juliensimon

Arcee Demos

Name: Arcee Demos
Author: juliensimon

AI community

SOURCE https://github.com/juliensimon/arcee-demos

Description

A collection of demos, examples, and tools for using Arcee AI models and services across various platforms and use cases.

Installation

This entry records only its repository, not the path inside it, so there is no exact command to give. Open the source below and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

README

Arcee AI Demos: Deploy, Fine-Tune, and Evaluate Small Language Models

[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT) [![Python 3.8+](https://img.shields.io/badge/python-3.8+-blue.svg)](https://www.python.org/downloads/) [![Arcee AI](https://img.shields.io/badge/Arcee-AI-purple)](https://arcee.ai) [![Conductor](https://img.shields.io/badge/Conductor-API-green)](https://conductor.arcee.ai)

Hands-on examples for deploying, evaluating, and optimizing [Arcee AI](https://arcee.ai) language models — including the Trinity model family, AFM, Virtuoso, and more — across AWS, Intel, Apple Silicon, and cloud API platforms.

Whether you're looking to run LLMs locally on a MacBook, deploy on AWS SageMaker, benchmark model quantizations, or build RAG applications, this repository has a working demo for you.

Repository Structure

Demo	Description
trinity-mini	Build a transparent reasoning chatbot with Arcee Trinity Mini on OpenRouter
trinity-mini-mlx	Run Trinity Mini locally on Apple Silicon with MLX — no cloud, no API keys
conductor-rag	Retrieval-Augmented Generation (RAG) document Q&A app with Arcee Conductor
conductor-ab-testing	A/B testing tool for comparing LLM responses with semantic similarity metrics
data-enrichment	AI-powered medical equipment metadata enrichment with Arcee AFM-4.5B
together-ai	Domain-specific LLM benchmarking with radar charts via Together.ai
sagemaker	Deploy Arcee models on AWS SageMaker (CPU, GPU, vLLM)
inferentia2	Run Arcee models on AWS Inferentia2 custom AI accelerators
openvino-lunar-lake	Optimize and run models on Intel Lunar Lake with OpenVINO
[openvino-granite-rapids](./