Amara
Our most capable open multimodal models
Our most advanced open models help developers create AI applications that run wherever users need them — from cloud servers to laptops and even phones.
import React from 'react';
import { SabiPTProvider, useModel } from '@sabipt/sdk';
// SabiPT Afro-Multimodal Engine
const config = {
models: ['amara', 'oruko', 'kikuyu', 'zouk'],
languages: ['yr', 'ig', 'ha', 'pcm', 'sw'],
streaming: true,
};
// Synthesize audio & visual streams
export const App = () => (
<SabiPTProvider config={config}>
<MultimodalWorkspace />
</SabiPTProvider>
);
WhywebuiltSabiPTSabiPT
Introducing SabiPT
Frontier-level capabilities and mobile-first AI
Maximum compute and memory efficiency
A new level of intelligence for mobile and IoT devices
Multimodal Native
Processes text, code, audio, and vision input natively with low-latency streaming.
Official variants
DiffusionSabiPT
A text diffusion model designed to maximize generation speed
T5SabiPT
Flexible encoder-decoder models that excel at deep contextual understanding
Code SabiPT
State-of-the-art open code generation, editing, and reasoning model.
ShieldSabiPT 2
A modular classifier model for detecting policy-violating content and upholding safety standards
Build AI that helps people
From cutting-edge techniques to personalized models, discover how developers are using SabiPT open models
Democratizing AI with offline access
Lentera runs an offline AI microserver for educators and students
Developing sovereign AI
Crane AI Labs improves Swahili language understanding in a lightweight model
Unlocking interspecies communication
Marine biologists and AI engineers partnered to develop DolphinSabiPT
Get started with SabiPT
Platforms and integrations
Developer resources
Official documentation, quickstarts, and guides to build applications with SabiPT
Get support
Ask questions on the developer forum