List your company

Cactus

Edge AI · by Cactus Compute

One inference engine for on-device AI across smartphones, laptops, and edge hardware.

Visit website

What it does

One inference engine for on-device AI across smartphones, laptops, and edge hardware. Runs LLMs, transcription, and embeddings locally with automatic cloud fallback. Also referred to as Cactus Hybrid Cloud and Cactus Engine.

  • On-device LLM inference
  • Local transcription
  • Local embeddings
  • Hybrid cloud routing for AI inference
  • Mobile voice assistant
  • Desktop notetaker
  • Wearable intelligence for smart glasses and AR devices
Category
Edge AI
Users
Smartphone app developers, Laptop and desktop application developers, Edge hardware and wearable developers
Public API
Not offered
Deployment
Self-hosted

Not yet disclosed: platforms, languages and support channels.

Pricing

  • Free plan$0

Prices as published by Cactus Compute, checked Oct 2026.

Security and compliance

As reported by Cactus Compute. Ask for audit reports before you buy.

  • Zero-copy memory mapping
  • Zero network transmission during on-device inference
  • Open-source MIT-licensed auditable codebase
  • Configurable cloud routing with disablement option

Reviews

No reviews yet

Reviews come from people who use Cactus at work. Share how your team uses it to help other buyers decide.

Write a review

Alternatives

  • OmniPHY-5G

    by DeepSig

    Machine-learning software for 5G RAN, deployed as drop-in component software in commercially available Open RAN baseband platforms.

  • SAS Event Stream Processing

    by SAS

    Use machine learning and streaming analytics to uncover insights at the edge and make real-time, intelligent decisions in the cloud.

  • Data Spree Inference

    by Data Spree GmbH

    Execution environment for deep neural networks on the edge and in the cloud.

  • Pro-AI Service

    by Aetina

    Comprehensive software and hardware integration services for industrial edge AI environments.

  • General Instinct Platform

    by General Instinct

    A deployment layer for physical AI that compresses frontier VLM and WAM checkpoints into smaller binaries for edge silicon, evaluates performance on target hardware, and deploys...

  • On-Device Speech-to-Text

    by Speechmatics

    Run Speechmatics speech recognition directly on devices for ultra-low latency and maximum data privacy.

Is this your product?

Claim it to keep details accurate and submit evidence for the next ranking review.

Claim Cactus