TypeScript multi-agent framework — one runTeam() call from goal to result. Auto task decomposition, parallel execution. 3 dependencies, deploys anywhere Node.js runs.

A powerful Zotero AI and MCP plugin with ChatGPT, Gemini 3.1, Claude, Grok, DeepSeek, OpenRouter, Kimi 2.5, GLM 5, SiliconFlow, GPT-oss, Gemma 4, Qwen 3.5

Gemma Gem runs Google's Gemma 4 model entirely on-device via WebGPU — no API keys, no cloud, no data leaving your machine.

PokeClaw (PocketClaw) — first on-device AI that controls your Android phone. Gemma 4, no cloud, no API key. Poke is short for Pocket.

Local AI desktop app — chat, agent mode, image gen, video gen. Supports Ollama, Gemma 4, Llama, Qwen, OpenAI, Anthropic. Single .exe, no Docker.

Interactive CLI for creating & running multiple agents across CLI, Slack & WhatsApp; 100% local, thanks to Ollama & Gemma 4

A C# inference engine for running large language models (LLMs) locally using GGUF model files. TensorSharp provides a console application, a web-based chatbot interface, and Ollama/OpenAI-compatible HTTP APIs for programmatic access.

LiteRT-LM for .NET

The YAML standard for AI agent governance. Write rules once, compile to any runtime. Deterministic. Sub-microsecond. Three templates: enterprise, DAO, AI safety. Seven governance laws.

100-question benchmark comparing proprietary (2025) and open-source (2026) LLMs.

Awesome Gemma 4

Go TurboQuant using GoMLX (Work in Progress)

Ollamaベースの、Gemma 4を使用したAIマルチエージェント議論プラットフォーム。

Three-tier Gemma 4 local inference on Mac Mini M4 — MLX + llama.cpp + Tailscale

Chrome extension that uses the built-in Gemini Nano model (Gemma 3n / Gemma 4 E2B / E4B) to automatically organize your bookmarks — a proof-of-concept for Chrome's on-device Prompt API

gemma-4-e2b-it-Q8_0+claude code超简易AI对话网页

PowerShell demo for sending VOICEVOX-generated WAV audio to gemma4:e2b via Ollama

🧪 70-test, 6-model AI benchmark: Gemma 4 vs Gemini Pro vs Flash vs Qwen. 420 verified runs across 13 categories. All prompts, rubrics, runner code & raw results included. Code executed, constraints verified, prompt injection confirmed on Vertex AI Studio.

Document (Text, PDF, Office, HTML) summarizer using MLX and Gemma4 on Apple Silicon hardware

Fast Gemma 4 inference in pure Java