Skip to content

ashwin2912/Autonomous-Intelligence

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

65 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Multi-Agent AI Systems: Winter Open Source Project

This is an open-sourced, research-driven initiative designed to explore and develop multi-agent AI systems over the winter. The project focuses on building a General Purpose AI Agent Framework and establishing a Registry of Domain-Specific AI Agents.

Agenda:

  • Intros
  • AI Agent Project Overview
  • Agent Presentation
  • Agent Registry
  • Agent Product Specs
  • Codebase Setup
  • Communications / Next Steps
  • Q&A

Product Overview

Project Milestones

1. Documentation

  • Comprehensive guides for understanding and using the framework and registry.

2. Website / Landing Page

  • A user-friendly interface for showcasing the project.

3. Product Development

  • Frontend/UI: Intuitive design for interaction.
  • Backend: Scalable and efficient architecture.
  • Software Developer Kit (SDK): Tools for developers to build and integrate agents.

4. Framework for Agent Registry

  • A structured catalog of reusable, domain-specific AI agents.

5. Final Deliverables (Early February)

  • Contribute to the open-source agent repository or develop a closed-source agent to add to the registry.
  • Deliver a Final Presentation during “AI Day,” showcasing:
    • Video tutorials of AI agents in action.
    • Research insights from the project.

Using Agentic Systems

The project enables various ways to deploy and use AI agent systems:

1. Run on the Web

  • Access through the product UI.

2. Run On-Premise

  • Deploy via a desktop application.

3. Call via API

  • Use the developer kit to integrate into applications.

4. Query Processing with Orchestrator

  • NLP queries are routed to one or more agents (Agent 1, Agent 2, Agent 3, etc.).
  • Tasks are performed either in series or in parallel.
  • The system generates and returns an output to the user.
  • Includes logs to monitor agent progress.

5. Agent Templates and Compound Systems

  • Spawn agent templates directly into the chatbot.
  • Use a Drag & Drop Flow to design and execute compound agent systems.

Notes

We will aim to really build two products over the winter:

  • the general purpose AI agent framework (main project)
  • a registry of specialized agents for specific domains

For each of these products, there will be a lot of details. For folks on the technical side, if you could try to follow the codebase development environment document in the materials folder of the Github repository, and get the codebase set up that would be appreciated. If you have any questions / experience any bugs, feel free to reach out directly, and I can either help you resolve the error or point you to the right POC.

For folks on the non-technical side, if you could look into the following resources that would be appreciated:

As far as a final deliverable, we will have final presentations on February 11th at 6 PM EST (date / time tentative). It would be awesome if whoever is interested could give a presentation on a topic that they worked on over the winter related to agents (similar to AI Day), that we could share / post on our youtube channel.

Natan will aim to hold weekly office hours on each Monday between 5 PM EST and 6 PM EST, in case anyone has any questions and would like to collaborate.

Communications will take place in the #agents thread within the anote slack channel (temporary link to join here): https://join.slack.com/t/anote-ai/shared_invite/zt-2vdh1p5xt-KWvtBZEprhrCzU6wrRPwNA

Get Involved

Join the initiative by contributing to the open-source repository, building specialized agents, or collaborating on research and development. Showcase your work during the AI Day event!

Note: to run code correctly you'll need to replace the openAI api key

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • HTML 40.2%
  • JavaScript 29.2%
  • Python 20.7%
  • CSS 9.9%