microsoft/TinyTroupe

Health v2 · maintenance only

Adoption not part of the score

7556 stars · 683 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

TinyTroupe is an experimental Python library for simulating people with specific personalities, interests, and goals using LLM-powered agents (TinyPersons) in simulated environments (TinyWorlds). It focuses on business and productivity scenarios like ad evaluation, brainstorming, and synthetic data generation rather than user-facing assistance.

Use cases

• simulate focus groups to get product feedback
• evaluate digital ads offline with a simulated audience
• generate synthetic training data with realistic personas
• get persona-based feedback on product or project proposals
• generate test inputs for chatbots or search engines and evaluate results
• brainstorm ideas with simulated expert personas

When to choose

• you want LLM-driven multiagent persona simulation for business or research insights
• you need synthetic behavioral data or simulated audience feedback cheaply
• you want customizable personas in a programmable simulated environment

When to avoid

• you need a production-ready, stable library - it is explicitly experimental
• you want an AI assistant to directly support end users rather than simulate behavior
• you need game-like roleplay simulation rather than business-focused scenarios

Facets

library · maturity experimental

agent-framework llm-inference data-generation simulation artificial-intelligence large-language-models data-science simulation python cross-platform multiagent persona-simulation synthetic-data focus-groups business-insights gpt-4 ai-agents

Member repositories

For agents

markdown · JSON · MCP: product_card(name="microsoft/TinyTroupe")