Skip to main content

🤖 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

Overall Architecture

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

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.

Metadata

Release files for microbots 0.0.22

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for microbots 0.0.22
File Size Uploaded Provenance Actions
microbots-0.0.22.tar.gz 2.1 MB Without provenance Details for microbots-0.0.22.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for microbots 0.0.22
File Interpreter ABI Platform Actions
microbots-0.0.22-py3-none-any.whl Python 3 none any Details for microbots-0.0.22-py3-none-any.whl

Total release size: 2.2 MB

Release files / microbots-0.0.22.tar.gz

Download URL microbots-0.0.22.tar.gz
Size 2.1 MB
Tags Source
SHA-256 checksum
How to use checksums
9b66f3f3a4a501ef23c89a1feca57b1d1c0f7c3e58f2e1f2bee6b0796d1f262c
BLAKE2b-256 checksum
How to use checksums
9afd3ae0382c789a674b675e8f8bd15d5114b5b3eb79d24be71edd887a94ec86
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.13.16

Release files / microbots-0.0.22-py3-none-any.whl

Download URL microbots-0.0.22-py3-none-any.whl
Size 135.9 kB
Tags Python 3
SHA-256 checksum
How to use checksums
927fa1c67e7068e7db0476ac02b18576bd3de822c1eff1fe499667104afec43d
BLAKE2b-256 checksum
How to use checksums
7bed8d60fdbcbb6b3cb8ecdf357590f4d33a96d9896150a65546861b729a3228
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.13.16

Security for microbots 0.0.22

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page