FollowAgents AI AGENTS DIRECTORY
Home / All Agents / GPTeam Collaborative Agents
Productivity & Collaboration multi-agent-simulationgpt-4agent-memorydiscord-integrationanthropic-claudewindow-extension

GPTeam Collaborative Agents

A shared-world simulation where memory-equipped model agents communicate and work in parallel toward predefined goals.

View on GitHub ↗ Quick start ↓
Source repo
101dotxyz/GPTeam
Stars
★ 1.7k
Last updated
2y ago
License
MIT
Primary language
Python
FA score
44/100 · Major gaps

At a glance

How it runs
CLI
Works with
Portable with changesOpenAI API · Claude API
Cost
Free software; you pay for model usage
Setup effort
Medium · a few setup steps
You'll need
PythonPoetryOpenAI API keyShell / CLINetwork accessLocal filesystem
Typical use
A developer studying multi-agent collaboration can observe memory-equipped agents divide work and communicate around predefined goals.
Not a fit if
  • Users wanting a zero-config start; Python setup and .env keys are needed
  • Teams needing consistent quality; --turbo mode is documented as worse
Source review
44/100 · Major gaps

What does this agent do, and when should you use it?

GPTeam is an open-source multi-agent simulation centered on GPT-4. It runs multiple agents with individual memory inside a world where they communicate to pursue predefined directives. Agents can move between locations, perform tasks, speak with one another, and collaborate in parallel on common goals. While the world is running, text files in agents/ summarize each agent’s current state. The project is launched from the command line and uses API keys in .env for model access and optional services.

The user runs python setup.py to check and configure the environment, adds an OpenAI API key to .env, and starts the simulation with poetry run world. The world runs multiple agents with memory that move among locations, perform tasks, communicate, and collaborate in parallel toward shared goals. During execution, agents/ contains one txt file per agent with a summary of its current state. To alter the simulation, the user changes agents or locations in config.json, runs poetry run db-reset, and starts the world again.

  1. A developer studying multi-agent collaboration can observe memory-equipped agents divide work and communicate around predefined goals.
  2. A technical team demonstrating GPT-4-based agent simulation can run the world and inspect per-agent state through the agents/ directory.
  3. An experimenter changing participants or locations can edit config.json, reset the database, and rerun the world with the revised setup.
  4. A cost-conscious user who accepts lower-quality outcomes can run poetry run world --turbo to use gpt3.5-turbo for every LLM call.
  5. A user with Anthropic credentials can set ANTHROPIC_API_KEY and use poetry run world --claude through the documented Claude path.

How do you install or deploy this agent?

  1. Clone the repository and enter the project directory: cd gpteam.
  2. Run python setup.py to check and configure the environment as needed.
  3. Add an OpenAI API key to .env; API keys for optional services enable other tools.
  4. Start it with Poetry: poetry run world.

How do you use this agent?

Run poetry run world to start and observe the agent world. For a cheaper run, use poetry run world --turbo; it uses gpt3.5-turbo for all LLM calls, with worse results expected. After changing agents or locations in config.json, run poetry run db-reset and then poetry run world. To use Claude, set ANTHROPIC_API_KEY and run poetry run world --claude.

What are this agent's strengths and limitations?

Pros
  • Models collaboration as a shared world with locations, movement, and agent-to-agent communication rather than a single model call.
  • Gives every agent memory and exposes per-agent state summaries in agents/ while the simulation runs.
  • Documents default GPT-4 execution plus --turbo, Claude, and Window execution options.
Limitations
  • An OpenAI API key is required to run it, and optional tools require credentials for their respective services.
  • The lower-cost --turbo mode is explicitly documented as producing worse results.
  • Window mode depends on the Window extension, and some models may respond slowly because prompts are long.
  • Changing the world configuration requires a database reset, which clears the existing database state.

How does this agent compare with similar options?

The default path uses GPT-4. poetry run world --turbo switches all LLM calls to gpt3.5-turbo for lower cost with expected quality loss, while --claude uses claude-v1 and claude-v1-instant for different calls.

Key facts side by side with the most closely related agents.

Agent Source review Form / cost Stars Updated Language Full support on
GPTeam Collaborative Agents This agent 44 · Major gaps CLIFree + model costs ★ 1.7k 2y ago Python OpenAI API · Claude API
Obsidian Second Brain 63 · Some gaps Agent plugin / skillFree + model costs ★ 5.2k today Python Codex · Claude Code
Commonly 70 · Some gaps Self-hosted serviceFree + model costs ★ 1.4k today JavaScript Codex · Claude Code
SwarmVault 75 · Good CLIFree + model costs ★ 733 4mo ago TypeScript Codex · Claude Code

How does FollowAgents rate this agent?

FollowAgents source review · FARS-2.1
Major gaps
44/ 100 5-point scale 2.2 / 5
Trust 10/29
Reliability 5/14
Adaptability 10/18
Convention 9/18
Effectiveness 7/13
Verifiability 3/8
Why each dimension lost points
Trust10 / 29 · 1.7/5

The README asks users to place OpenAI and optional service API keys in .env. main.py reads OPENAI_API_KEY and starts the world, Discord listener, and web server. Data flows, permission scope, and external effects are partly visible, but key protection, startup confirmation, recovery, and side-effect controls are not described, so most criteria receive 1. The README links a research paper and architecture article, providing limited attribution; responsibility and an update path are unclear.

Reliability5 / 14 · 1.8/5

The README gives startup steps and pyproject.toml states the Python range and dependency constraints, but no lockfile or dependency availability guarantee is shown. main.py catches exceptions and prints a traceback, offering basic but weakly user-oriented failure reporting. The README directs users to run setup.py, and the shown CI covers that script; it does not verify the full Agent run, limiting consistency and reliability evidence.

Adaptability10 / 18 · 2.8/5

The README describes multi-agent collaboration, predefined goals, locations, and communication, and documents turbo, Claude, Window, and Discord options. This supports ordinary scenario and environment fit. Capability boundaries and suitability limits are sparse, which keeps those scores low.

Convention9 / 18 · 2.5/5

The README is organized around overview, setup, operation, configuration, integrations, and contribution, with actionable setup steps, command examples, and a pointer to separate Discord documentation. The MIT license text is complete. The packet shows no version history or changelog, and maintenance responsibility is only generally described as contribution and PR review, so those scores are reduced.

Effectiveness7 / 13 · 2.7/5

The README explains agent collaboration and how to observe agent state, and offers turbo as a way to reduce model-call costs. This supports usability and potential value, but there is no quantified effectiveness or full cost discussion.

Verifiability3 / 8 · 1.9/5

README claims about features and operation partly correspond to main.py and pyproject.toml; the CI file supports only the narrow claim that setup.py is run across operating systems. No evidence validates Agent outcomes. Scores reflect limited traceability in this static packet and distinguish descriptive claims from actual verification.

Risks and how to mitigate them
  • Running requires API keys and starts the world, Discord listener, and local web server; the static material does not explain key protection or detailed data handling by these components.
  • The shown CI runs only setup.py, so it does not establish Agent outcome correctness, runtime stability, or reproducibility.
Evidence confidence: Low Reviewed Nov 08, 2026 Reviewed revision a216364ea2db
Review evidence README.mdsrc/main.pyLICENSEpyproject.tomlworkflows/test_setup_script.yml
See the full review method →
Maintain this project? Add the FARS badge to your README

The badge shows the current review score and verdict and links back to this page. It refreshes about once an hour after a re-review.

FARS

[![FARS review](https://followagents.com/badge/gpteam.svg)](https://followagents.com/en/agents/gpteam)
<a href="https://followagents.com/en/agents/gpteam"><img src="https://followagents.com/badge/gpteam.svg" alt="FARS review"></a>

FAQ

What credentials are required?
An OpenAI API key is required in .env. API keys for optional services enable their associated tools.
How can I reduce run cost?
Use poetry run world --turbo, which uses gpt3.5-turbo for all LLM calls; the documentation warns that results will be worse.
How do I see what agents are doing?
While the world runs, inspect agents/; each agent has a txt file summarizing its current state.
Can it run with Claude?
Yes. Set ANTHROPIC_API_KEY and run poetry run world --claude; the documented mode uses claude-v1 for some calls and claude-v1-instant for others.
What should I do after changing agents or locations?
Update config.json, run poetry run db-reset, then run the world again.
Was this page helpful?
View on GitHub ↗ Install ↓