Other
Jul 2026A third-party security analysis reported that Cactus Hybrid cloud handoff can disable TLS peer and hostname verification by default unless CACTUS_CLOUD_STRICT_SSL is set, which could expose handoff traffic and tool context.
SourceKernels & Engine for running AI on consumer devices.
Company research
Public company, workplace, funding, and market signals
Updated Jul 30, 2026
Overview
Cactus Compute is a San Francisco-based YC S25 startup building an open-source, hybrid on-device AI inference engine for phones, laptops, wearables, and other edge devices, with cloud handoff for harder requests.
Primary product
Cactus Engine
Founded
2025
Headquarters
San Francisco, California, United States
Team size
20-30
Industry
Research Services
Sub-industry
on-device AI inference / edge AI infrastructure
Offices
San Francisco, California, United States (HQ)
London, United Kingdom
Business model
open-source software
freemium
usage-based cloud inference
paid hybrid features
Funding
Stage
pre-seed/seed
Total raised
$625K
Latest round
Pre-Seed Round · Oct 2025
Latest amount
$500K
Oct 2025 · Y Combinator
Aug 2025
People & investors
Work & culture
Open-source, research-heavy, and performance-focused; the company appears mobile-first, shipping-oriented, and distributed across multiple countries.
Product & market
Pricing
Freemium / usage-based cloud inference: free on-device tier with paid cloud STT/LLM and hybrid features for production use.
Differentiators
- —Confidence-based hybrid routing that hands hard requests to the cloud
- —Cross-platform SDKs and bindings for mobile and developer stacks
- —Fast on-device inference with privacy/offline operation
- —PyTorch-to-Cactus transpilation
- —Custom quantization down to low-bit formats
- —Unified engine for text, speech, vision, embeddings, and tool calling
Technology
C++
Python
TypeScript
React Native
Flutter
Swift
Kotlin
Rust
Metal
ARM NEON SIMD
C
Objective-C++
PyTorch
Hugging Face
OpenAI-compatible API
Customers
AnythingLLM (Mintplex Labs Inc.)
KinAI
Competitors
ExecuTorch
MLC LLM
ONNX Runtime
llama.cpp
whisper.cpp
Nexa AI
MediaPipe
Scale & contact
Estimated monthly visits
19.5K
Signals & risks
Latest news
Ground Truth · Jul 2026
Third-party security analysis highlighted a cloud-handoff TLS verification concern in Cactus Hybrid and described the model's confidence-based routing design.
LinkedIn · Jul 2026
Major product release introducing a PyTorch transpiler, lossless low-bit quantization, GPU support, and hybrid routing.
LinkedIn · Jun 2026
Cactus said it powers the AnythingLLM mobile app, citing the app's scale and the partnership as a production deployment.
Cactus Blog · May 2026
Official launch of Needle, a 26M parameter function-calling model with high throughput on consumer devices and open-source weights on Hugging Face.
Cactus Blog · Apr 2026
Announced day-one Gemma 4 support, multimodal on-device inference, and cloud handoff for harder tasks.
Jobs and careers at Cactus
0 jobs at Cactus
No open positions
Check back later for new openings