# ammaarreshi/gemma-chat

Local AI chat + coding agent for Apple Silicon, powered by Gemma 4 via MLX / Supports Ollama

Repository: https://github.com/ammaarreshi/gemma-chat
Canonical: https://ross.abutalabs.com/products/gemma-chat
Language: TypeScript
License: MIT
License Family: permissive
Last push: 2026-04-28T19:56:12+00:00

## Health v2 (maintenance only)
Score: 50/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 79, release rhythm 35, longevity 9
- inputs: {"age_days": 136, "days_push": 127, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1424, forks 258 (observed 2026-08-28T04:04:41.338245+00:00)

## What it is
An open-source Electron app that runs Google's Gemma 4 models locally on Apple Silicon via Apple's MLX framework, providing a chat interface and a coding agent with live preview. It works fully offline after the initial model download and also supports Ollama.

## Use cases
- run a local ai chatbot on my mac without api keys
- vibe code offline with a local llm
- generate html css javascript projects with a local coding agent
- chat with gemma on apple silicon
- keep my code and prompts private on my own machine
- use voice input with local speech-to-text
- switch between local llm models on the fly

## When to choose
- you have an Apple Silicon Mac and want fully offline LLM chat and code generation
- privacy matters and you don't want code sent to cloud servers
- you want a zero-config local model setup with live preview while coding
- you want a lightweight open model (~3 GB) instead of paid API access

## When to avoid
- you need frontier-level coding quality from large cloud models
- you're on Windows, Linux, or non-Apple-Silicon hardware
- you need team collaboration or cloud sync features
- you don't have RAM/disk for multi-GB local models

## Facets
- artifact type: application
- maturity: active
- function: llm-inference, chatbot, agent-framework, speech-recognition, chat-interface
- domain: large-language-models, artificial-intelligence, developer-tools, privacy, self-hosted
- platform: python
- tags: local-first, offline-ai, apple-silicon, mlx, gemma, vibe-coding, coding-agent, ollama, macos, electron, desktop, typescript

## Member repositories
- ammaarreshi/gemma-chat (main) score 50

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:41.338245+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:37:34.057124+00:00, confidence not recorded.
  - readme: https://github.com/ammaarreshi/gemma-chat (fetched 2026-08-28T04:04:41.338245+00:00, sha 554fa8428320)
- Data as of 2026-08-30T08:39:29.467469+00:00.