SmartAgents 1.0.2

.NET 8.0 This package targets .NET 8.0. The package is compatible with this framework or higher. 
dotnet tool install --global SmartAgents --version 1.0.2
This package contains a .NET tool you can call from the shell/command line. 
dotnet new tool-manifest
                    


                            if you are setting up this repo
                        

                    

                
dotnet tool install --local SmartAgents --version 1.0.2
This package contains a .NET tool you can call from the shell/command line. 
#tool dotnet:?package=SmartAgents&version=1.0.2
                    


                    

                
nuke :add-package SmartAgents --version 1.0.2

settings

You need to have appsettings.json file, it is similar to this:

{
  "Log": {
    "Enabled": true
  },
  "llm": {
    "model_text": "openAI",
    "model_image": "gemini",
    "model_embedding": "gemini",
    "RPM": 10,
    "TPM": 900000
  },
  "gemini": {
    "key": "A..................................eM",
    "model_text": "gemini-2.5-flash",
    "model_image": "gemini-2.0-flash-exp-image-generation",
    "model_embedding": "gemini-embedding-exp-03-07"
  },
  "openAI": {
    "key": "5S............................................................................SB",
    "serviceURL": "https://admin-12312-eastus2.openai.azure.com",
    "model_text": "gpt-4.1",
    "model_text_version": "2025-01-01-preview",
    "model_embedding": "text-embedding-3-large",
    "model_embedding_version": "2024-02-15-preview"
  },
  "ollama": {
    "url": "http://localhost:11434/api/generate",
    "model_text": "deepseek-r1:1.5b"
  },
  "ocr": {
    "path": "C:\\Program Files\\Tesseract-OCR\\tessdata",
    "lang": "eng"
  },
  "vectorDb": {
    "provider": "pinecone"
  },
  "pinecone": {
    "key": "pcsk..................................................................K"
  },
  "googleSearch" : {
    "key": "A..................................M",
    "searchEnginId" : "e................7"
  }
}

notes:

  • the most important section is llm, you can choose between (openAI, gemini, ollama)
  • you need to have valid keys for the model you would like to use

run

You can run the project using the following command:

smartagents -root .

you can also use some args:

-agent : this is to specify the agent you want to use, if not specified, it will list all agents -path : this is to specify the path to agents vault, if not specified, it will use the current directory -id : this is to specify the id of your current request, if not specified, it will generate a new one

Agent example

in your agent vault, you can create folders, if the folder contains file called (init.md) then the folder will be considered an agent

this is example of simple agent:

init.md

- output: "hello world"
- output: "what is your name?"
- input: {{name}}
- output: "you are welcomed:"
- output: {{name}}

Command Summary Cheat Sheet

Statement Description Example
set Assign value to variable set: "value" in {{var}}
append Append value to variable (concatenate) append: {{add}} in {{base}}
file append Append text to a file file append: {{data}} in "out.log"
for each Loop over newline/JSON array string for each: {{item}} in {{list}}
if Conditional execution (string equals/not equals) if: {{status}} = "done"
break Exit current loop or script break
remark Add a comment line remark: Initialization phase
ocr Extract text from image ocr: [[img.png]] in {{text}} by eng
pdf Extract text content from PDF file pdf: [[doc.pdf]] in {{pdfText}}
download text Get simplified text content from URL download text: "url" in {{content}}
json to csv Convert JSON array string to CSV string json to csv: {{jsonVar}} in {{csvVar}}
csv to json Convert CSV string to JSON array string csv to json: {{csvVar}} in {{jsonVar}}
run terminal Execute shell commands from file run terminal: [[cmd.sh]] in {{output}}
run curl Execute cURL command from file run curl: [[request.curl]] in {{response}}
run template Process file, substitute variables, store result run template: [[msg.txt]] in {{message}}
run text prompt Send text prompt to LLM run text prompt: [[query.txt]] in {{llmOut}}
run image prompt Send image generation prompt to LLM run image prompt: [[desc.txt]] in {{imgFile}}
run action Execute another CSL script file run action: [[sub-routine]]
delay Pause execution for N seconds delay: 3
{{variable}} Variable substitution file append: "User: {{name}}" in "log"
[[filename]] File reference for commands ocr: [[input.jpg]] in {{text}} by eng
"static string" Literal string value set: "completed" in {{status}}
{{HasError}} Global flag set on curl/terminal failure if: {{HasError}} = true
{{ItemIndex}} Zero-based index within for each loop remark: Processing index {{ItemIndex}}
emit Notify host application of an event with parameters emit: EventName {{var1}} {{var2}} {{var-n}}
Product Compatible and additional computed target framework versions.
.NET net8.0 is compatible.  net8.0-android was computed.  net8.0-browser was computed.  net8.0-ios was computed.  net8.0-maccatalyst was computed.  net8.0-macos was computed.  net8.0-tvos was computed.  net8.0-windows was computed.  net9.0 was computed.  net9.0-android was computed.  net9.0-browser was computed.  net9.0-ios was computed.  net9.0-maccatalyst was computed.  net9.0-macos was computed.  net9.0-tvos was computed.  net9.0-windows was computed.  net10.0 was computed.  net10.0-android was computed.  net10.0-browser was computed.  net10.0-ios was computed.  net10.0-maccatalyst was computed.  net10.0-macos was computed.  net10.0-tvos was computed.  net10.0-windows was computed. 
Compatible target framework(s)
Included target framework(s) (in package)
Learn more about Target Frameworks and .NET Standard.

This package has no dependencies.

Version Downloads Last Updated
1.0.2 157 10/11/2025
1.0.0 164 8/1/2025