MultiAgentPacman offers a Python-based game environment where users can implement, visualize, and benchmark multiple AI agents in the Pacman domain. It supports adversarial search algorithms like minimax, expectimax, alpha-beta pruning, as well as custom reinforcement learning or heuristic-based agents. The framework includes a simple GUI, command-line controls, and utilities to log game statistics and compare agent performance under competitive or cooperative scenarios.

RL Collision Avoidance provides a complete pipeline for developing, training, and deploying multi-robot collision avoidance policies. It offers a set of Gym-compatible simulation scenarios where agents learn collision-free navigation through reinforcement learning algorithms. Users can customize environment parameters, leverage GPU acceleration for faster training, and export learned policies. The framework also integrates with ROS for real-world testing, supports pre-trained models for immediate evaluation, and features tools for visualizing agent trajectories and performance metrics.

ThreeAgents is built in Python, leveraging OpenAI's chat completions API to instantiate multiple AI agents with distinct roles (system, assistant, user). It provides abstractions for agent prompting, role-based message handling, and context memory management. Developers can define custom prompt templates, configure agent personalities, and chain interactions to simulate realistic dialogues or task-oriented workflows. The framework handles message passing, context window management, and logging, enabling experiments in collaborative decision-making or hierarchical task decomposition. With support for environment variables and modular agents, ThreeAgents allows seamless swapping between OpenAI and local LLM backends, facilitating rapid prototyping of multi-agent AI systems. It ships with example scripts and Docker support for quick setup.

Thufir is a Python-based open-source agent framework designed to facilitate the creation of autonomous AI agents capable of complex task planning and execution. At its core, Thufir provides a planning engine that decomposes high-level objectives into actionable steps, a memory module for storing and retrieving contextual information across sessions, and a plug-and-play tool interface allowing agents to interact with external APIs, databases, or code execution environments. Developers can leverage Thufir’s modular components to customize agent behaviors, define custom tools, manage agent state, and orchestrate multi-agent workflows. By abstracting away low-level infrastructure concerns, Thufir accelerates the development and deployment of intelligent agents for use cases like virtual assistants, workflow automation, research, and digital workers.

AgentServe provides a unified interface for creating and deploying AI agents. Users define agent behaviors in configuration files or code, integrate external tools or knowledge sources, and expose agents over REST endpoints. The framework handles model routing, parallel requests, health checks, logging, and metrics out of the box. AgentServe’s modular design allows plugging in new models, custom tools, or scheduling policies, making it ideal for building chatbots, automated workflows, and multi-agent systems in a scalable, maintainable way.