Search

More Filters

Show More
Add Listing
Go Back

AgentVerse

0
New
Multi-Agent Platforms & Frameworks
Report

Report Abuse

Basic Information

AgentVerse is an open-source Python framework to build, run and study systems composed of multiple large language model based agents. The repository provides two primary frameworks: a task-solving framework that composes multiple agents into an automatic multi-agent system to collaboratively solve problems, and a simulation framework that creates custom environments to observe and interact with agent behaviors. It includes example scenarios and demos such as NLP Classroom, Prisoner’s Dilemma, software design, database administrator, and game-like interactions. The project targets researchers and developers who want to deploy multi-agent LLM applications, reproduce experiments from the accompanying paper, or explore emergent behaviors among agents. The codebase supports both cloud APIs and local models and includes CLI and optional GUI interfaces for running tasks and simulations.

Links

Stars
4714
App URL
https://github.com/OpenBMB/AgentVerse
Github Repository
https://github.com/OpenBMB/AgentVerse/blob/main/README.md

Categorization

App Details

Features
AgentVerse supplies modular components for agents and environments and ready-to-run tasks and demos. It offers two frameworks: task-solving with benchmark support and tool-using agents, and simulation with customizable multi-agent environments. The repo provides CLI commands for launching simulations and task runs and a GUI demo server for local visualization. It supports cloud LLMs via OpenAI and Azure, local LLM integration via FSChat and listed models, vLLM server integration with API variables, and optional toolkits like BMTools and a ToolServer for tool-using experiments. Configuration-driven experiments are supported through YAML task configs and packaged example tasks including benchmarks like Humaneval and paper examples. The package is installable via pip or editable install and requires Python 3.9 or newer.
Use Cases
AgentVerse helps researchers and developers prototype and evaluate multi-agent LLM systems without building orchestration from scratch. It centralizes components for agent behaviors, environment definitions, and task configurations so teams can quickly reproduce published experiments, run benchmarks, and compare setups across local and cloud LLMs. The simulation framework enables controlled studies of emergent social behaviors and interactive scenarios, while the task-solving framework demonstrates collaborative problem solving and tool use. Built-in examples, CLI and GUI runners, and guidance for integrating local models, vLLM, and external ToolServers reduce engineering overhead. Documentation and community resources such as demos, showcases, and contribution guidelines further assist users in extending the framework and applying it to research, application prototypes, or educational experiments.

Categories

Content Creation (5042)
Monetization & Business (2246)
Development Tools (1407)
Marketing & Social Media (1403)
Education & Career (1380)
Multi-Agent Platforms & Frameworks (1009)
Health & Life (957)
AI Resources (920)
Agents & Automation (778)
Data & Analytics (764)
Productivity Tools (679)
Writing & Editing (666)

Similar Listings

listing image

virtual lab

0 (0 review)
listing image

mnemo

0 (0 review)
listing image

EdgeChains

0 (0 review)
listing image

RAG Agents Accelerator

0 (0 review)
listing image

LLM Zero to Hundred

0 (0 review)

Featured Listings

Tags

Please fill the required fields*