# 101dotxyz/GPTeam

GPTeam: An open-source multi-agent simulation

Repository: https://github.com/101dotxyz/GPTeam
Canonical: https://ross.abutalabs.com/products/gpteam
Homepage: https://www.gpteamai.com/
Language: Python
License: MIT
License Family: permissive
Topics: ai, agents, autogpt, gpt-4
Last push: 2026-08-26T17:04:47+00:00

## Health v2 (maintenance only)
Score: 75/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 35, longevity 89
- inputs: {"age_days": 1248, "days_push": 7, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1723, forks 252 (observed 2026-08-28T04:05:27.910204+00:00)

## What it is
GPTeam is an open-source multi-agent simulation that uses GPT-4 to create multiple AI agents with memory who collaborate and communicate to achieve predefined goals. Agents move around a configurable world, speak to each other, and work in parallel on tasks, with agent memory and reflection inspired by generative agent research.

## Use cases
- simulate multiple AI agents collaborating on tasks
- explore multi-agent communication with GPT-4
- run a simulated world of agents with memory and reflection
- experiment with agent-to-agent collaboration architectures
- watch agents interact and complete directives in parallel
- customize agent and location configurations via config.

## When to choose
- you want to experiment with multi-agent collaboration and communication patterns
- you need a research playground for agent memory and reflection inspired by the generative agents paper
- you want a configurable simulated world of GPT-4 agents you can run locally
- you want to observe agent states and interactions in a lightweight setup

## When to avoid
- you need a production-ready multi-agent orchestration framework for real workloads
- you want to avoid OpenAI API costs, since running the simulation requires paid LLM calls
- you need a stable, actively developed tool rather than an exploratory research project
- you need fine-grained programmatic control over agent behavior beyond config.

## Facets
- artifact type: application
- maturity: maintenance
- function: agent-framework, llm-inference, chatbot
- domain: artificial-intelligence, large-language-models, simulation
- platform: python, cross-platform, cli
- tags: multi-agent, gpt-4, autogpt, agent-memory, simulation, langchain, discord-integration, ai-agents

## Member repositories
- 101dotxyz/GPTeam (main) score 75

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:27.910204+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:33:55.991518+00:00, confidence not recorded.
  - readme: https://github.com/101dotxyz/GPTeam (fetched 2026-08-28T04:05:27.910204+00:00, sha a9ca3dcda537)
  - homepage: https://www.gpteamai.com/ (fetched 2026-08-29T11:09:21.439166+00:00, sha e532fd131c64)
- Data as of 2026-08-30T08:39:29.467469+00:00.