LLM-powered NPCs running on your hardware
Hey HN, My team is open-sourcing the inference stack and fined-tuned models we use to create LLM-powered NPCs: https://github.com/GigaxGames/gigax The generative agents paper [1] pioneered the idea of prompting LLMs to create autonomous NPCs. But existing implementations require multiple calls to an LLM to make the agent plan its day, chat with people, and interact with its environment [2]. Our approach allows NPCs to be stepped at runtime with a single pass on consumer-grade hardware, with reasonable latency. To achieve this, we've fine-tuned open-source LLMs [3] to…
LLM-powered NPCs running on your hardware launched on April 30, 2024 with 24 votes, #805 of 4,347 launches that month and more than 75% of that year's launches. The site was still online in September 2026, 2 years on.
In plain words
Gigax Games has open-sourced an inference stack and fine-tuned language models for creating NPCs that run on consumer hardware. The system enables autonomous non-player characters to plan their day, interact with environments, and chat with players using a single inference pass rather than multiple API calls. Developers can deploy these LLM-powered agents with reasonable latency by using custom function-calling formats optimized for speed, making it practical for game development without requiring high-end server infrastructure.
written from the facts on this page · September 2026
From the sources
LLM-powered NPCs running on your hardware. Contribute to GigaxGames/gigax development by creating an account on GitHub.
In the maker’s words, at launch
Hey HN, My team is open-sourcing the inference stack and fined-tuned models we use to create LLM-powered NPCs: https://github.com/GigaxGames/gigax The generative agents paper [1] pioneered the idea of prompting LLMs to create autonomous NPCs. But existing implementations require multiple calls to…
Does a similar job
all alternatives →
I built a tiny LLM to demystify how language models workApr 2026 · github.com · ▲915Built a ~9M param LLM from scratch to understand how they actually work. Vanilla transformer, 60K synthetic conversations, ~130 lines of PyTorch. Trains in 5 min on a free Colab T4. The fish thinks the meaning of life is food. Fork it and swap the personality for your own character.
Getting GLM 5.2 running on my slow computerJul 2026 · github.com · ▲937A few days ago I found myself trying out GLM 5.2 and was really positively impressed. The capabilities and security I was getting from this LLM are similar to those I've gotten from models like Claude or GPT, and this really surprised me. But then I thought, "I wonder how it would work on a normal computer like mine," and above all, "I wonder if it would work without going into OOM on a computer like mine." So I started working with the help of agents to test this possibility. I started converting the model to int4, understanding MTP usage, and if possible implementing DSA for long context.…
AI-town, run your own custom AI world SIM with JavaScript2023 · github.com · ▲429Hi 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…
Agent M - Powered by Floatbot.AI2023 · floatbot.ai · ▲268Generative AI powered Master Agent Developer Framework
Smallville – Create generative agents for simulations and games2023 · github.com · ▲112Smallville can be used to create NPCs with the same level of realism as human players without having to pre-program interactions. The agents store and retrieve past memories which they use to create plans so they can decide where to move, what to say, and how to react to observations. Agents are also capable of interacting with the world around them to change the state of objects on their own. This project was intended to make it easy for anyone to create custom simulations and my attempt to recreate Generative Agents: Interactive Simulacra of Human Behavior. I’ve been working on Smallville…
TERMy – A fast terminal assistant that does not use LLMsSep 2026 · github.com · ▲225NPC-Forge is a framework for building conversational agents that run on the CPU without relying on machine learning or LLMs. - NPC-Forge/docs/development.md at main · gioblu/NPC-Forge
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 20d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 29d ago · world.pixverse.video
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, April 2024
the whole month →
Supabase▲2,325The Postgres developer platform is now generally available
Dev tools · 2024 · supabase.com
Cal.com Platform▲1,601Build your pixel-perfect booking experience with Atoms
Dev tools · 2024 · cal.com
deco.cx 2.0▲1,078Build web apps 10x faster with Deno, JSX, TS & Tailwind
Dev tools · 2024 · decocms.com
