Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
A simple agent framework that's capable of browser use + mcp + auto instrument + plan + deep research + more
| Date | Stars |
|---|---|
| 2026-07-31 | 395 |
| 2026-08-05 | 395 |
| 2026-08-06 | 395 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
[](https://mseep.ai/app/femto-minion-agent) **[](https://github.com/femto/minion-agent) [](https://github.com/femto/minion-agent) [](https://discord.gg/HUC6xEK9aT) [](https://x.com/femtowin)** [](https://deepwiki.com/femto/minion-agent) # Minion Agent A powerful agent framework with enhanced capabilities including browser automation, code execution, MCP tool support, and deep research. **Now defaults to EXTERNAL_MINION_AGENT framework** for superior performance and functionality. ## 🎬 Demo Videos - [Compare Price Demo](https://youtu.be/O0RhA3eeDlg) - [Deep Research Demo](https://youtu.be/tOd56nagsT4) - [Generating Snake Game Demo](https://youtu.be/UBquRXD9ZJc) ## Quick Start Minion Agent now defaults to the powerful `EXTERNAL_MINION_AGENT` framework, providing enhanced code execution, browser automation, and advanced planning capabilities out of the box. ## Installation ```bash pip install minion-agent-x ``` ## Or from source ```bash git clone [email protected]:femto/minion-agent.git cd minion-agent pip install -e . ``` ## Usage Here's a simple example of how to use Minion Agent: ```python import asyncio import os from dotenv import load_dotenv from minion_agent import MinionAgent, AgentConfig, AgentFramework from minion.agents import CodeAgent import minion_agent load_dotenv() async def main(): # Configure the agent (using EXTERNAL_MINION_AGENT as default) agent_config = AgentConfig( model_id=os.environ.get("AZURE_DEPLOYMENT_NAME"), name="research_assistant", description="A helpful research assistant", model_args={ "azure_endpoint": os.environ.get("AZURE_OPENAI_ENDPOINT"), "api_key": os.environ.get("AZURE_OPENAI_API_KEY"), "api_version": os.environ.get("OPENAI_API_VERSION"), "model": "gpt-4o", # Actual model to use in minion framework }, tools=[ minion_agent.tools.browser_tool.browser, ], agent_type=CodeAgent, # Default agent type for EXTERNAL_MINION_AGENT ) # Create agent with EXTERNAL_MINION_AGENT framework (default) agent = await MinionAgent.create_async(AgentFramework.EXTERNAL_MINION_AGENT, agent_config) # Run the agent with a question result = await agent.run_async("What are the latest developments in AI?") print("Agent's response:", result.final_output.content) if __name__ == "__main__": asyncio.run(main()) ``` see example.py see example_browser_use.py see example_with_managed_agents.py see example_deep_research.py see example_reason.py ## Agent Frameworks Minion Agent supports multiple agent frameworks. The default framework is `EXTERNAL_MINION_AGENT`, which provides enhanced capabilities including: - **Code Generation and Execution**: Advanced code generation with built-in execution capabilities - **Browser Automation**: Integrated browser control and web interaction - **MCP Tool Support**: Full Model Context Protocol integration - **Enhanced Planning**: Sophisticated task planning and execution ### Available Frameworks - `EXTERNAL_MINION_AGENT` (Default): Enhanced framework with code execution and browser capabilities - `SMOLAGENTS`: HuggingFace's smolagents framework with planning support - `LANGCHAIN`: LangChain-based agents - `OPENAI`: OpenAI's assistant API - `BROWSER_USE`: Specialized for browser automation tasks - `DEEP_RESEARCH`: Optimized for research and information gathering ### Framework-Specific Agent Types When using `EXTERNAL_MINION_AGENT`, you can specify different agent types: ```python from minion.agents
Excerpt of 7,938 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:785e410b802d495e, llm:Description: "A simple agent framework that's capable of browser use + mcp + auto instrument + plan + deep research + more" (repo description). Language: Python.
matched fp:785e410b802d495e, llm:Description: "A simple agent framework that's capable of browser use + mcp + auto instrument + plan + deep research + more" (repo description). Language: Python.
matched fp:785e410b802d495e, llm:Description: "A simple agent framework that's capable of browser use + mcp + auto instrument + plan + deep research + more" (repo description). Language: Python.