awesome-repositories.com
Blog
MCP
awesome-repositories.com

Discover the best open-source repositories with AI-powered search.

ExploreCurated searchesOpen-source alternativesSelf-hosted softwareBlogSitemap
ProjectMCP serverAboutHow we rankPress
LegalPrivacyTerms
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
a16z-infra avatar

a16z-infra/ai-town

0
View on GitHub↗
convex.dev/ai-town↗

Ai Town

AI Town is a TypeScript-based simulation engine used to create virtual environments where autonomous characters interact and socialize. It functions as a framework for orchestrating multiple AI agents within a persistent digital world, utilizing language models and a game engine to drive character behavior and social interactions.

The project differentiates itself through a dedicated agent sandbox and a vector database agent store, which allow for the management of agent memories and world state. It integrates generative AI for background music and provides tools for simulation world design, including the definition of maps and character assets.

The system covers a broad range of capabilities including real-time multiplayer synchronization via WebSockets and reactive data fetching. It incorporates serverless function orchestration, durable workflows for long-running tasks, and a relational-document data store with built-in vector search. Additional infrastructure includes cloud object storage, identity management, and comprehensive monitoring for function execution and system health.

Local development can be bootstrapped using Docker Compose.

AI search

Explore more awesome repositories

Describe what you need in plain English — the AI ranks thousands of curated open-source projects by relevance.

Start searching with AI

Features

  • Autonomous Agent Simulations - Creates virtual environments where autonomous AI characters interact using language model inference.
  • Autonomous AI Agent Simulations - Convex creates a virtual environment where digital characters interact via a game engine and language models.
  • Autonomous Agent Orchestration - Manages background processes and scheduled tasks to drive independent AI agent actions.
  • LLM Application Development - Integrates large language models with backend logic and databases to power dynamic conversations and autonomous agent behaviors.
  • LLM Provider Integrations - Facilitates connectivity and authentication for integrating external large language model providers.
  • Data Change Subscriptions - Pushes updated database results to clients automatically in real time whenever records change.
  • Data Schema Definitions - Specifies table structures and field types to ensure data consistency across the simulation store.
  • Atomic Transactions - Ensures data consistency by grouping multiple database reads and writes into single atomic transactions.
  • Database Record Querying - Retrieves database records using specific arguments, filters, and business logic.
  • Document-Relational Databases - Provides a database architecture combining flexible JSON document storage with relational linking.
  • JSON Document Storage - Supports native storage of semi-structured JavaScript-like objects as flexible JSON documents.
  • Real-time Data Subscriptions - Pushes real-time database updates to clients via WebSockets to synchronize the UI without polling.
  • Real-time Data Synchronization - Synchronizes the frontend automatically as backend code or database state changes.
  • Relational Data Modeling - Links documents across different tables using unique identifiers to model complex relationships.
  • Transactional Data Mutations - Provides mechanisms to modify application state via transactional data mutations from a JavaScript environment.
  • Type-Safe Database Clients - Implements a type-safe language for defining database schemas, queries, and APIs integrated with application code.
  • Vector Memory Stores - Implements a vector database store for managing agent memories and world state using semantic search.
  • Vector Search - Integrates built-in support for vector search to enable semantic retrieval of agent memories.
  • Simulation Worlds - Defines simulation maps and character assets to build structured digital environments for AI interaction.
  • Agent Orchestration Engines - Implements a TypeScript-based simulation engine for orchestrating multiple AI agents in a persistent digital world.
  • Reactive Record Mutations - Triggers automatic updates across all active reactive queries when backend data is modified.
  • Autonomous Process Orchestration - Runs autonomous background agents independently of user sessions via scheduled triggers and task queues.
  • Asynchronous Data Fetching - Automatically updates the user interface whenever the underlying database records change.
  • Multiplayer Synchronization - Synchronizes game state and character movements across multiple clients in real time using WebSockets.
  • Prompt-Based Audio Generation - Automatically produces generative background music based on configurable prompts.
  • Agent Sandboxes - Provides a dedicated development environment for testing autonomous agents with real-time state synchronization.
  • Job Schedulers - Automates repetitive maintenance tasks through a system for scheduling functions on a fixed timetable.
  • Background Processing - Provides an architecture for handling compute-intensive autonomous tasks asynchronously in the background.
  • Serverless Function Orchestration - Executes isolated backend logic on demand using a high-performance runtime to eliminate cold starts.
  • Delayed Executions - Enables the postponement of background task execution until a specified future timestamp.
  • World Design Tools - Provides tools for defining simulation maps and character assets to build structured digital spaces.
  • High-Performance - Utilizes a high-performance runtime designed to eliminate cold starts and provide fast database access for TypeScript code.
  • Durable Workflow Engines - Implements fault-tolerant process orchestration that persists state across crashes and automatic retries.
  • Optimistic Updates - Updates the user interface immediately before a backend process completes to improve perceived responsiveness.
  • Autonomous Agents - Starter kit for building virtual environments with social AI agents.
9,285 stars·975 forks·TypeScript·mit·69 views

Star history

Star history chart for a16z-infra/ai-townStar history chart for a16z-infra/ai-town

How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.

Projects sharing features with Ai Town

These projects share indexed features with Ai Town. Shared tags can include platform or build tooling; verify the primary use case before treating a result as a replacement.
  • get-convex/convex-backendget-convex avatar

    get-convex/convex-backend

    11,947View on GitHub↗

    Convex is a serverless backend platform that provides a real-time reactive database, serverless functions, and state synchronization for web applications. It manages relational JSON documents using ACID-compliant transactions and schema validation to ensure data consistency and integrity. The platform distinguishes itself by synchronizing database state with clients via WebSockets, allowing user interfaces to update automatically as data changes. It also includes a specialized vector search database for performing semantic search using embeddings and supports both cloud-native deployment and

    TypeScriptbackendconvexdatabase
    View on GitHub↗11,947
  • ravendb/ravendbravendb avatar

    ravendb/ravendb

    3,961View on GitHub↗

    RavenDB is a multi-model NoSQL document database designed for high-performance, ACID-compliant data storage. It persists structured information as schema-flexible JSON documents and utilizes a unit-of-work session pattern to track entity changes and batch modifications into atomic transactions. The platform is built on a distributed architecture that supports horizontal scaling through sharding and ensures high availability via multi-node, master-to-master cluster replication. The database distinguishes itself through a self-optimizing query engine that automatically creates and maintains ind

    C#csharpdatabasedocument-database
    View on GitHub↗3,961
  • geldata/gelgeldata avatar

    geldata/gel

    14,065View on GitHub↗

    Gel is an object-relational database system that models data as a graph of interconnected objects. By utilizing a strongly typed schema, it enables complex relational queries and polymorphic data structures without the need for traditional join tables. The system integrates native vector storage and similarity search operators, allowing it to function as both a relational and a vector database for semantic data retrieval. The platform distinguishes itself through a comprehensive suite of developer-centric automation tools. It features a declarative migration system that tracks and versions sc

    Pythondatabaseedgedbedgeql
    View on GitHub↗14,065
  • mastra-ai/mastramastra-ai avatar

    mastra-ai/mastra

    21,221View on GitHub↗

    Mastra is an orchestration framework designed for building, deploying, and managing autonomous AI agents and multi-agent systems. It provides a comprehensive suite of primitives for creating resilient AI applications, including durable workflow orchestration, event-driven agent loops, and semantic memory management. By integrating these core components, the platform enables developers to build complex, multi-step processes that can reason about goals and execute tasks without manual intervention. The framework distinguishes itself through its focus on observability and secure, isolated execut

    TypeScriptagentsaichatbots
    View on GitHub↗21,221
Compare all 30 related projects→

Frequently asked questions

What does a16z-infra/ai-town do?

AI Town is a TypeScript-based simulation engine used to create virtual environments where autonomous characters interact and socialize. It functions as a framework for orchestrating multiple AI agents within a persistent digital world, utilizing language models and a game engine to drive character behavior and social interactions.

What are the main features of a16z-infra/ai-town?

The main features of a16z-infra/ai-town are: Autonomous Agent Simulations, Autonomous AI Agent Simulations, Autonomous Agent Orchestration, LLM Application Development, LLM Provider Integrations, Data Change Subscriptions, Data Schema Definitions, Atomic Transactions.

Which projects share features with a16z-infra/ai-town?

Projects with overlapping indexed features include: get-convex/convex-backend — Convex is a serverless backend platform that provides a real-time reactive database, serverless functions, and state… ravendb/ravendb — RavenDB is a multi-model NoSQL document database designed for high-performance, ACID-compliant data storage. It… geldata/gel — Gel is an object-relational database system that models data as a graph of interconnected objects. By utilizing a… mastra-ai/mastra — Mastra is an orchestration framework designed for building, deploying, and managing autonomous AI agents and… firebase/quickstart-js — This project is a collection of reference implementations, sample code, and starter kits for integrating Firebase… redis/go-redis — This project is a feature-rich Go client library designed for interacting with Redis. It serves as a comprehensive…