AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompare
Home/
Multi-Agent/
concordia
concordia logo

concordia

Active·★ 1.8k·Apache-2.0·Updated 2026-10-20
★ Trending

Concordia is Google DeepMind's open-source library for generative social simulation. It builds generative agent-based models in which entities powered by a language model interact in grounded physical, social or digital environments. The interaction pattern comes from tabletop role-playing games: a special Game Master entity simulates the environment, player entities describe their intended actions in natural language, and the Game Master decides what actually happens, for example by checking physical plausibility.

It is used for social science research, AI safety and ethics studies, cognitive science, economics, synthetic data generation for personalisation, and evaluating real services through simulated usage. Simulations are built from entities made of components (instructions, memory, action selection and so on); prefabs provide ready-made entity templates you can customise, and an engine runs the loop that assigns player and Game Master roles. A GUI and command-line interface let you inspect components, edit a simulation and watch its behaviour, and the design is documented in a tech report and a design-pattern paper.

© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.

Guides

Getting started: note that the PyPI package is named `gdm-concordia`, not `concordia`. Run `pip install gdm-concordia`, then `import concordia` in your code. You need access to a standard LLM API. The tutorial notebook and a video lecture walk through building a first simulation.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool. Data as of 2026-10-17.

License
Apache-2.0
Latest release
v2.4.0 · 2026-03-06
Last commit
2026-10-16
Contributors
62
Forks
386
Open issues and PRs
53
First published
2023-11-21
PyPI package
gdm-concordia 2.4.0 · 760 downloads last week

Source: GitHub, npm and PyPI public APIs.

#Generative AI#Agent-based Modeling#Social Simulation#LLM#Python#Coding
$ Install
$ pip install gdm-concordia
↗ Visit site★ GitHub
01

Features

01Generative agent-based modeling
02Game Master (GM) pattern for environment simulation
03Natural language agent actions
04Integration with external tools/APIs (via GM)
05Supports a wide array of research and application areas
02

Why choose it

+Well-designed abstraction (Game Master plus entities and components) for simulations driven by language models.
+Backed by Google DeepMind research, with a tech report and design-pattern paper.
+Prefabs, a GUI and a CLI make simulations easier to build and inspect.
+Apache-2.0 licensed and actively maintained.
03

Trade-offs

!The PyPI name (`gdm-concordia`) differs from the import name, which trips up many first-time installs.
!Simulations with many entities make many model calls, so cost and runtime grow quickly.
!It is a research library: you design the experiment and interpret results yourself; it is not a ready-made product.
04

Maintenance check

ActiveChecked: 2026-10-18
Last commit
2026-10-16
Commits, last 90 days
79
Releases, last 90 days
0
Latest release
v2.4.0 (2026-03-06)
Open issues
54
Recent issues with at least one comment
6/15
Commits per week, last 12 weeks
Commits per week, last 12 weeks: 5, 4, 1, 0, 8, 3, 1, 5, 7, 8, 16, 0

Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

05

Compatibility

Generic LLM API
Supported
Verified via docs
Google LLM API
Native
Verified via docs
Python
Native
Verified via docs
06

Quick start

1
$ pip install gdm-concordia
07

Use cases

↳Social science research
↳AI ethics and cognitive neuroscience studies
↳Generating data for personalization applications
↳Performance evaluation of real services through simulated usage
↳Economics research
08

Alternatives

⚡Top VS:
VSPydantic AI★20.8k→VSmcp-agent★8.6k→VSchatarena★1.6k→VS

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Maintenance check05Compatibility06Quick start

Most discussed open issues

  • #161 Support for Anthropic + OpenRouter8 comments · 2025-08-26
  • #178 Fix invalid Python dev container image tag7 comments · 2025-12-07
  • #205 Expand test coverage for contrib/components and core modules6 comments · 2026-01-28
  • #159 Reproducing Concordia Contest @NeurIPS 20246 comments · 2025-08-19
  • #146 An installation problem5 comments · 2025-06-06

Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.

edsl
★507
→
Pydantic AI logo
Pydantic AI★ 20.8k
GenAI Agent Framework, the Pydantic way. A Python agent framework designed for production with type safety at its core.
VSCompare→
mcp-agent logo
mcp-agent★ 8.6k
Build effective agents using Model Context Protocol and simple workflow patterns
VSCompare→
chatarena logo
chatarena★ 1.6k
ChatArena (or Chat Arena) is a Multi-Agent Language Game Environments for LLMs. The goal is to develop communication and collaboration capabilities of AIs.
VSCompare→
edsl logo
edsl★ 507
Design, conduct and analyze results of AI-powered surveys and experiments. Simulate social science and market research with large numbers of AI agents and LLMs.
VSCompare→
skyagi logo
skyagi★ 775
SkyAGI: Emerging human-behavior simulation capability in LLM
VSCompare→
deer-flow logo
deer-flow★ 84.3k
DeerFlow is a community-driven Deep Research framework, combining language models with tools like web search, crawling, and Python execution, while contributing back to the open-source community.
VSCompare→
Microsoft AutoGen logo
Microsoft AutoGen★ 61.5k
A framework that enables the development of LLM applications using multiple agents that can converse with each other to solve tasks.
VSCompare→
CrewAI logo
CrewAI★ 60.0k
Framework for orchestrating role-playing, autonomous AI agents. By working together, your Crew can tackle complex tasks.
VSCompare→
See all alternatives →
07
Use cases
08Alternatives
google-deepmind /
concordia
↗

Google DeepMind library for generative social simulation

1.8k386Apache-2.0
Last commit3d ago
StatusActive
CategoryMulti-Agent
Contributors62
Latest releasev2.4.0
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit