Search Results for "jade multi agent"

Gradient Bang is an experimental open-source project developed within the Pipecat ecosystem that reimagines AI interaction as a persistent, multiplayer simulation where users and large language models coexist inside a shared virtual environment. Rather than functioning as a traditional application or API, it is conceptualized as an “online multiplayer universe” in which participants can explore, trade, battle, and collaborate while interacting with AI agents as active entities within the...

...Agents learn behaviors in a shared ecosystem that supports long-term training and emergent dynamics across large populations. The project is built to test scalability in multi-agent reinforcement learning, with features such as procedurally generated terrain and configurable game mechanics. While the original release has since been succeeded by newer versions maintained outside OpenAI, it remains a landmark framework for studying large-scale agent interactions in complex environments.

...A C++ core provides fast environments and concurrent actors, while Python bindings expose simple APIs for agents, replay, and optimization loops. It supports both single-agent and multi-agent settings, with batched stepping and shared-memory queues that keep GPUs saturated during training. ELF introduced widely used reference systems, most notably ELF OpenGo, demonstrating at-scale self-play with strong analysis tooling and public checkpoints. Its design emphasizes reproducibility: deterministic seeds, logging, and evaluation harnesses make large-scale experiments trackable and comparable. ...

...To provide a set of agents that non-technical people can play around with and get a feel for how various AI techniques work. CoffeeMudForAI goals 1. To provide a platform to study the non-robotic aspects of AI(AI Planning, inter-agent planning, muti-agent planning, Machine learning, etc.) 2. To provide a game-like platform so people coming from the game AI world can contribute to AI research.

Limph Is Monitoring Pingable Hosts. Written in PHP(multi-DB) for portability, Limph provides ICMP, UDP, TCP and agent checks of grouped network hosts with email notification. Limph is completely web-configurable, an advantage over similar applications.

A multi-agent architecture for building interactive dramas. It uses the Jason's BDI engine, being the Jason's agent-oriented programming language utilized for performing the drama management and for authoring behaviors for the characters.

MASyV (Multi-Agent System Visualization) enables one to write agent-based models/cellular automata, eg. in C, visualize them in real time & capture to movie file with MASyVs GUI & message passing lib. Includes examples: Hello World, ants, viral infection

SARGE - Search And Rescue Game Environment is a multi-player training game for robot operators which also supports agent based robot control for simulation work via TCP.

Symbiomotive is an extensible engine for modeling multi-agent environments that exhibit self-organizing, symbiotic behaviors.

The FlashServer is a part of the MASSim project of the Computational Intelligence Group at the TU Clausthal, Germany and his main task is the visualization of the games as Flash videos. Currently the FS is not in use during the Multi-Agent Contest.

The Virtual Storyteller is a multi-agent framework for generating stories based on a concept called emergent narrative.

LabLOVE (Life On a Virtual Environment) is an evolutionary multi-agent simulation environment. It is fast, modular and extensible. Contains the reference implementation for the gridbrain algorithm.

TOS is a multi-player soccer simulation game and a match simulation engine for on-line soccer management games. TOS can also be used as a tool for multi-agent AI research and education.

This is a framework to develop Contexts and Agents and a Container to run them. The Container lets each Agent interact with the Context and other Agents. The agents are deployed in jar files and each one runs in an exclusive sandbox.

Fungus is a framework for distributed simulation by multi-agents. It uses a very modular architecture. A GUI is provided. In our model, everything is Agent. Even the environnement. You have an access to the communication's 'canals'.