LLArmy 🦙🔪🦙🔫🦙🔫

LLArmy is a collection of small, specialized LlamaIndex-based agents and tools designed to create powerful agentic systems.

PyPI: https://pypi.org/project/llarmy/

Repository: https://github.com/llarmy

Documentation: Coming soon

Overview

NOTE: This README is updated frequently as the project evolves. Check back for the latest features and examples!

Context

• LlamaIndex provides excellent data structures for connecting LLMs with external knowledge
• Agentic systems require specialized, composable tools for complex workflows
• Reusability is key - developers shouldn't rebuild common agent patterns

Proposed Solution

At its core, LLArmy provides a toolkit of specialized agents and utilities built on top of LlamaIndex. LLArmy helps provide the following advantages:

• Pre-built agents for common use cases, reducing boilerplate code
• Composable tools that can be combined to create complex agentic workflows
• LlamaIndex integration leveraging the power of existing data structures
• Lightweight design with minimal dependencies for maximum flexibility

Each agent and tool offers distinct use cases and customizable parameters. These can be combined and orchestrated to achieve various tasks:

• Multi-step reasoning workflows
• Data processing pipelines with AI assistance
• Intelligent automation for repetitive tasks
• Custom agentic systems tailored to specific domains

📄 Documentation

Full documentation is coming soon. For now, check the examples below and explore the source code in src/llarmy/.

💻 Example Usage