prime, False otherwise.\n \"\"\"\n if n <= 1:\n return False # Numbers less than or equal to 1 are not prime.\n for",
|
|
105
|
+
"status": 200
|
|
106
|
+
},
|
|
107
|
+
{
|
|
108
|
+
"id": 3,
|
|
109
|
+
"success": true,
|
|
110
|
+
"latency": 189,
|
|
111
|
+
"content": "An API (Application Programming Interface) is a set of defined rules and protocols that enables different software systems to communicate with each other, exchanging data and functionality to achieve a specific task or outcome.",
|
|
112
|
+
"status": 200
|
|
113
|
+
},
|
|
114
|
+
{
|
|
115
|
+
"id": 4,
|
|
116
|
+
"success": true,
|
|
117
|
+
"latency": 371,
|
|
118
|
+
"content": "Climate change is a complex issue with multiple causes, but some of the main contributors include:\n\n1. **Greenhouse gases**: The burning of fossil fuels such as coal, oil, and gas releases carbon dioxide (CO2), methane (CH4), and other gases that trap heat in the atmosphere, leading to global warming. The main greenhouse gases responsible for climate change are:\n\t* Carbon dioxide (CO2): 65% of human-caused greenhouse gas emissions.\n\t* Methane (CH",
|
|
119
|
+
"status": 200
|
|
120
|
+
},
|
|
121
|
+
{
|
|
122
|
+
"id": 5,
|
|
123
|
+
"success": true,
|
|
124
|
+
"latency": 193,
|
|
125
|
+
"content": "Code flows like the sea\nPuzzles solved in digital\nSilent, dark delight",
|
|
126
|
+
"status": 200
|
|
127
|
+
},
|
|
128
|
+
{
|
|
129
|
+
"id": 6,
|
|
130
|
+
"success": true,
|
|
131
|
+
"latency": 396,
|
|
132
|
+
"content": "**Summary:**\n\nAI models, a key component of Artificial Intelligence, improve significantly with access to a large and diverse dataset. The quality and quantity of the data play a crucial role in enhancing the performance, accuracy, and efficiency of AI models.\n\nHere are some key points summarizing the importance of data in AI model improvement:\n\n1. **Training and Learning**: AI models learn from data by identifying patterns, relationships, and trends. The more data provided, the better the model can learn and improve.\n",
|
|
133
|
+
"status": 200
|
|
134
|
+
},
|
|
135
|
+
{
|
|
136
|
+
"id": 7,
|
|
137
|
+
"success": true,
|
|
138
|
+
"latency": 149,
|
|
139
|
+
"content": "Here are three programming languages:\n\n1. Java\n2. Python\n3. C++",
|
|
140
|
+
"status": 200
|
|
141
|
+
},
|
|
142
|
+
{
|
|
143
|
+
"id": 8,
|
|
144
|
+
"success": true,
|
|
145
|
+
"latency": 273,
|
|
146
|
+
"content": "Machine learning (ML) is a subset of artificial intelligence (AI) that involves the use of algorithms and statistical models to enable computers to learn from data, make decisions, and improve their performance on a task without being explicitly programmed. In other words, machine learning allows computers to learn from experience and improve their accuracy over time.\n\nMachine learning typically involves the following steps:\n\n1. **Data collection**: Gathering a large dataset relevant to the problem you want to solve.\n2. **Model training**: Using the",
|
|
147
|
+
"status": 200
|
|
148
|
+
},
|
|
149
|
+
{
|
|
150
|
+
"id": 9,
|
|
151
|
+
"success": true,
|
|
152
|
+
"latency": 476,
|
|
153
|
+
"content": "**Reversing a String in Python**\n=====================================\n\nYou can reverse a string in Python using the slicing feature of the language. Here's an example:\n\n```python\ndef reverse_string(s):\n \"\"\"\n Reverse a string.\n\n Args:\n s (str): The string to be reversed.\n\n Returns:\n str: The reversed string.\n \"\"\"\n return s[::-1]\n\n# Example usage:\nprint(reverse_string(\"Hello World\")) # Output: \"dlroW olle",
|
|
154
|
+
"status": 200
|
|
155
|
+
},
|
|
156
|
+
{
|
|
157
|
+
"id": 10,
|
|
158
|
+
"success": true,
|
|
159
|
+
"latency": 129,
|
|
81
160
|
"content": "The capital of Japan is Tokyo.",
|
|
82
161
|
"status": 200
|
|
83
162
|
}
|
|
@@ -86,78 +165,78 @@
|
|
|
86
165
|
"groq-qwen-3-32b": {
|
|
87
166
|
"name": "Groq Qwen 3 32B",
|
|
88
167
|
"successRate": 1,
|
|
89
|
-
"avgLatency":
|
|
90
|
-
"avgOutputLen":
|
|
168
|
+
"avgLatency": 459,
|
|
169
|
+
"avgOutputLen": 454,
|
|
91
170
|
"inputCostPer1M": 0,
|
|
92
171
|
"questions": [
|
|
93
172
|
{
|
|
94
173
|
"id": 1,
|
|
95
174
|
"success": true,
|
|
96
|
-
"latency":
|
|
97
|
-
"content": "<think>\nOkay, so
|
|
175
|
+
"latency": 648,
|
|
176
|
+
"content": "<think>\nOkay, so the question is, What is 2+2? Hmm, that's pretty straightforward. But let me make sure I'm not missing anything. First, let's recall basic addition. Adding two numbers means combining their quantities. So, two plus two should be four. But wait, is there any context where this might not be the case? Like, are we talking about regular integers here? I don't think so. The user didn't specify anything unusual, so it",
|
|
98
177
|
"status": 200
|
|
99
178
|
},
|
|
100
179
|
{
|
|
101
180
|
"id": 2,
|
|
102
181
|
"success": true,
|
|
103
|
-
"latency":
|
|
104
|
-
"content": "<think>\nOkay, I need to write a Python function to check if a number is prime.
|
|
182
|
+
"latency": 307,
|
|
183
|
+
"content": "<think>\nOkay, I need to write a Python function to check if a number is prime. Let me think about how to approach this. \n\nFirst, what's a prime number? A prime number is a number greater than 1 that has no divisors other than 1 and itself. So numbers less than 2 aren't prime. For example, 2 is prime, 3 is prime, but 4 is not because it's divisible by 2.\n\nSo the function should return",
|
|
105
184
|
"status": 200
|
|
106
185
|
},
|
|
107
186
|
{
|
|
108
187
|
"id": 3,
|
|
109
188
|
"success": true,
|
|
110
|
-
"latency":
|
|
111
|
-
"content": "<think>\nOkay,
|
|
189
|
+
"latency": 417,
|
|
190
|
+
"content": "<think>\nOkay, I need to explain what an API is in one sentence. Let me start by recalling what I know. API stands for Application Programming Interface. From what I've heard, it's a way for different software applications to communicate with each other. So, maybe something like, \"An API is a set of protocols and tools that allow different software applications to communicate with each other.\" Wait, does that cover it?\n\nLet me check another angle. APIs act as intermediaries between different systems",
|
|
112
191
|
"status": 200
|
|
113
192
|
},
|
|
114
193
|
{
|
|
115
194
|
"id": 4,
|
|
116
195
|
"success": true,
|
|
117
|
-
"latency":
|
|
118
|
-
"content": "<think>\nOkay, I need to figure out what causes climate change. Let
|
|
196
|
+
"latency": 380,
|
|
197
|
+
"content": "<think>\nOkay, I need to figure out what causes climate change. Let's start by recalling what I know. Climate change is when the Earth's average temperature rises over time, right? But what actually causes this? I've heard about greenhouse gases being a major factor. Maybe things like carbon dioxide (CO2) and methane? I think cars, factories, and burning fossil fuels like coal, oil, and natural gas release a lot of CO2. That probably traps heat in the atmosphere.",
|
|
119
198
|
"status": 200
|
|
120
199
|
},
|
|
121
200
|
{
|
|
122
201
|
"id": 5,
|
|
123
202
|
"success": true,
|
|
124
|
-
"latency":
|
|
125
|
-
"content": "<think>\nOkay, I need to write a haiku about programming. Let me start by recalling what a haiku is. It's a traditional Japanese poem with three lines. The
|
|
203
|
+
"latency": 553,
|
|
204
|
+
"content": "<think>\nOkay, I need to write a haiku about programming. Let me start by recalling what a haiku is. It's a traditional Japanese poem with three lines. The structure is 5 syllables in the first line, 7 in the second, and 5 in the third. So, 5-7-5.\n\nFirst, I should brainstorm words and concepts related to programming. Words like code, debug, logic, syntax, loops, algorithms, bugs, servers, maybe",
|
|
126
205
|
"status": 200
|
|
127
206
|
},
|
|
128
207
|
{
|
|
129
208
|
"id": 6,
|
|
130
209
|
"success": true,
|
|
131
210
|
"latency": 518,
|
|
132
|
-
"content": "<think>\nOkay, the user wants
|
|
211
|
+
"content": "<think>\nOkay, the user wants a summary of \"AI models improve with data.\" Let me start by understanding the core idea here. The main point is that more data leads to better AI performance. But I need to make sure to cover the key aspects.\n\nFirst, I should mention that data is essential for training AI models. Then, explain how additional data helps the model learn patterns and generalize better. Maybe include types of data like diverse and high-quality examples. Also, data expansion techniques like data",
|
|
133
212
|
"status": 200
|
|
134
213
|
},
|
|
135
214
|
{
|
|
136
215
|
"id": 7,
|
|
137
216
|
"success": true,
|
|
138
|
-
"latency":
|
|
139
|
-
"content": "<think>\nOkay, the user
|
|
217
|
+
"latency": 518,
|
|
218
|
+
"content": "<think>\nOkay, the user wants a list of three programming languages. Let me think about which ones to mention. Popular ones like Python, JavaScript, and Java come to mind. Python is great for beginners because of its readability. JavaScript is essential for web development, both front-end and with Node.js for back-end. Java has been around a long time and is widely used in enterprise applications. Alternatively, I could include C++ or C# for systems programming or game development. Let me make sure",
|
|
140
219
|
"status": 200
|
|
141
220
|
},
|
|
142
221
|
{
|
|
143
222
|
"id": 8,
|
|
144
223
|
"success": true,
|
|
145
|
-
"latency":
|
|
146
|
-
"content": "<think>\nOkay, the user is asking
|
|
224
|
+
"latency": 464,
|
|
225
|
+
"content": "<think>\nOkay, so the user is asking \"What is machine learning?\" Let me start by recalling what I know. Machine learning is a subset of artificial intelligence, right? But I need to explain it clearly without jargon. Maybe start with the basic definition: it's about making computers learn from data without being explicitly programmed.\n\nWait, how does that work? I should mention algorithms that improve with experience. Maybe use examples like email spam filters or recommendation systems. Oh, and there are different types",
|
|
147
226
|
"status": 200
|
|
148
227
|
},
|
|
149
228
|
{
|
|
150
229
|
"id": 9,
|
|
151
230
|
"success": true,
|
|
152
|
-
"latency":
|
|
153
|
-
"content": "<think>\nOkay, I need to figure out how to reverse a string in Python. Let me think... Hmm, I remember that strings in Python are immutable, so maybe I
|
|
231
|
+
"latency": 368,
|
|
232
|
+
"content": "<think>\nOkay, I need to figure out how to reverse a string in Python. Let me think... Hmm, I remember that strings in Python are immutable, so maybe I need to convert it into a list first? Wait, but there's probably a simpler way. Oh right! String slicing can do that.\n\nWait, how does slicing work again? Like, the syntax is [start:stop:step]. So if I want to reverse it, I can set the step to -1.",
|
|
154
233
|
"status": 200
|
|
155
234
|
},
|
|
156
235
|
{
|
|
157
236
|
"id": 10,
|
|
158
237
|
"success": true,
|
|
159
|
-
"latency":
|
|
160
|
-
"content": "<think>\nOkay,
|
|
238
|
+
"latency": 415,
|
|
239
|
+
"content": "<think>\nOkay, the user is asking for the capital of Japan. Let me start by recalling what I know. Japan is an island nation in East Asia. Its capital is... hmm, I think it's Tokyo. But wait, wasn't there a time when the capital was Kyoto or something else? Let me verify.\n\nI remember that Japan used to have Kyoto as its capital for a long time, especially during the feudal era. But after the Meiji Restoration in the late 19th",
|
|
161
240
|
"status": 200
|
|
162
241
|
}
|
|
163
242
|
]
|