@aiagenta2z/agtm 1.0.5 → 1.0.8

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 CHANGED
@@ -1,227 +1,259 @@
1
1
 
2
- ### agtm: Command Line CLI Tool for AI Agent Registry in the Open Source AI Agent Marketplace
2
+ ### agtm: CLI Tool for AI Agent Management, Skills, Agent Registry, Benchmarks and Hints in AI Agent Marketplace
3
3
 
4
- [GitHub](https://github.com/aiagenta2z/agtm)|[AI Agent Marketplace CLI Doc](https://www.deepnlp.org/doc/ai_agent_marketplace)|[DeepNLP AI Agent Marketplace](https://www.deepnlp.org/store/ai-agent) | [OneKey Agent Router](https://www.deepnlp.org/agent/onekey-mcp-router) | [Agent MCP OneKey Router Ranking](https://www.deepnlp.org/agent/rankings)
4
+ [GitHub](https://github.com/aiagenta2z/agtm)|[AI Agent Marketplace CLI Doc](https://www.deepnlp.org/doc/ai_agent_marketplace)|[DeepNLP AI Agent Marketplace](https://www.deepnlp.org/store/ai-agent) | [OneKey Agent Router](https://www.deepnlp.org/agent/onekey-mcp-router) | [Agent MCP OneKey Router Ranking](https://www.deepnlp.org/agent/rankings) | [NodeJS agtm](https://www.npmjs.com/package/@aiagenta2z/agtm)
5
5
 
6
+ `agtm` (AI Agent Management CLI) unifies skill management, agent registration, marketplace search, and provider CLI execution. Install skills from GitHub, log and rate skill runs, upload agent metadata to registries, query the public marketplace, and run agent toolchains with fuzzy hints.
6
7
 
7
- The command line `agtm --upload` , `agtm --search` helps users to register and publish their AI Agents meta api information from agent.json/agent.yaml file
8
- or a github repo URL in a few seconds.
8
+ Features
9
9
 
10
- 'agtm' means 'ai agent marketplace' or 'ai agent manager'
11
- To use the command line, you need to first install the package either using python or node environment
10
+ *`agtm skills`*: Manage Skills, Add Skills, List Skills, Log Skills Performance, Skills performance Evaluator, compare to realworld benchmarks
11
+ *`agtm upload`*: AI Agent Registry, register local agent meta information of json or yaml format(agent.json/agent.yaml) or sync your github source meta including README.md
12
+ *`agtm search`*: Search the open source AI Agent Marketplace, including github community, huggingface community, product hunt community, deepnlp ai agent marketplace index, etc
13
+ *`agtm run`*: Run agent clis, don't need to remember, with the powerful hints and completion ability, just type a few characters and "--hint" will help you complete the command line.
12
14
 
15
+ Furthermore, `agtm` provides memory to track skill outputs and enables performance rating against industry job level benchmarks. This allows you to score each skill execution and assign a professional tier to your AI Agent's capabilities—for example, evaluating its performance as equivalent to that of an L3 or L5 software engineer, marketing prefessional, etc.
13
16
 
14
- #### Install and Use `agtm` CLI
15
- Python
16
- ``` Python
17
- pip install ai-agent-marketplace
17
+ ```shell
18
+ skill_id run_times score level
19
+ ------------------- --------- ----- -----
20
+ code_success_skills 5 0.9 L3(100%)
18
21
  ```
19
22
 
20
- Node
23
+ ## Quickstart
24
+
25
+ ### Installation
26
+
27
+ **Node**
21
28
  ``` NodeJS
22
29
  npm install -g @aiagenta2z/agtm
23
30
  ```
24
31
 
32
+ Agtm CLI Options
25
33
 
26
- note: run nodejs environment, you need to add -g to install, so you can just run command line `agtm` without the `npx agtm` prefix,
27
-
28
-
29
- Command line to register your AI agent from GitHub, Local config(agent.json, agent.yaml) or search the AI agent marketplace.
30
- To see detailed usage, visit the GitHub of `agtm` at Documentation (https://github.com/aiagenta2z/ai-agent-marketplace)
31
-
34
+ | CLI | Command and Options | Document |
35
+ |-------------|-------------------------------------------|--------------------------------|
36
+ | agtm skills | add, list, log, rate | [Doc](../docs/skills/README.md) |
37
+ | agtm search | --q query | [Doc](../docs/registry/README.md) |
38
+ | agtm upload | --github --config to local agent meta | [Doc](../docs/registry/README.md) |
39
+ | agtm run | --hint agent-cli hint and auto completion | [Doc](../docs/run/README.md) |
32
40
 
33
- #### Tutorial
41
+ ## `skills`
34
42
 
35
- Let's say you have create a repo of your open source AI Agent (e.g. https://github.com/AI-Hub-Admin/My-First-AI-Coding-Agent), And you want to
36
- register and get a registered detailed page of AI Agent in the marketplace and monitor the traffic.
43
+ ### skills add
37
44
 
38
- **1. Setup Access Key**
39
-
40
- First you need to setup an access_key in the environment to authenticate.
41
- Register your AI Agent Marketplace Access Key here (https://deepnlp.org/workspace/keys)
45
+ Download and add skills to your agent directory.
42
46
 
47
+ #### Usage
43
48
  ```
44
- export AI_AGENT_MARKETPLACE_ACCESS_KEY="{your_access_key}"
49
+ agtm skills add <unique_id>
50
+ agtm skills add <github_url>
51
+ agtm skills add <github_url> -a <agent_id>
52
+ agtm skills add <owner_id/repo_id> -s <skill_id>
45
53
  ```
46
54
 
47
- You can also use the test key for validation, which is associated with a test-only account on deepnlp.org and aiagenta2z.com.
48
-
55
+ #### Example
49
56
  ```
50
- export AI_AGENT_MARKETPLACE_ACCESS_KEY="TEST_KEY_AI_AGENT_REGISTRY"
57
+ agtm skills add anthropics/skills -a claude-code ## install skills only to claude-codex
58
+ agtm skills add msitarzewski/agency-agents
59
+ agtm skills add aiagenta2z/onekey-gateway
60
+ agtm skills add msitarzewski/agency-agents -s academic-anthropologist -a codex
61
+ agtm skills add anthropics/skills -s skill-creator -a claude-code --global
51
62
  ```
52
63
 
53
- **2. Registry AI Agent from your GitHub**
64
+ ### skills list
54
65
 
55
- The default registry provider endpoint includes: [DeepNLP AI Agent Registry Endpoint](https://www.deepnlp.org/api/ai_agent_marketplace/registry) |
56
- [aiagenta2z.com Registry Endpoint](https://www.aiagenta2z.com/api/ai_agent_marketplace/registry)|[aiagenta2z.org Registry Endpoint](https://www.aiagenta2z.org/api/ai_agent_marketplace/registry), etc.
66
+ #### Usage
67
+ ```
68
+ agtm skills list
69
+ agtm skills list --agent <agent_id> --global
70
+ ```
71
+ Lists installed skills with `agent`, `skill_id`, `description`, install `path`, average `score`, and aggregated `level` (if ratings exist).
57
72
 
58
- You can also set your customized registry endpoint via `--endpoint` parameter
59
73
 
60
74
 
75
+ #### Example
61
76
  ```
62
- agtm upload --github https://github.com/AI-Hub-Admin/My-First-AI-Coding-Agent
77
+ agtm skills list
78
+ agtm skills list --agent codex
79
+ agtm skills list --agent claude-code --global
63
80
  ```
64
81
 
65
82
 
66
- **3. Registry AI Agent from agent.json or agent.yaml file**
67
-
83
+ ### skills log
68
84
 
85
+ #### Usage
86
+ ```
87
+ agtm skills log <skill_id> --data '<json_payload>'
69
88
  ```
89
+ - Persists a run record at `.agtm/skills/log/<uuid>.json` (or the `--logDir` you supply).
90
+ - `<json_payload>` must contain at least `input` and `output`; optional fields (meta, rating, level) are accepted.
70
91
 
71
- ## Register from local config of AI Agent meta
72
- agtm upload --config ./agent.json
73
- agtm upload --config ./agent.yaml
92
+ #### Example
93
+ ```
94
+ agtm skills log <skill_id> --data '{"input":"write a website for store","output":"success"}'
95
+ agtm skills log code_success_skills --data '{"input":"generate sql","output":"ok","meta":{"agent":"claude-code"}}'
74
96
  ```
75
97
 
76
- You can download sample [agent.json](https://github.com/aiagenta2z/agtm/blob/main/agent.json) or [agent.yaml](https://github.com/aiagenta2z/agtm/blob/main/agent.yaml) file from github https://github.com/aiagenta2z/agtm
77
- See the explanation of the schema, please visit the [documentation](https://www.deepnlp.org/doc/ai_agent_marketplace).
98
+ ### skills rate
78
99
 
100
+ #### Setup
79
101
 
80
- Demo agent.json file
102
+ To use the rate command, have to setup the benchmark levels configuration. save to `./agtm/levels/*.json` files
103
+ ```shell
104
+ agtm setup --levels
81
105
  ```
82
- {
83
- "name": "My First AI Coding Agent",
84
- "content": "This AI Agent can do complicated programming work for humans",
85
- "website": "https://www.my_first_agent.com",
86
- "field": "AI AGENT",
87
- "subfield": "Coding Agent",
88
- "content_tag_list": "coding,python",
89
- "github": "",
90
- "thumbnail_picture": "https://avatars.githubusercontent.com/u/242328252?s=200&v=4",
91
- "upload_image_files": "",
92
- "api": "https://www.my_first_agent.com/agent",
93
- "price_type": "PER_CALL",
94
- "price_per_call_credit": 0.0,
95
- "price_fixed_credit" : 0.0,
96
- "price_subscription": "Basic: your basic plan introduction, Advanced: Your Advanced Plan introduction, etc."
97
- }
106
+
107
+ #### Usage
98
108
  ```
99
- Demo agent.yaml file
109
+ agtm skills rate prepare --skill_id <skill_id> --prompt "<eval_prompt>" --benchmark <path/benchmark.json>
110
+ agtm skills rate apply --skill_id <skill_id> --result '<result_json>'
111
+ agtm skills rate show --skill_id <skill_id>
100
112
  ```
113
+ - `prepare` exports logs plus the top benchmark slices (e.g., Google SWE L3–L7) for an external evaluator.
114
+ - `apply` writes evaluator outputs (`rating`, `level`) back to each log.
115
+ - `show` summarizes run counts, average score, and level distribution.
101
116
 
102
- name: "My First AI Coding Agent"
103
- content: "This AI Agent can do complicated programming work for humans"
104
- website: "https://www.my_first_agent.com"
105
- field: "AI AGENT"
106
- subfield: "Coding Agent"
107
- content_tag_list: "coding,python"
108
- github: "https://github.com/AI-Hub-Admin/My-First-AI-Coding-Agent"
109
- thumbnail_picture: "https://avatars.githubusercontent.com/u/242328252?s=200&v=4"
110
- upload_image_files: ""
111
- api: "https://www.my_first_agent.com/agent"
112
- price_type: "API Call"
113
- price_per_call_credit: 0.0
114
- price_fixed_credit: 0.0
115
- price_subscription: "Basic: your basic plan introduction, Advanced: Your Advanced Plan introduction, etc."
116
-
117
+ #### Example
117
118
  ```
119
+ agtm skills rate prepare --skill_id code_success_skills --prompt "Evaluate the results" --benchmark path/customized_agent_benchmark.json
120
+ agtm skills rate apply --skill_id code_success_skills --result '{"results":[{"log_id":"3679a3fe-4d97-4eb1-83bc-f83d711be195","rating":0.90,"level":"L4"}]}'
121
+ agtm skills rate show --skill_id code_success_skills
122
+ ```
123
+ Sample output:
124
+ ```
125
+ skill_id run_times score level
126
+ ------------------- --------- ----- -----
127
+ code_success_skills 3 0.88 L4(100%)
128
+ ```
129
+ Benchmarks live in `data/config/levels/*.json` and follow this structure:
130
+ ```
131
+ {
132
+ "software-engineering": {
133
+ "Google": [
134
+ { "level": "L3", "title": "Software Engineer II", "description": "Entry-level engineer. Delivers well-scoped tasks with guidance.", "signals": ["task execution","learning velocity","code quality basics"] },
135
+ { "level": "L4", "title": "Software Engineer III", "description": "Independent contributor. Owns small features end-to-end.", "signals": ["ownership","code quality","debugging ability"] }
136
+ ]
137
+ }
138
+ }
139
+ ```
140
+ The evaluator compares each `<input,output>` log to the benchmark definitions and assigns a rating. You can customize levels such as `poor`, `fair`, `good`, `excellent` in your benchmark file.
118
141
 
119
- **4. Use your customized endpoint and schema definition**
120
-
121
- You have the flexibility to use the AI Agent marketplace/manager cli `agtm` to submit customized ai agent schema to your customized endpoint.
122
-
123
- You need to define a customized `schema.json` (https://github.com/aiagenta2z/agtm/blob/main/schema.json) file similar to the default one below and your URL of `endpoint`.
124
- Then the package will POST the the data schema to your endpoint.
125
-
126
-
127
- Note: the keys in agent.json and schema.json should match. Package will select keys from the agent.json/agent.yaml files.
142
+ Partial List of Skills and Job Level Description
128
143
 
144
+ | Job Category | Company | Levels Description (e.g. Google L3, Meta E4) |
145
+ |-------------------|---------|-------------------------------------------------------------------------------------------|
146
+ | Marketing | Apple | [marketing_sales_apple_levels.json](data/config/levels/marketing_sales_apple_levels.json) |
147
+ | Software Engineer | Google | [software_engineer_google_levels.json](data/config/levels/software_engineer_google_levels.json) |
148
+ | Software Engineer | Meta | [software_engineer_meta_levels.json](data/config/levels/software_engineer_meta_levels.json) |
129
149
 
130
- `schema.json` should have two keys defined the required fields and optional fields you want to submit from the agent.json file.
131
150
 
132
- Remember to keep the `access_key` in safe place, the post request will post the `access_key` as well as schema to the endpoint.
151
+ write your `customized_agent_benchmark.json` following the formats
133
152
 
134
- ## default schema.json definition
135
153
  ```
136
154
  {
137
- "required": [
138
- "name",
139
- "content"
140
- ],
141
- "optional": [
142
- "website",
143
- "field",
144
- "subfield",
145
- "content_tag_list",
146
- "github",
147
- "price_type",
148
- "api",
149
- "thumbnail_picture",
150
- "upload_image_files",
151
- "sdk",
152
- "package"
155
+ "domain": {
156
+ "my_benchmark": [
157
+ { "level": "poor", "description": "the skill failed or the output is meaningless"},
158
+ { "level": "fair", "description": "the skills produces fair results, complete the task"},
159
+ { "level": "good", "description": "the skills output a report, an image is good in real life standards.."},
153
160
  ]
161
+ }
154
162
  }
155
163
  ```
156
164
 
157
165
 
158
- Please visit the command line github package [agtm](https://github.com/aiagenta2z/agtm) and [DOC](https://www.deepnlp.org/doc/ai_agent_marketplace) detailed usage.
166
+ ## `Run`
159
167
 
168
+ Execution of Agent Cli with hints and auto completion.
160
169
 
161
- Use the test account and access
170
+ The `run` command executes agent workflows with interactive hints and fuzzy CLI completion. Typing a few characters surfaces suggested commands so you can finish the full invocation quickly (for example, typing `play` will suggest the Playwright runner).
162
171
 
163
- ```
164
- export AI_AGENT_MARKETPLACE_ACCESS_KEY="TEST_KEY_AI_AGENT_REGISTRY"
172
+ Let's say you want to run an agent command of Playwright to go to a URL and fetch a webpage. You don't need to remember the full command—type `play`, pick the provider, then pick the CLI action.
165
173
 
166
- agtm upload --config ./agent.json --endpoint https://www.deepnlp.org/api/ai_agent_marketplace/registry --schema ./schema.json
174
+ ### Usage
167
175
 
168
- agtm upload --config ./agent.json --endpoint https://www.aiagenta2z.com/api/ai_agent_marketplace/registry --schema ./schema.json
176
+ ```
177
+ agtm run <provider_unique_id> <agent_cli>
169
178
  ```
170
179
 
180
+ ### Example
171
181
 
172
- ```
173
- Setting Registry Endpoint to URL: https://www.deepnlp.org/api/ai_agent_marketplace/registry
174
- Customized Schema is enabled : ./schema.json
175
- Attempting to register agent from config file: ./agent.json
176
- ✅ Loaded custom schema from: ./schema.json
177
- Using customized schema {"required": ["name", "content"], "optional": ["website", "field", "subfield", "content_tag_list", "github", "price_type", "api", "thumbnail_picture", "upload_image_files", "sdk", "package"]}
178
- WARN: Calling AddServiceAPI input param optional keys filled fields ['website', 'field', 'subfield', 'content_tag_list', 'github', 'price_type', 'api', 'thumbnail_picture', 'upload_image_files']|missing_fields []
179
- Submitting agent information to the marketplace...
182
+ ```shell
183
+ rockingdingo@rockingdingodeMacBook-Pro skills_cli % agtm run play
184
+ DEBUG: Entering Human Mode | idArg play | commandArgs | options [object Object] | hasHints true | hints [object Object]
180
185
 
181
- Registration Successful!
182
- URL: https://www.deepnlp.org/store/ai-agent/coding-agent/pub-test-agtm-registry/my-first-ai-coding-agent
183
- Message: Content Updated Successfully|Visit URL at https://www.deepnlp.org/store/ai-agent/coding-agent/pub-test-agtm-registry/my-first-ai-coding-agent and Login to View the Pending status webpage...
184
- Track its status at: https://www.deepnlp.org/store/ai-agent/coding-agent/pub-test-agtm-registry/my-first-ai-coding-agent
186
+ Skill ID suggestions:
187
+ 1. microsoft/playwright-cli
188
+ 2. googleworkspace/cli
189
+ Skill ID suggestions: 1
190
+ Command hints:
191
+ 1. playwright-cli goto <url> # navigate to a url
192
+ 2. playwright-cli open [url] # open browser, optionally navigate to url
193
+
194
+ Select command (number or input custom): 1
195
+ Final command [playwright-cli goto <url>]: playwright-cli goto https://www.github.com
196
+ agtm run microsoft/playwright-cli playwright-cli goto https://www.github.com
185
197
  ```
186
198
 
199
+ Support CLI List, Please welcome to contrib
200
+
201
+ | unique_id | agent cli |
202
+ | --- | --- |
203
+ | microsoft/playwright-cli | playwright-cli open [url], playwright-cli goto <url>
204
+ | googleworkspace/cli | gws drive files list --params
205
+ | aiagenta2z/onekey-gateway | onekey agent <unique_id> <api_id> <data_json|@file>, onekey mcp <server_name> [--name config_name], onekey llm --provider <provider> --model <model> --messages <json|@file> [--temperature <num>] [--response-format <format>] [--options <json|@file>], onekey llm --payload <json|@file>
206
+ | openai/codex-cli | codex, codex exec "[instruction]"
207
+ | anthropic/claude-code | claude "[prompt]", claude --dangerously-skip-permissions
208
+ | paul-gauthier/aider | aider --model [model_name], /test [command]
209
+ | openinterpreter/open-interpreter | interpreter, interpreter --os
210
+ | google-gemini/gemini-cli | gemini, gemini -p "[prompt] @[file/dir]", gemini --yolo, /memory add "[fact]", /mcp list, /restore
187
211
 
188
- Use www.example.com as endpoint example
189
212
 
213
+ ## AI Agent Registry
214
+ ### `search`
215
+ `agtm search` helps to search AI Agent MCP and skills marketplace by id or query keywords.
190
216
 
217
+ Example Usage
218
+ ```shell
219
+ agtm search --q 'coding agent'
220
+ agtm search --id 'google-maps/google-maps'
191
221
  ```
192
- agtm upload --config ./agent.json --endpoint https://www.example.com --schema ./schema.json
193
222
 
223
+ ### `upload`
224
+ `agtm update` helps to update your local agent.json or agent.yaml meta information to DeepNLP AI Agent Marketplace Index.
225
+ Example Usage
226
+ ```shell
227
+ agtm upload --github https://github.com/AI-Hub-Admin/My-First-AI-Coding-Agent
228
+ agtm upload --config ./agent.json
229
+ agtm upload --config ./agent.yaml
194
230
  ```
195
231
 
196
- It will return an error message showing the endpoint and data, https://www.example.com doesn't have endpoint handling
232
+ `schema.json` should have two keys defined the required fields and optional fields you want to submit from the agent.json file.
197
233
 
198
- ```
199
- ❌ Registration Failed. Please check your endpoint https://www.example.com and agent data {'name': 'My First AI Coding Agent', 'content': 'This AI Agent can do complicated programming work for humans', 'website': 'https://www.my_first_agent.com', 'field': 'AI AGENT', 'subfield': 'Coding Agent', 'content_tag_list': 'coding,python', 'github': '', 'thumbnail_picture': 'https://avatars.githubusercontent.com/u/242328252?s=200&v=4', 'upload_image_files': '', 'api': 'https://www.my_first_agent.com/agent', 'price_type': 'FREE', 'price_per_call_credit': 0.0, 'price_fixed_credit': 0.0, 'price_subscription': 'Basic: your basic plan introduction, Advanced: Your Advanced Plan introduction, etc.'}
200
- ```
234
+ Remember to keep the `access_key` in safe place, the post request will post the `access_key` as well as schema to the endpoint.
235
+
236
+ Please visit the command line github package [agtm](https://github.com/aiagenta2z/agtm) and [DOC](https://www.deepnlp.org/doc/ai_agent_marketplace) detailed usage.
201
237
 
202
238
 
203
- **5. Search AI Agent Marketplace**
239
+ Use the test account and access
204
240
 
205
241
  ```
242
+ export AI_AGENT_MARKETPLACE_ACCESS_KEY="TEST_KEY_AI_AGENT_REGISTRY"
206
243
 
207
- ## Search Open Source AI Agent marketplace of deepnlp
244
+ agtm upload --config ./agent.json --endpoint https://www.deepnlp.org/api/ai_agent_marketplace/registry --schema ./schema.json
208
245
 
209
- agtm search --q 'coding agent'
210
- agtm search --id 'google-maps/google-maps'
211
- agtm search --id 'AI-Hub-Admin/My-First-AI-Coding-Agent'
246
+ agtm upload --config ./agent.json --endpoint https://www.aiagenta2z.com/api/ai_agent_marketplace/registry --schema ./schema.json
212
247
  ```
213
248
 
214
- Search Result of query q="coding agent"
249
+ ### Contributing
215
250
 
216
- ```
217
- [{'content_name': 'Cursor AI', 'publisher_id': 'pub-cursor', 'detail_url': 'https://www.deepnlp.org/store/ai-agent/coding-agent/pub-cursor/cursor-ai', 'website': 'https://docs.cursor.com/agent', 'github': '', 'review_cnt': '3', 'rating': '3.3', 'description': 'Cursor AI Coding Editor provides Agent mode, which is the default mode in Cursor, equipped with all tools to efficiently handle a wide range of coding tasks. Agent is the default mode in Cursor that is best for most tasks. It has all tools enabled to allow it to perform all operations necessary to complete the task at hand. Make sure to read chat overview to learn more about how modes work in Curs', 'subfield': 'Coding Agent', 'field': 'AI AGENT', 'id': 'cursor/cursor-ai', 'content_tag_list': 'Coding Agent,AI AGENT', 'thumbnail_picture': 'https://static.aiagenta2z.com/scripts/img/ai_service_content/a7dd95e7eb419437ef4a91f4b0e853cb.jpg'}, {'content_name': 'trae ai', 'publisher_id': 'pub-trae-ai', 'detail_url': 'https://www.deepnlp.org/store/ai-agent/coding-agent/pub-trae-ai/trae-ai', 'website': 'https://www.trae.ai/', 'github': '', 'review_cnt': '2', 'rating': '4.0', 'description': 'Trae AI IDE is a cutting-edge AI-integrated development environment designed to enhance developer productivity by leveraging advanced AI models like Claude3.5 and GPT-4o. It offers a seamless coding experience with features such as intelligent code generation, real-time feedback, and multi-modal input support, making it a powerful tool for developers. Introduction Trae AI IDE, developed by ByteDan', 'subfield': 'Coding Agent', 'field': 'AI AGENT', 'id': 'trae-ai/trae-ai', 'content_tag_list': 'CODING AGENT,AI AGENT', 'thumbnail_picture': 'https://static.aiagenta2z.com/scripts/img/ai_service_content/cc43d2dc25488b50b883781e0ae8c988.png'}, {'content_name': 'codex', 'publisher_id': 'pub-openai', 'detail_url': 'https://www.deepnlp.org/store/ai-agent/coding-agent/pub-openai/codex', 'website': 'https://github.com/openai/codex', 'github': 'https://github.com/openai/codex', 'review_cnt': '1', 'rating': '5.0', 'description': 'npm i -g @openai/codexor brew install --cask codex\n\nCodex CLI is a coding agent from OpenAI that runs locally on your computer.\n\nIf you want Codex in your code editor (VS Code, Cursor, Windsurf), install in your IDE\nIf you are looking for the cloud-based agent from OpenAI, Codex Web, go to chatgpt.com/codex\n\n\n \n \n\n---\n\n## Quickstart\n\n### Installing and running Codex CLI\n\nInstall globally with yo', 'subfield': 'CODING AGENT', 'field': 'AI AGENT', 'id': 'openai/codex', 'content_tag_list': 'GitHub 48.6k', 'thumbnail_picture': 'https://avatars.githubusercontent.com/u/14957082?v=4'}, {'content_name': 'fine dev', 'publisher_id': 'pub-fine-dev', 'detail_url': 'https://www.deepnlp.org/store/ai-agent/ai-agent/pub-fine-dev/fine-dev', 'website': 'https://www.fine.dev', 'github': '', 'review_cnt': '1', 'rating': '4.0', 'description': 'Full-Stack AI Developer Agent for Startups Accelerate your startup’s release schedule and ship daily improvements. Fine is the AI Coding Agent built to act like another team member, getting work done. Try free or watch it work.', 'subfield': 'AI AGENT', 'field': 'AI AGENT', 'id': 'fine-dev/fine-dev', 'content_tag_list': ',AI AGENT', 'thumbnail_picture': 'https://www.fine.dev/_next/static/media/logo.76f79362.svg'}, {'content_name': 'claude code', 'publisher_id': 'pub-claude-code', 'detail_url': 'https://www.deepnlp.org/store/ai-agent/coding-agent/pub-claude-code/claude-code', 'website': 'https://www.anthropic.com/claude-code', 'github': '', 'review_cnt': '1', 'rating': '5.0', 'description': 'Claude Code by Anthropic is an AI-powered coding assistant designed to enhance developer productivity by providing intelligent code generation, debugging, and optimization capabilities. It integrates seamlessly with various developer tools, making it easy to use within existing workflows. Introduction Claude Code is a powerful AI coding assistant developed by Anthropic, aimed at helping developers', 'subfield': 'Coding Agent', 'field': 'AI AGENT', 'id': 'claude-code/claude-code', 'content_tag_list': 'CODING AGENT,AI AGENT', 'thumbnail_picture': 'https://static.aiagenta2z.com/scripts/img/ai_service_content/7d6c735321396b42b5c2e46499e17a6e.png'}, {'content_name': 'qwen code', 'publisher_id': 'pub-qwen-code', 'detail_url': 'https://www.deepnlp.org/store/ai-agent/coding-agent/pub-qwen-code/qwen-code', 'website': '', 'github': '', 'review_cnt': '1', 'rating': '4.0', 'description': 'Qwen Coding Agent offers an advanced framework for developing applications utilizing large language models (LLMs), enhancing capabilities such as instruction following, tool usage, planning, and memory. Introduction Qwen Coding Agent provides a robust platform for building LLM applications, leveraging the advanced features of Qwen models (version 2.0 and above). It facilitates the development of i', 'subfield': 'Coding Agent', 'field': 'AI AGENT', 'id': 'qwen-code/qwen-code', 'content_tag_list': ',AI AGENT', 'thumbnail_picture': 'https://camo.githubusercontent.com/db544c14e8419ecf289564a79841e005c518fc29cd418ac4a31215e9377eaa22/68747470733a2f2f7169616e77656e2d7265732e6f73732d636e2d6265696a696e672e616c6979756e63732e636f6d2f5177656e322e352f5177656e322e352d436f6465722f7177656e322e352d636f6465722d6c6f676f'}, {'content_name': 'Qoder', 'publisher_id': 'pub-qoder', 'detail_url': 'https://www.deepnlp.org/store/ai-agent/coding-agent/pub-qoder/qoder', 'website': 'https://qoder.com/download', 'github': '', 'review_cnt': '1', 'rating': '5.0', 'description': '\r\n## Qoder\r\n\r\nQoder is an agentic coding platform designed for real software development. It seamlessly integrates enhanced context engineering with intelligent agents to gain a comprehensive understanding of your codebase and systematically tackles software development tasks.\r\nIt goes beyond simple code completion-Qoder helps you think deeper, code smarter, and build better by automating intricat', 'subfield': 'Coding Agent', 'field': 'AI AGENT', 'id': 'qoder/qoder', 'content_tag_list': 'coding,agent', 'thumbnail_picture': 'https://static.aiagenta2z.com/scripts/img/ai_service_content/6d7c68c43f520b76251fe2ac7c0061a8.jpg'}, {'content_name': 'CodeBuddy IDE Tencent', 'publisher_id': 'pub-tencent', 'detail_url': 'https://www.deepnlp.org/store/ai-agent/coding-agent/pub-tencent/codebuddy-ide-tencent', 'website': 'https://copilot.tencent.com/ide', 'github': '', 'review_cnt': '1', 'rating': '4.0', 'description': '\r\nCodeBuddy IDE Tencent AI 一站式工作台:从此用自然语言实现产品、设计、研发全流程\r\n\r\n\r\n\r\n## AI 智能代码补全\r\n所想即所码\r\nAI驱动的实时代码预测与智能补全,让编程如行云流水\r\n\r\n\r\n## AI 设计生成\r\n草图秒变原型\r\n手绘概念瞬间转化为高保真交互原型,创意无需等待\r\n\r\n## 设计稿转代码\r\n一稿生万码\r\nFigma设计 稿一键转换为生产级代码,还原度高达99.9%\r\n\r\n\r\n## AI 全栈开发\r\n你的AI编程搭档\r\n智能开发代理,自主完成多文件代码生成与重构\r\n\r\n\r\n## 内置后端服务\r\n后端开 发零门槛\r\n内置腾讯云 CloudBase 和 Supabase服务,数据库与用户认证一键搞定\r\n\r\n## 一键部署分享\r\n开发、部署、分享,一键搞定\r\n内置 Cloud Studio,EdgeOne Pages,从开发环境到在线演示,只需一秒钟', 'subfield': 'Coding Agent', 'field': 'AI AGENT', 'id': 'tencent/codebuddy-ide-tencent', 'content_tag_list': 'ide,coding agent', 'thumbnail_picture': 'https://static.aiagenta2z.com/scripts/img/ai_service_content/3ef7d0e02ecbf36eb9dbd25590c7c87e.jpg'}, {'content_name': 'zencoder ai', 'publisher_id': 'pub-zencoder-ai', 'detail_url': 'https://www.deepnlp.org/store/ai-agent/coding-agent/pub-zencoder-ai/zencoder-ai', 'website': 'https://zencoder.ai', 'github': '', 'review_cnt': '0', 'rating': '0.0', 'description': "Zencoder AI provides a range of AI agents designed to streamline and enhance various business processes through intelligent automation and advanced AI capabilities. Introduction Zencoder AI's AI agents are built to act as digital assistants, automating complex tasks and improving operational efficiency across multiple industries. These agents leverage cutting-edge AI technologies to handle tasks s", 'subfield': 'Coding Agent', 'field': 'AI AGENT', 'id': 'zencoder-ai/zencoder-ai', 'content_tag_list': ',AI AGENT', 'thumbnail_picture': 'https://zencoder.ai/favicon.ico'}, {'content_name': 'gpt-engineer', 'publisher_id': 'pub-antonosika', 'detail_url': 'https://www.deepnlp.org/store/ai-agent/ai-agent/pub-antonosika/gpt-engineer', 'website': 'https://github.com/AntonOsika/gpt-engineer', 'github': 'https://github.com/AntonOsika/gpt-engineer', 'review_cnt': '0', 'rating': '0.0', 'description': '# gpt-engineer\n\n](https://github.com/gpt-engineer-org/gpt-engineer)\n](https://discord.gg/8tcDQ89Ej2)\n](https://github.com/gpt-engineer-org/gpt-engineer/blob/main/LICENSE)\n](https://github.com/gpt-engineer-org/gpt-engineer/issues)\n\n](https://twitter.com/antonosika)\n\nThe OG code genereation experimentation platform!\n\nIf you are looking for the evolution that is an opinionated, managed service – chec', 'subfield': 'AI AGENT', 'field': 'AI AGENT', 'id': 'antonosika/gpt-engineer', 'content_tag_list': 'GitHub 55.0k,ai,autonomous-agent,code-generation,codebase-generation,codegen,coding-assistant,gpt-4,gpt-engineer,openai,python', 'thumbnail_picture': 'https://avatars.githubusercontent.com/u/4467025?v=4'}]
218
- ```
251
+ #### Agent CLI List
252
+ You are welcome to contrib your cli list to the agent cli hints json file to folder [hints](data/config/hints) or table README.md
219
253
 
220
- Search Result of Retrieving registered project id 'AI-Hub-Admin/My-First-AI-Coding-Agent'
254
+ #### Skill Run Benchmark
255
+
256
+ You are welcome to contrib your own customized benchmarks of skills and unique levels system in folder [levels](data/config/levels).
221
257
 
222
- ```
223
- Retrieving specific agent with unique ID: AI-Hub-Admin/My-First-AI-Coding-Agent
224
258
 
225
- {'total_hits': 1, 'id': 'AI-Hub-Admin/My-First-AI-Coding-Agent', 'items': [{'content_name': 'My-First-AI-Coding-Agent', 'publisher_id': 'pub-ai-hub-admin', 'detail_url': 'https://www.deepnlp.org/store/ai-agent/ai-agent/pub-ai-hub-admin/my-first-ai-coding-agent', 'website': 'https://github.com/AI-Hub-Admin/My-First-AI-Coding-Agent', 'github': 'https://github.com/AI-Hub-Admin/My-First-AI-Coding-Agent', 'review_cnt': '0', 'rating': '0.0', 'description': '# My-First-AI-Coding-Agent\nAI Agent Registry Demo project\n\n', 'subfield': 'AI AGENT', 'field': 'AI AGENT', 'id': 'ai-hub-admin/my-first-ai-coding-agent', 'content_tag_list': 'GitHub 0', 'thumbnail_picture': 'https://avatars.githubusercontent.com/u/184629057?v=4'}]}
226
- ```
227
259
 
package/agent.json CHANGED
@@ -13,5 +13,4 @@
13
13
  "price_per_call_credit": 0.0,
14
14
  "price_fixed_credit" : 0.0,
15
15
  "price_subscription": "Basic: your basic plan introduction, Advanced: Your Advanced Plan introduction, etc.",
16
- "new_key_1": "new_value_1"
17
16
  }
@@ -0,0 +1,118 @@
1
+ {
2
+ "microsoft/playwright-cli": {
3
+ "hints": [
4
+ {
5
+ "cli": "playwright-cli open [url]",
6
+ "hint": "open browser, optionally navigate to url"
7
+ },
8
+ {
9
+ "cli": "playwright-cli goto <url> ",
10
+ "hint": "navigate to a url"
11
+ }
12
+ ]
13
+ },
14
+ "googleworkspace/cli": {
15
+ "hints": [
16
+ {
17
+ "cli": "gws drive files list --params",
18
+ "hint": "List the 10 most recent files"
19
+ }
20
+ ]
21
+ },
22
+ "aiagenta2z/onekey-gateway": {
23
+ "hints": [
24
+ {
25
+ "cli": "onekey agent <unique_id> <api_id> <data_json|@file>",
26
+ "hint": "Invoke a specific agent by ID with structured JSON data or a file input"
27
+ },
28
+ {
29
+ "cli": "onekey mcp <server_name> [--name config_name]",
30
+ "hint": "Connect to a Model Context Protocol server to extend agent capabilities"
31
+ },
32
+ {
33
+ "cli": "onekey llm --provider <provider> --model <model> --messages <json|@file> [--temperature <num>] [--response-format <format>] [--options <json|@file>]",
34
+ "hint": "Execute a direct LLM call with granular control over provider, model, and sampling parameters"
35
+ },
36
+ {
37
+ "cli": "onekey llm --payload <json|@file>",
38
+ "hint": "Run a raw LLM request using a pre-formatted JSON payload or configuration file"
39
+ }
40
+ ]
41
+ },
42
+ "openai/codex-cli": {
43
+ "hints": [
44
+ {
45
+ "cli": "codex",
46
+ "hint": "Start an interactive terminal UI (TUI) coding session"
47
+ },
48
+ {
49
+ "cli": "codex exec \"[instruction]\"",
50
+ "hint": "Run Codex non-interactively and stream results to stdout"
51
+ }
52
+ ]
53
+ },
54
+ "anthropic/claude-code": {
55
+ "hints": [
56
+ {
57
+ "cli": "claude \"[prompt]\"",
58
+ "hint": "Start an interactive session with an initial task"
59
+ },
60
+ {
61
+ "cli": "claude --dangerously-skip-permissions",
62
+ "hint": "Run without interrupting for tool execution permissions"
63
+ }
64
+ ]
65
+ },
66
+ "paul-gauthier/aider": {
67
+ "hints": [
68
+ {
69
+ "cli": "aider --model [model_name]",
70
+ "hint": "Start aider with a specific LLM context"
71
+ },
72
+ {
73
+ "cli": "/test [command]",
74
+ "hint": "Run a test; aider will automatically attempt to fix code if it fails"
75
+ }
76
+ ]
77
+ },
78
+ "openinterpreter/open-interpreter": {
79
+ "hints": [
80
+ {
81
+ "cli": "interpreter",
82
+ "hint": "Launch the natural language interface to control your local computer"
83
+ },
84
+ {
85
+ "cli": "interpreter --os",
86
+ "hint": "Enable visual/OS-level control for mouse and keyboard automation"
87
+ }
88
+ ]
89
+ },
90
+ "google-gemini/gemini-cli": {
91
+ "hints": [
92
+ {
93
+ "cli": "gemini",
94
+ "hint": "Start an interactive agentic session in the current directory"
95
+ },
96
+ {
97
+ "cli": "gemini -p \"[prompt] @[file/dir]\"",
98
+ "hint": "Run a prompt with specific file or directory context injected"
99
+ },
100
+ {
101
+ "cli": "gemini --yolo",
102
+ "hint": "Enable 'YOLO mode' to auto-approve all tool and shell executions"
103
+ },
104
+ {
105
+ "cli": "/memory add \"[fact]\"",
106
+ "hint": "Save a persistent fact to the project's GEMINI.md hierarchical memory"
107
+ },
108
+ {
109
+ "cli": "/mcp list",
110
+ "hint": "List all active Model Context Protocol servers and available tools"
111
+ },
112
+ {
113
+ "cli": "/restore",
114
+ "hint": "List or restore project state checkpoints created before file edits"
115
+ }
116
+ ]
117
+ }
118
+ }
File without changes
@@ -0,0 +1,83 @@
1
+ {
2
+ "marketing-and-sales": {
3
+ "Apple": [
4
+ {
5
+ "level": "M1",
6
+ "title": "Marketing / Sales Associate",
7
+ "description": "Entry-level contributor supporting campaigns, retail operations, or sales initiatives. Executes well-defined tasks under guidance.",
8
+ "signals": [
9
+ "task execution",
10
+ "attention to detail",
11
+ "basic customer interaction",
12
+ "learning speed"
13
+ ]
14
+ },
15
+ {
16
+ "level": "M2",
17
+ "title": "Marketing / Sales Specialist",
18
+ "description": "Independently executes campaigns or sales processes. Contributes to customer engagement and supports revenue goals.",
19
+ "signals": [
20
+ "execution quality",
21
+ "customer engagement",
22
+ "ownership of small initiatives",
23
+ "data awareness"
24
+ ]
25
+ },
26
+ {
27
+ "level": "M3",
28
+ "title": "Senior Specialist",
29
+ "description": "Owns key campaigns, product messaging, or regional sales performance. Drives measurable business impact.",
30
+ "signals": [
31
+ "campaign ownership",
32
+ "revenue contribution",
33
+ "cross-functional collaboration",
34
+ "analytics usage"
35
+ ]
36
+ },
37
+ {
38
+ "level": "M4",
39
+ "title": "Manager",
40
+ "description": "Leads teams or major initiatives. Defines strategy for campaigns or sales programs and ensures execution excellence.",
41
+ "signals": [
42
+ "team leadership",
43
+ "strategic planning",
44
+ "execution consistency",
45
+ "performance management"
46
+ ]
47
+ },
48
+ {
49
+ "level": "M5",
50
+ "title": "Senior Manager",
51
+ "description": "Drives large-scale marketing or sales programs across regions or product lines. Aligns execution with business goals.",
52
+ "signals": [
53
+ "program leadership",
54
+ "cross-region coordination",
55
+ "scaling execution",
56
+ "business alignment"
57
+ ]
58
+ },
59
+ {
60
+ "level": "M6",
61
+ "title": "Director",
62
+ "description": "Defines organizational strategy for marketing or sales. Oversees multiple teams and drives significant business outcomes.",
63
+ "signals": [
64
+ "organizational impact",
65
+ "strategy ownership",
66
+ "multi-team leadership",
67
+ "market positioning"
68
+ ]
69
+ },
70
+ {
71
+ "level": "M7",
72
+ "title": "Senior Director / VP",
73
+ "description": "Sets long-term vision and direction for major business units. Influences company-wide marketing or sales strategy.",
74
+ "signals": [
75
+ "company-level influence",
76
+ "vision setting",
77
+ "brand leadership",
78
+ "market expansion"
79
+ ]
80
+ }
81
+ ]
82
+ }
83
+ }