L2mac
by Community
๐ The LLM Automatic Computer Framework: L2MAC
Agents
L2mac
Added 10 July 2026
Overview
L2mac is an open-source Python framework that turns LLMs into autonomous agents capable of controlling a simulated computer. It uses a multi-agent architecture to break down complex tasks into subtasks, each handled by a specialized LLM agent that can write and execute code, manage files, and interact with a virtual environment.
Best for
Best for
Developers building autonomous coding agents or complex multi-step automation pipelines
Use cases
- Automating multi-step software development workflows
- Running long-horizon tasks that require file system and shell access
- Building and testing prototypes through iterative code generation
Notes
L2mac is an open-source Python framework that turns LLMs into autonomous agents capable of controlling a simulated computer. It uses a multi-agent architecture to break down complex tasks into subtasks, each handled by a specialized LLM agent that can write and execute code, manage files, and interact with a virtual environment.
157 stars on GitHub. Last updated 2024-12-27. Licensed MIT.
Use cases
- Automating multi-step software development workflows
- Running long-horizon tasks that require file system and shell access
- Building and testing prototypes through iterative code generation
Pros
- Modular multi-agent design allows parallel subtask execution
- Full computer control enables complex, real-world automation
- Active community with 157 GitHub stars and ongoing development
Cons
- Requires significant computational resources for multiple LLM agents
- Limited documentation and examples for advanced use cases
- Relies on external LLM APIs, adding cost and latency
Indexed from awesome-ai-agents and enriched against its public facts.
Pros
- Modular multi-agent design allows parallel subtask execution
- Full computer control enables complex, real-world automation
- Active community with 157 GitHub stars and ongoing development
Cons
- Requires significant computational resources for multiple LLM agents
- Limited documentation and examples for advanced use cases
- Relies on external LLM APIs, adding cost and latency
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
OpenDevin
Community
๐ OpenHands: AI-Driven Development
AutoGPT
Community
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
MetaGPT
Community
๐ The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming