DeGirum

Visit Tool

DeGirum is an AI development platform that simplifies edge AI adoption. It offers a hardware-agnostic PySDK and AI Hub for model management and deployment, along with Orca hardware accelerators.

Claim this tool

3Views

At a glance

Pricing

Freemium · Paid · Usage-based · Enterprise

Free tier

Yes

API

Yes

Skill level

Technical

About

What is DeGirum?

DeGirum provides comprehensive AI solutions designed to simplify the development, deployment, and scaling of edge AI applications. Its core offerings include PySDK, a unified Python API for running inference across various hardware accelerators, and AI Hub, which facilitates cloud model management and deployment workflows. The platform also features a Cloud Compiler for optimizing and porting models, and Orca AI Hardware Accelerators to maximize performance for edge AI. DeGirum supports a range of pre-trained models and offers application packages like Face Recognition and Speech Transcription, making it easier for developers to integrate AI into their applications across diverse edge devices.

Best used for

Ideal for developers and data scientists who need to build, deploy, and scale AI applications on edge devices. Especially valuable for those requiring hardware-agnostic model deployment, cloud-based model management, and performance optimization for edge AI workloads.

Common actions

deploy AI models

optimize edge AI

manage AI models

develop AI applications

run AI inference

Capabilities

Key features

Unified Python API
Cloud model management
Hardware accelerators
Model optimization
Pre-trained models
Application packages
Edge AI deployment

Target Audience

developerdata scientiststartup founder

Integrations

github

Pricing & Plans

Freemium · Paid · Usage-based · Enterprise

Not publicly disclosed. Check degirum.com for current pricing.

FAQs

What is a PySDK local runtime?

A PySDK local runtime enables models to run locally on various accelerators or vendor runtimes, offering higher performance, lower latency, or on-device processing compared to the default CPU path. It supports runtimes like HAILORT, DEEPX, OPENVINO, AXELERA, MEMRYX, AKIDA, and RKNN.

How is Cloud Compiler billed?

Cloud Compiler is billed per successful compile at $4.99 on Professional and Enterprise plans. A successful compile is defined as a task that finishes with a 'Success' status, produces a valid compiled output artifact, and is available for use or download. Failed compiles are not billed.

What happens if I hit my monthly AI Hub inference limit?

If you reach your monthly AI Hub inference limit, you can upgrade to a higher plan to get more included inferences. Otherwise, inferences will pause until the next billing cycle begins. This ensures you maintain control over your usage and costs.

Trending

Subcategories trending in Coding & Development

Open Source & Models Code Assistants DevOps & Infrastructure No-Code / Low-Code Testing & QA Backend & APIs

Trending

Explore

Browse AI tools by category

Content & Design Productivity & Business Coding & Development AI Agents & Automation Research & Education Wellness & Lifestyle Career Development Marketing & Growth Data & Analytics Customer Support & CX Finance E-commerce