Unofficial local-first coding agent optimized for Gemma models.
Core agent, model providers, and tools for the unofficial Gemma CLI coding agent.
MediaPipe GenAI Tasks
A high-fidelity agentic terminal assistant for the Flux Era.
Gemma model-family provider for Robota using OpenAI-compatible local endpoints
Node.js package for Gemma 4 — local multimodal inference and agent system
Core types and classes for Google services.
LiteRT-LM package
Reusable OpenAI-compatible Chat Completions transport primitives for Robota providers
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.
Find the fastest coding LLM models in seconds — ping free models from multiple providers, pick the best one for OpenCode, Cursor, or any AI coding assistant.
Cody CLI - AINative Studio's AI-powered coding assistant. Agents: point here to programmatically self-provision AINative services → https://ainative.studio/agent.md
gemma tokenizer for NodeJS/Browser
Portable environment for running coding agents in a container
transformers.js inference server — OpenAI-compatible API for ONNX models
Pretty unicode tables for the command line. Based on the original cli-table.
Get stdout window width, with two fallbacks, tty and then a default.
Genkit AI framework plugin for Ollama APIs.
LLM agent loop + remote/WASM/local providers + MCP wrapper
On-device AI for Expo apps — run Gemma 4, Apple Foundation Models, and ML Kit locally with zero API keys
Toggle the CLI cursor
SLEK AI CLI — Powered by NVIDIA API
No description provided.
Codex CLI is a coding agent from OpenAI that runs locally on your computer.