A lightweight CSS library
Unofficial local-first coding agent optimized for Gemma models.
gemma tokenizer for NodeJS/Browser
Core agent, model providers, and tools for the unofficial Gemma CLI coding agent.
Node.js package for Gemma 4 — local multimodal inference and agent system
Gemma model-family provider for Robota using OpenAI-compatible local endpoints
Gemma 4 agent reasoning loop with tool calling
On-device Gemma 4 contextual PHI redaction toolkit for HIPAA Safe Harbor de-identification. Runs locally via Ollama (browser WebLLM path wired for when MLC ships a Gemma 4 build). Never on a server.
CLI chat with Drexler, a corporate-executive AI persona built on OpenRouter Gemma 4 31B.
Browser-native, WebGPU-accelerated Gemma inference. Tiny SDK + React hook, zero server.
On-device AI for Expo apps — run Gemma 4, Apple Foundation Models, and ML Kit locally with zero API keys
React Native SDK for on-device AI agents powered by Google Gemma 4
Expo Modules bindings for Google AI Edge LiteRT-LM. On-device Gemma 4 / Gemma 3n inference with .litertlm and .task model formats. Companion to react-native-litert-lm (Nitro Modules).
OpenClaw provider plugin for Runware — unified OpenAI-compatible access to Claude, GPT, Gemini, Qwen, GLM, MiniMax, Kimi, and Gemma.
A TypeScript wrapper for the MediaPipe Gemma model
High-performance LLM inference for React Native using LiteRT-LM. Optimized for Gemma 4 and other on-device language models.
Gemma-first personal AI assistant, auto-configured for your hardware. Built on OpenClaw.
Gemma 4-powered AI agent world — local, offline, GPU-accelerated. Npx to launch.
Gemma open models for React Native
This is a module that will interface with [Gemma](https://blog.google/technology/developers/gemma-open-models/)'s [gemma.cpp](https://github.com/google/gemma.cpp). Its still a work in progress.
SDK oficial Syrus AI para Gemma 4 - Acesso via CLI e Integrações para VS Code e Antigravity
Offline authorization adapter for Google Gemma on-device AI agents
Terminal chat with Gemma via Ollama — auto-downloads the model on first run
A terminal-based AI CLI using Groq + Gemma
Model loading for RLX — config parsing, safetensors weights, graph builders
Board Support crate for the Adafruit Gemma M0
Gemma / Gemma 2 causal LMs for RLX
Gemma inference engine in rust
A voice-interactive AI assistant with multimodal capabilities
Rust ONNX inference library for Google's EmbeddingGemma (text embeddings)
A general-purpose CLI for chat models
Mechanistic interpretability for language models in Rust, built on candle
Semantic search and spatial navigation for Git repositories — map, get, and grep for AI coding agents
Multi-runtime GPU + remote inference as a supervised actor system on atomr. Single-crate rollup that re-exports per-runtime backends behind feature flags.
Model architecture implementations — LLaMA, Qwen3, Mistral, Gemma, Phi
Browser-resident Gemma 4 inference: pure Rust → WebAssembly + WebGPU. Loads Ollama's on-disk GGUF blobs and runs the forward pass on the local GPU via hand-written WGSL.
Gemma is a gem development helper like hoe and jeweler, but it keeps the gemspec in a gemspec file, instead of in a Rakefile. This helps your gem to play nicely with commands like gem and bundle, and it allows gemma to provide rake tasks with sensible defaults for many common gem development tasks.
GEMMA wrapper adds LOCO and permutation support. Also runs in parallel and caches K between runs with LOCO support
Gestione di varie operazioni come sincronia con le cartelle bindate dei container (rsync) up o down e possibilità di scaricare/caricare i file direttamente all'interno del cluster, in modo facilitato
Gemma per che raccoglie varie tipologie di classi di utilità varia che possono servire al funzionamento delle applicazioni e semplificare la vita al programmatore Rails
You can send an Email now.
Gemmate uses Bundler to identify an application's dependencies and opens them in TextMate for quick reference.
A Ruby port of mlx-lm providing large language model inference, quantization, LoRA fine-tuning, and an OpenAI-compatible server built on the mlx gem. Supports Llama, Gemma, Qwen2, Phi3, Mixtral, DeepSeek, and many more architectures.
A RubyLLM plugin that enables local LLM execution using the Red Candle gem. Run quantized GGUF models directly in Ruby without external API calls. Supports streaming, structured output, and multiple model architectures including Gemma, Llama, Qwen, Mistral, and Phi.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.