You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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
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).
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.
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.
The text was updated successfully, but these errors were encountered:
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
Support a dedicated configuration block for swarm agents in a manner similar to single-character agents.
Allow specifying:
The text was updated successfully, but these errors were encountered: