#419 · Primary category: AI Coding Assistants
gemma-chat
Local AI chat + coding agent for Apple Silicon, powered by Gemma 4 via MLX / Supports Ollama
Project last updated:04/28/26
GitHub Stars
1.4K
Forks
259
Contributors
1
License
MIT
Why we included this project
Gemma Chat is a proof-of-concept for running a coding agent entirely offline on Apple Silicon. It's an Electron app that uses Google's Gemma 4 through Apple's MLX framework, so after a one-time model download you can describe an app and watch the model write out multi-file projects in HTML, CSS, and JavaScript with a live preview updating as it types. No API keys, no cloud calls, and no Wi-Fi once the model is on disk. A separate chat mode adds tool use for web search, URL fetching, a calculator, and bash, and voice input works through in-browser Whisper. The recommended model is about 3 GB, so the whole thing runs on a laptop. This is a working demo rather than a battle-tested production tool, but if your code and prompts should never leave your machine, or you often work where there's no signal, it's a useful place to start.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
superpowers
An agentic skills framework & software development methodology that works.
ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
skills
Skills for Real Engineers. Straight from my .agents directory.
opencode
The open source coding agent.
andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.