Alternatives
Products that do what Distil-NPC: a family of models for non-playable characters in games does
we finetuned Google's Gemma 270m (and 1b) small language models specialized in having conversations as non-playable characters (NPC) found in various video games. Our goal is to enhance the experience of interacting in NPSs in games by enabling natural language as means of communication (instead of single-choice dialog options).
- 1IB
Built 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.
Apr 2026 · github.com
- 2DA
2025 · github.com
- 3
NPC-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
2d ago · github.com
- 4CY
May 2026 · llmgame.scalex.dev
- 5
- 6
- 7NE
Hey! I built this system to humanize NPCs by giving them emotions using Rust and ML. The system provides emotion coordinates (based on Russell's circumplex model) from text input or actions, with persistent emotional memory per entity. Think NPCs that remember how they feel about specific players or events. I pre-trained a DistilBERT model on ~1k video game dialogues (Skyrim, Cyberpunk, etc.) and plan to extract and evaluate 100k+ dialogues soon. However studio/team can manually add dialogues to enrich their own dataset. The matrix doesn't generate dialogue, it only analyzes content.…
Sep 2025 · github.com
- 8IW
I grew up on the Infocom games and when microsoft actually open-sourced Zork 1/2/3 I really wanted to figure out how to use LLMs to let you type whatever you want, I always found the amount language that the games "understood" to be so limiting - even if it was pretty state of the art at the time. So I figured out how to wrap it with Tambo.. (and run the game engine in the browser) basically whatever you type gets "translated" into zork-speak and passed to the game - and then the LLM takes the game's output and optionally adds flavor. (the little ">_" button at the top exposes the…
Jan 2026 · infocom.tambo.co
- 9EC
For the past 3 years, I've been creating a new 2D game programming language where the multiplayer is completely automatic. The idea is that someone who doesn't even know what a "remote procedure call" is can make a multiplayer game by just setting `maxHumanPlayers=5` and it "just works". The trick is the whole game simulation, including all the concurrent threads, can be executed deterministically and snapshotted for rollback netcode. Normally when coding multiplayer you have to worry about following "the rules of multiplayer" like avoiding non-determinism, or not modifying entities your…
2025 · easel.games
- 10NA
I built over the last two years a human-like neural network chess engine that tries to predict your rating from a single game. It automatically adapts to your play and tries to play like a human at your level would play, giving you a balanced game. At the core I’m using an AlphaZero / Leela Chess Zero style neural network that I have trained on 1 billion human games from the lichess.org open database. Around this network I have built a chess engine in Rust with algorithms that use the outputs from the NN to produce human-like moves at a given rating from beginner to world champion, as…
2022 · noctie.ai
- 11SA
After many months of development, we are releasing Squally as early-access on Steam! This game teaches low-level computer science; topics such as data types, data structures, bin/dec/hex, and x86 assembly are gradually introduced through puzzles and gameplay. https://store.steampowered.com/app/770200/Squally/ It's still very early in development, we currently have only released a card mini-game that teaches binary operations: https://i.gyazo.com/0a33bbac5bbb5421f7eb120edd3ff6bb.gif
2018
- 12LP
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…
2024 · github.com
- 13DO
I just released a free demo (no login!) for "Talk to Me Human", a game about social persuasion. You speak out loud to play a variety of conversational challenges, and the NPCs talk back. I hope you enjoy, and would love to get your feedback!
2024 · talktomehuman.com
- 14LG
2020 · github.com
- 15
- 16
- 17RR
2023 · rpg-gpt.vercel.app
- 18AT
2024 · s3-eu-west-1.amazonaws.com
- 19NC
2023 · flippit.ai
- 20SG
Hi everyone! Want to share something I'm working on. Here is the brief description: From a single text prompt, craft dynamic worlds (both fictional and real-life, of any kind) filled with interacting NPCs pursuing goals, and control (human-in-the-loop) their behaviour and world state in real-time. Text-to-image to visualise every single step of change in the world's and NPC's state. My main goal was to check if it's possible to use LLMs (GPT-4 currently) to make characters interact with each other but in the end, it ended up with a neat little app where users can interfere with NPC's (and…
2024 · github.com
- 21IR
The Emotion Engine has 32 MB of RAM total, so the trick is streaming weights from CD-ROM one matrix at a time during the forward pass — only activations, KV cache and embeddings live in RAM. This means models bigger than the RAM can still run, they just read more from disc. Had to build a custom quantized format (PSNT), hack endianness, write a tokenizer pipeline, and most of the PS2 SDK from scratch (releasing that separately). The model itself is also custom — a 10M param Llama-style architecture I trained specifically for this. And it works. On real hardware.
Mar 2026 · github.com
- 22MR
Hey HN! We’ve just open-sourced model2vec-rs, a Rust crate for loading and running Model2Vec static embedding models with zero Python dependency. This allows you to embed text at (very) high throughput; for example, in a Rust-based microservice or CLI tool. This can be used for semantic search, retrieval, RAG, or any other text embedding usecase. Main Features: - Rust-native inference: Load any Model2Vec model from Hugging Face or your local path with StaticModel::from_pretrained(...). - Tiny footprint: The crate itself is only ~1.7 mb, with embedding models between 7 and 30 mb. Performance:…
2025 · github.com
- 23AE
2025 · github.com
- 24AM
Hi, I’ve been working on Artifacts for the past 2 years, and it’s now ready to try. It’s a sandbox MMORPG where every action is done through a REST API. Instead of clicking to move, fight, gather, craft, or trade, you write code to control your characters. If you have any questions, comments, or feedback, I’d be happy to hear them.
Jun 2026 · artifactsmmo.com
Ranked by how close each launch is in meaning, then by votes. Refine with a description →