Skip to main content

A plethora of small llama-index based agents and tools to create agentic systems

Project description

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

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

llarmy-0.0.1.tar.gz (8.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

llarmy-0.0.1-py3-none-any.whl (3.7 kB view details)

Uploaded Python 3

File details

Details for the file llarmy-0.0.1.tar.gz.

File metadata

  • Download URL: llarmy-0.0.1.tar.gz
  • Upload date:
  • Size: 8.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.5

File hashes

Hashes for llarmy-0.0.1.tar.gz
Algorithm Hash digest
SHA256 7a716b81ccaaa6904d86f1a7c2d36658a4bea7fe2181066cd19e8f7d1014239e
MD5 99a4deeba7867931b0672b32fe85c47c
BLAKE2b-256 a9fbf38891ab68a7a3574d7f018e9fd843e7b7a46fa59da1551678cc445e1100

See more details on using hashes here.

File details

Details for the file llarmy-0.0.1-py3-none-any.whl.

File metadata

  • Download URL: llarmy-0.0.1-py3-none-any.whl
  • Upload date:
  • Size: 3.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.5

File hashes

Hashes for llarmy-0.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 e7d99670d4730a7c3590ac35dee53f39f75bcc607fdfacd63a7fe03ea1ed7a2b
MD5 98111a116186dfda6832dc53ba8e962d
BLAKE2b-256 c00ee4835944fa7d881705dd0a37846c21085992cca1533100aa4491f0d55b5f

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page