HackerReposA FIELD GUIDE TO OPEN SOURCE
ProSponsor the shelf♧ 0
← Back to top all-time
a16z-infra
ai-town
TypeScript2023–2024
a16z-infra / ai-town

ai-town

A MIT-licensed, deployable starter kit for building and customizing your own version of AI town - a virtual town where AI characters live, chat and socialize.

AI & Machine LearningCommunication & Social
Explore on GitHubRead Hacker News discussions
6Distinct people
9Mentions
0Explicit recommenders
10.8KGitHub stars
REPOSITORY AT A GLANCE

What to know before exploring

What it is

A MIT-licensed, deployable starter kit for building and customizing your own version of AI town - a virtual town where AI characters live, chat and socialize.

GitHub

Where it is used

No documented product use has been verified yet.

What people are saying

No recommendation phrase was found in the indexed comments.

No classified warning is attached to this page. Read the discussions before treating silence as approval.

Also in these discussions

No other repository is repeatedly linked in the same discussions.

This week on Hacker News

Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 5:04:57 PM UTC.

No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.

Mentions over time

HN mentions by month9 dated mentions

Observed mentions: 2023-08-14 23:46:02 UTC to 2024-12-31 20:07:27 UTC.

01232023-08-01 00:00:00 UTC to 2023-09-01 00:00:00 UTC (exclusive): 3 mentions; 2 submissions, 1 commentsAug 20232023-09-01 00:00:00 UTC to 2023-10-01 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 comments2023-10-01 00:00:00 UTC to 2023-11-01 00:00:00 UTC (exclusive): 1 mentions; 1 submissions, 0 comments2023-11-01 00:00:00 UTC to 2023-12-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-12-01 00:00:00 UTC to 2024-01-01 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 comments2024-01-01 00:00:00 UTC to 2024-02-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2024-02-01 00:00:00 UTC to 2024-03-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2024-03-01 00:00:00 UTC to 2024-04-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2024-04-01 00:00:00 UTC to 2024-05-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 commentsApr 20242024-05-01 00:00:00 UTC to 2024-06-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2024-06-01 00:00:00 UTC to 2024-07-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2024-07-01 00:00:00 UTC to 2024-08-01 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 comments2024-08-01 00:00:00 UTC to 2024-09-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2024-09-01 00:00:00 UTC to 2024-10-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2024-10-01 00:00:00 UTC to 2024-11-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2024-11-01 00:00:00 UTC to 2024-12-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2024-12-01 00:00:00 UTC to 2025-01-01 00:00:00 UTC (exclusive): 2 mentions; 0 submissions, 2 commentsDec 2024

Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.

View mention counts and date ranges
UTC ranges include their start and exclude their end. Select a period to filter the source evidence.
PeriodStart (UTC)End (exclusive, UTC)MentionsSubmissionsComments
Aug 20232023-08-01 00:00:00 UTC2023-09-01 00:00:00 UTC321
Sep 20232023-09-01 00:00:00 UTC2023-10-01 00:00:00 UTC101
Oct 20232023-10-01 00:00:00 UTC2023-11-01 00:00:00 UTC110
Nov 20232023-11-01 00:00:00 UTC2023-12-01 00:00:00 UTC000
Dec 20232023-12-01 00:00:00 UTC2024-01-01 00:00:00 UTC101
Jan 20242024-01-01 00:00:00 UTC2024-02-01 00:00:00 UTC000
Feb 20242024-02-01 00:00:00 UTC2024-03-01 00:00:00 UTC000
Mar 20242024-03-01 00:00:00 UTC2024-04-01 00:00:00 UTC000
Apr 20242024-04-01 00:00:00 UTC2024-05-01 00:00:00 UTC000
May 20242024-05-01 00:00:00 UTC2024-06-01 00:00:00 UTC000
Jun 20242024-06-01 00:00:00 UTC2024-07-01 00:00:00 UTC000
Jul 20242024-07-01 00:00:00 UTC2024-08-01 00:00:00 UTC101
Aug 20242024-08-01 00:00:00 UTC2024-09-01 00:00:00 UTC000
Sep 20242024-09-01 00:00:00 UTC2024-10-01 00:00:00 UTC000
Oct 20242024-10-01 00:00:00 UTC2024-11-01 00:00:00 UTC000
Nov 20242024-11-01 00:00:00 UTC2024-12-01 00:00:00 UTC000
Dec 20242024-12-01 00:00:00 UTC2025-01-01 00:00:00 UTC202

What Hacker News says

9 sources
vunderba·Dec 31, 2024
It sounds very similar to AI town - there's been a couple attempts at building virtual playgrounds for chatbots to interact with each other, and vote on solutions if they're trying to come up with a consensus. In that respect, it's probably similar to how mixture of experts work but just modeled at a higher level. https://github.com/a16z-infra/ai-town The big thing that you want though is diversity in terms of each of the AI's, and I'm not convinced that altering temperature / system context prompt / optional backing RAG represents sufficient variety from virtual bot to virtual bot. Ideally, you would want to throw as many different LLMs (Llama, Mistral, Qwen, etc.) into the mix as possible, but hardware constraints make this borderline impossible.
In Agentarium: Creating social simulations with AI Agents
ykhli·Oct 31, 2023Submission

Show HN: JS Local-only AI Apps starter kit: cost $0 to run and test locally

Hi HN! Here's a local-only stack I built over the weekend - hope it can be useful for you! I have been building a lot of AI apps - https://github.com/a16z-infra/ai-town https://github.com/a16z-infra/companion-app ... And there were definitely times I spent way too much $$ before deploying the app to production. So I was looking for a "local only" stack and found a few tools that worked well together. I used the following set of tools but may add more options later: - Inference: Ollama - VectorDB: Supabase pg-vector - LLM orchestration: langchain - Framework: nextjs My learning from building ai-town was also that many people don't have the luxury of swiping a credit card to test an app with a lot of AI workloads -- not surprisingly, many models on Ollama are already very good - I used llama2-7b for majority of my dev work. Hope this can lo
Read the rest
wer the barrier to entry for building AI apps. :)
11 points · Open discussion
tetris11·Sep 11, 2023
If the surge of indie game popularity has shown anything, it's that games can be 8-bit hot pixellated messes but still touted as visual masterpieces as long as there's a decent global lighting engine somewhere in the mix. I think, as you say, AI will be the next paradigm for gamers, and having specialised chips on these GPUs that can turn a scripted NPC story-based interaction into a do-what-you-want-under-these-contraints a la "AI town"[1] might keep them in business a little longer before they have to start upping the visuals again. 1: https://github.com/a16z-infra/ai-town
In Graphics card generation is over and it was mostly trash
broken_clock·Aug 24, 2023Submission

Show HN: eastworld – quickly add generative agents to games, visual novels, etc.

Hi HN, We’re Michael and Scott and we’re releasing an open-source, language-agnostic framework to create, debug, and serve Generative Agents. This project has two main goals: - to abstract away the complexities of prompt-engineering detailed Agents and elaborate Storylines with an easy to use no-code dashboard - using dashboard output, expose powerful functionalities - Agent Actions, Emotion Queries, Player Guardrails, etc. - in a simple small API & server We have a demo game that we made (https://github.com/game-kings/detective), and a demo video (https://www.youtube.com/watch?v=VSqIzjOk5p4). The demo game is a murder mystery set in Gold Rush era San Francisco. It includes a somewhat novel scoring mechanism at the end where your ability as a detective is scored based on cosine similarity between the embeddings of your explanation and
Read the rest
ours. We showed this to some friends of ours and, despite it frankly being an extremely hacked together game, they thought it surprisingly fun. This makes us really excited for what kinds of games are possible with tools like this. We know there’s some similar prior art in this category but we think this still has a lot to offer. The open-source work like GPTeam (https://github.com/101dotxyz/GPTeam) or ai-town (https://github.com/a16z-infra/ai-town) is mostly geared towards recreations of the Sims, and are not as general purpose as our framework. There are commercial offerings like InworldAI, but I think our framework exists in a different space - we support Local AI out of the box, and hope this is the direction that gaming goes in. I don’t really want to start paying a subscription for every single-player game in the future. While we wait for chips to get cheaper and open-source models to get better, using GPT-3.5 or GPT-4 produces pretty similar if not better results than commercial offerings. Of course, our project isn't perfect, isn’t feature-complete and definitely isn’t polish-complete. After showing it to our friends, we realized we need release early to get early feedback from others. We want to make this great and empower open-source LLM gaming in the future. We would love to hear your feedback. We know for sure that some of you are much more creative storytellers than we are, and we can’t wait to see what you come up with! Have fun!
4 points · Open discussion
ykhli·Aug 14, 2023Submission

Show HN: AI-town, run your own custom AI world SIM with JavaScript

Hi HN community! We want to share AI-town, a deployable starter kit for building and customizing your own version of AI simulation - a virtual town where AI characters live, chat and socialize. Inspired by great work from the Stanford Generative Agent paper (https://arxiv.org/abs/2304.03442). A few features: - Includes a convex.dev backed server-side game engine that handles global state - Multiplayer ready. Deployment ready - 100% Typescript - Easily customizable. You can fork it, change character memories, add new sprites/tiles and you have a custom AI simulation The goal is to democratize building your own simulation environment with AI agents. Would love to see the community build more complex interactions on top of this. Let us know what you think! Demo: https://www.convex.dev/ai-town I made a world Cat Town to demonstrate how to cu
Read the rest
stomize AI town. Using C(h)atGPT :) Demo: https://cat-town.fly.dev/ Code: https://github.com/ykhli/cat-town
429 points · Open discussion

MAKE YOURSELF AT HOME

A few shortcuts

/
Search the collection
?
Open this guide
Esc
Close dialogs and navigation

Your saved repositories and interests stay in this browser.