Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Feature: Add Swarm Agent Capabilities to Eliza #1560

Open
UD1sto opened this issue Dec 29, 2024 · 4 comments
Open

Feature: Add Swarm Agent Capabilities to Eliza #1560

UD1sto opened this issue Dec 29, 2024 · 4 comments
Labels
enhancement New feature or request

Comments

@UD1sto
Copy link
Contributor

UD1sto commented Dec 29, 2024

Description
Adding a new type of “swarm agent” to the Eliza framework. The goal is to allow multiple agents to coordinate on tasks in a way similar to how single-character agents are currently configured, while supporting unique swarm features such as collective decision-making and interactions among multiple agents.

Motivation & Rationale

Eliza currently supports single “character” agents with various providers, settings, and behaviours.
A natural next step is to introduce the ability for multiple agents to work collectively (swarm) on tasks.

Proposed Feature Requirements

  1. Swarm Agent Configuration

Support a dedicated configuration block for swarm agents in a manner similar to single-character agents.

Allow specifying:

  • Number of agents in the swarm.
  • Provider definitions for each agent (could be the same or different).
  • Traditional settings (e.g., roles, personas, capabilities).
  • Additional swarm-specific settings (e.g., rules for agent coordination, speaker settings, collective decision-making thresholds).`
  1. Create Swarm Logic.
  • Configure and Execute swarms by importing the core package in external projects.
  • Allow all supported clients to use swarm logic without disrupting current flows(ex: the last agent in a twitter maker team will post as a singular agent akin to current implementation).
  • Write dedicated test suite or carefully extend the current tests to confirm proper handling of the majority of cases.
  1. Document feature:
  • How multiple agents can be spawned and coordinated.
  • How tasks or sub-tasks are delegated among swarm agents (e.g., parallel vs. sequential).
  • How swarm memory storage works.
  • Document possible flows.
  • How can the utility be extended further.
@UD1sto UD1sto added the enhancement New feature or request label Dec 29, 2024
@UD1sto
Copy link
Contributor Author

UD1sto commented Dec 29, 2024

Please comment here if you are interested in partnering on this effort

@alessandromazza98
Copy link
Contributor

Please comment here if you are interested in partnering on this effort

I'm interested to help here. Still a bit new to this repo, but fast to learn 🤝

@humanagent
Copy link

Same! But in js?

@UD1sto
Copy link
Contributor Author

UD1sto commented Jan 2, 2025

@alessandromazza98 @humanagent would love to discuss this further on discord! This is my handle 'de_fi_ne'

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
Development

No branches or pull requests

3 participants