
Repository for creating AI bots in VRChat
Description in other languages
Statistics
Statistics as of Nov 17, 2026
GitHub stars
30
±0 (Oct 13〜)
Last commit
Dec 2022
Created on GitHub
Dec 10, 2022
Listed
Apr 1, 2023
Stars over time
Show as a table
| Month | Stars |
|---|---|
| Dec 2025 | 28 |
| Jan 2026 | 28 |
| Feb 2026 | 28 |
| Mar 2026 | 29 |
| Apr 2026 | 29 |
| May 2026 | 30 |
| Jun 2026 | 30 |
| Jul 2026 | 30 |
| Aug 2026 | 30 |
| Sep 2026 | 30 |
| Oct 2026 | 30 |
| Nov 2026 | 30 |
Last snapshot of each month. Star counts of 1,000 or more are rounded to the nearest 100.
Popular in the same category
ChatdollKituezo1.3kChatdollKit enables you to make your 3D model into a chatbot
chatvrmpixiv848ChatVRM is a demo application that allows you to easily chat with 3D characters in your browser.
aiavatarkituezo704Building AI-based conversational avatars lightning fast
generativeai-prompt-sample-japanesedahatake441Sample prompts for various generative AIs such as ChatGPT and Copilot in Japanese.
jp-azureopenai-samplesazure-samples278We provide free samples of applications (reference architecture, sample code, and deployment instructions) for the purpose of implementing applications using Azure OpenAI.
summarize_arxvrkmt173Summarize arXiv paper with figures
Resources in similar research fields
- llm-jp-4-8b-instructllm-jp49kllm‑jp‑4‑8b‑instruct is a 4.1 B‑parameter Japanese LLM from NII’s LLM‑jp‑4 series, pretrained on large corpora and then fine‑tuned solely with supervised instruction data (no DPO/REINFORCE) and accompanied by cookbook‑style usage guides and a byte‑fallback unigram tokenizer.HF modelShared: Text Generation・Language Models
- llm-jp-4-8b-basellm-jp11kA repository that hosts the 8.6 B‑parameter llm‑jp‑4‑8b‑base transformer from the National Institute of Informatics’ LLM R&D Center, trained with pre‑training and mid‑training followed by supervised fine‑tuning and direct preference optimization (no reinforcement learning), and provides a PyTorch‑transformers usage guide.HF modelShared: Text Generation・Language Models
- LFM2.5-1.2B-JP-202606-GGUFLiquidAI8kHybrid LFM2 models from Liquid AI, such as the 1.2 B Japanese GGUF version, deliver high‑quality, fast, and memory‑efficient edge AI for on‑device deployment and can be run locally with llama.cpp via the Hugging Face repo.HF modelShared: Text Generation・Language Models
- Llama-3.1-Swallow-8B-Instruct-v0.5tokyotech-llm7kLlama 3.1 Swallow is a set of 8‑B and 70‑B models that continue pre‑training Meta’s Llama 3.1 to boost Japanese language performance, then instruction‑fine‑tune on synthetic Japanese data—providing multiple released variants with improved conversational behavior comparable to gemma‑3‑27b‑it.HF modelShared: Text Generation・Language Models
- Mistral-Nemo-Japanese-Instruct-2408cyberagent6kA Japanese continually‑pre‑trained Mistral‑Nemo model (Mistral‑Nemo‑Japanese‑Instruct‑2408) built on mistralai/Mistral‑Nemo‑Instruct‑2407, usable via transformers with device mapping and ChatML prompts, released under Apache‑2.0 by Ryosuke Ishigami.HF modelShared: Text Generation・Language Models
- Qwen3-Swallow-8B-RL-v0.2tokyotech-llm5kQwen3‑Swallow v0.2 delivers Japanese‑English LLMs (30B‑A3B and 32B) trained via CPT, SFT and RLVR, preserving strong math, coding, and reasoning abilities, with nine released models and AWQ‑quantized variants.HF modelShared: Text Generation・Language Models