AgentMake AI

AgentMake AI: an agent developement kit (ADK) for developing agentic AI applications that support 18 AI backends and work with 7 agentic components, such as tools and agents. (Developer: Eliran Wong)

Supported backends: anthropic, azure_anthropic, azure_openai, azure_sdk, cohere, custom, deepseek, genai, github, googleai, groq, llamacpp, mistral, ollama, openai, vertexai, xai

Audio Introduction

9-min introduction 24-min introduction

Latest projects

The following two projects are in active development. Both are powered by AgentMake AI and AgentMake AI MCP Servers:

ComputeMate AI

BibleMate AI

Sibling Projects

This SDK incorporates the best aspects of our favorite projects, LetMeDoIt AI, Toolmate AI and TeamGen AI, to create a library aimed at further advancing the development of agentic AI applications.

The agentmake ecosystem is further extended by two companion projects:

WebUI - agentmakestudio

MCP Servers - agentmakemcp

Supported Platforms

Windows, macOS, Linux, ChromeOS, Android via Termux Terminal and Pixel Terminal

Supported backends

anthropic - Anthropic API [docs]

azure_anthropic - Claude models via Azure Service API [docs]

azure_cohere - Cohere models via Azure Service API [docs]

azure_deepseek - DeepSeek models via Azure Service API [docs]

azure_mistral - Mistral models via Azure Service API [docs]

azure_openai - OpenAI models via Azure Service API [docs]

azure_xai - Grok models viaAzure Service API [docs]

azure_sdk - Other models via Azure AI Inference API [docs]

cohere - Cohere API [docs]

custom - any openai-compatible backends that support function calling

custom1 - any openai-compatible backends that support function calling

custom2 - any openai-compatible backends that support function calling

deepseek - DeepSeek API [docs]

genai - Vertex AI or Google AI [docs]

github - Azure OpenAI Service via Github Token [docs]

github_any - Azure AI Inference via Github Token [docs]

googleai - Google AI [docs]

groq - Groq Cloud API [docs]

llamacpp - Llama.cpp Server [docs] - local setup required

mistral - Mistral API [docs]

ollama - Ollama [docs] - local setup required

ollamacloud - Ollama [docs]

openai - OpenAI API [docs]

vertexai - Vertex AI [docs]

xai - XAI API [docs]

For simplicity, agentmake uses ollama as the default backend, if parameter backend is not specified. Ollama models are automatically downloaded if they have not already been downloaded. Users can change the default backend by modifying environment variable DEFAULT_AI_BACKEND.

Setup Examples

https://github.com/eliranwong/agentmake/tree/main/docs

Introducing Agentic Components

agentmake is designed to work with seven kinds of components for building agentic applications:

1. system - System messages are crucial for defining the roles of the AI agents and guiding how AI agents interact with users. Check out our examples. agentmake supports the use of fabric patterns as system components for running agentmake function or CLI options READ HERE.

2. instruction - Predefined instructions that are added to users' prompts as prefixes, before they are passed to the AI models. Check out our examples. agentmake supports the use of fabric patterns as instruction components for running agentmake function or CLI options READ HERE.

3. input_content_plugin - Input content plugins process or transform user inputs before they are passed to the AI models. Check out our examples.

4. output_content_plugin - Output content plugins process or transform assistant responses after they are generated by AI models. Check out our examples.

5. tool - Tools take simple structured actions in response to users' requests, with the use of schema and function calling. Check out our examples.

6. agent - Agents are agentic applications automate multiple-step actions or decisions, to fulfill complicated requests. They can be executed on their own or integrated into an agentic workflow, supported by agentmake, to work collaboratively with other agents or components. Check out our examples.

7. follow_up_prompt - Predefined prompts that are helpful for automating a series of follow-up responses after the first assistant response is generated. Check out our examples.

Built-in and Custom Agentic Components

agentmake supports both built-in agentic components, created by our developers or contributors, and cutoms agentic components, created by users to meet their own needs.

Built-in Agentic Components

Built-in agents components are placed into the following six folders inside the agentmake folders:

agents, instructions, plugins, prompts, systems, tools

To use the built-in components, you only need to specify the component filenames, without parent paths or file extensions, when you run the agentmake signature function or CLI options.

Custom Agentic Components

agentmake offers two options for users to use their custom components.

Option 1: Specify the full file path of inidividual components

Given the fact that each component can be organised as a single file, to use their own custom components, users only need to specify the file paths of the components they want to use, when they run the agentmake signature function or CLI options.

Option 2: Place custom components into agentmake user directory

The default agentmake user directory is ~/agentmake, i.e. a folder named agentmake, created under user's home directory. Uses may define their own path by modifying the environment variable AGENTMAKE_USER_DIR.

After creating a folder named agentmake under user directory, create six sub-folders in it, according to the following names and place your custom components in relevant folders, as we do with our built-in components.

If you organize the custom agentic components in this way, you only need to specify the component filenames, without parent paths or file extensions, when you run the agentmake signature function or CLI options.

Priorities

In cases where a built-in tool and a custom tool have the same name, the custom tool takes priority over the built-in one. This allows for flexibility, enabling users to copy a built-in tool, modify its content, and retain the same name, thereby effectively overriding the built-in tool.

Agentic Application that Built on AgentMake AI

Below are a few examples to illustrate how easy to build agentic applications with AgentMake AI.

Example 1 - ToolMate AI

ToolMate AI version 2.0 is completely built on AgentMake AI, based on the following two agentic workflows, to reolve both complex and simple tasks.

To resolve complex tasks:

<img width="794" alt="Image" src="