microbots 0.0.20

container-based autonomous agent framework

🤖 Microbots

MicroBots is a lightweight, extensible AI agent for code comprehension and controlled file edits. It integrates cleanly into automation pipelines, mounting a target directory with explicit read-only or read/write modes so LLMs can safely inspect, refactor, or generate files with least-privilege access.

🚀 Quick Start

Pre-requisites

• Docker
• AI LLM Provider and API Key

Install

pip install microbots

Example

from microbots import WritingBot

myWritingBot = WritingBot(
    model="azure-openai/my-gpt5",
    folder_to_mount=str("myReactApp"),
)

data = myWritingBot.run(
    "Fix the build error and make sure the build is successful.",
    timeout_in_seconds=600,
)
print(data.results)

🤖 Available Bots

Bot	Description
ReadingBot	Reads files and extracts information based on instructions (read-only)
WritingBot	Reads and writes files based on instructions (read/write)
BrowsingBot	Browses the web to gather information
LogAnalysisBot	Analyzes logs for debugging
AgentBoss	Orchestrates multiple bots for complex tasks

⚙️ How it works

MicroBots creates a containerized environment and mounts the specified directory, restricting permissions to read-only or read/write based on the Bot used. This ensures AI agents operate within defined boundaries, enhancing security and control over code modifications while protecting the local environment.

✨ LLM Support

Microbots supports multiple LLM providers — pick whichever fits your stack:

Provider string	Description
openai	OpenAI or Azure OpenAI via the OpenAI SDK (API key)
azure-openai	Azure OpenAI via the Azure SDK (API key or Azure AD token)
anthropic	Anthropic models, direct or via Azure AI Foundry
ollama-local	Local models via Ollama

Each provider has its own set of environment variables (endpoint, API key, deployment name, etc.). See the Authentication guide for the exact .env variables required for each provider and for Azure AD / managed identity setup.

Azure Pipelines Log Analyzer

Microbots includes a published Azure DevOps Marketplace task, MicrobotsLogAnalyzer@0, for analyzing logs with Azure OpenAI models through an Azure Resource Manager Service Connection. See docs/advanced/azure-pipelines-log-analyzer.md to install and use the task in Azure Pipelines.

---

🎯 Getting Started

Ready to build your first Microbot project? Follow the step-by-step onboarding guide:

➡️ Get Started with Microbots

🛠️ Developer Contribution Guidance

Want to contribute to Microbots? Follow the step-by-step guide to set up your environment and meet the project's code and documentation standards:

➡️ Developer Contribution Guidance

📚 Links

• GitHub Repository
• Contributing Guide
• Code of Conduct

Legal Notice

Trademarks: this project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow Microsoft's Trademark & Brand Guidelines. Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party's policies.