Awesome Godot
Section: Plugins and scripts · Local large language models (LLMs) for "AI-powered" NPC dialogue.
Entry
Appears in 5 awesome lists
On-device LLM inference engine that embeds directly in games and apps with no server or API key. Supports streaming generation, embeddings, GBNF grammar-constrained structured output, and Whisper speech-to-text, with bindings for Godot, Flutter, React Native, and Swift.
Section: Plugins and scripts · Local large language models (LLMs) for "AI-powered" NPC dialogue.
Section: Large Model Serving · On-device LLM inference engine (Rust / llama.cpp) to embed local models directly in games and apps, with Godot / Flutter / React Native / Swift bindings; streaming, embeddings, tool calling, GBNF-structured output, and STT/TTS.
Section: Python · The simplest way to run an LLM locally. Supports tool calling and grammar constrained sampling.
Section: Deployment and Serving · NobodyWho is an on-device LLM inference engine written in Rust on top of llama.cpp, running GGUF models locally with no API key or network call, with bindings for Flutter, React Native, Swift, Kotlin, Python and Godot.
Section: Artificial Intelligence · On-device LLM inference engine that embeds directly in games and apps with no server or API key. Supports streaming generation, embeddings, GBNF grammar-constrained structured output, and Whisper speech-to-text, with bindings for Godot, Flutter, React Native, and Swift.
How to use the Hexagon Delegate to speed up model inference on mobile and edge devices. Also see blog post Accelerating TensorFlow Lite on Qualcomm Hexagon DSPs.
Comet's open-source AI observability and evaluation platform: deep tracing of LLM calls, conversation logging, and agent activity, plus built-in eval metrics, prompt versioning, guardrails, and the Opik Agent Optimizer. Worth including because it unifies observability, verification, and…
(label: good first issue) PyTorch is an open source machine learning library based on the Torch library, used for applications such as computer vision and natural language processing.
(formerly known as pytorch-transformers and pytorch-pretrained-bert) provides state-of-the-art general-purpose architectures (BERT, GPT-2, RoBERTa, XLM, DistilBert, XLNet, CTRL...) for Natural Language Understanding (NLU) and Natural Language Generation (NLG) with over 32+ pretrained models in…
A fast and simple framework for building and running distributed applications. Ray is packaged with RLlib, a scalable reinforcement learning library, and Tune, a scalable hyperparameter tuning library. ray.io
(from Hpcaitech) - A Unified Deep Learning System for Large-Scale Parallel Training (1D, 2D, 2.5D, 3D and sequence parallelism, and ZeRO protocol).
Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search,…