Cactus Compute, Inc.
@cactus-compute • Tiny AI For TIny Devices. Use this route to separate flagship concentration from portfolio breadth before you treat a publisher as broadly strong.
Portfolio concentration
97%
Top three share
Shows whether the organization is driven by one breakout repo or several visible projects.
Breadth
19 repos
Visible snapshot
6 repositories updated in the last 90 days.
Leading language
Python
Portfolio mix
Python (7), C++ (3), TypeScript (3)
Average size
835
Stars per repository
Useful for distinguishing one flagship-heavy publisher from a repeatable portfolio.
Updated: 2026-08-26(7h ago)GitHub API fallback19 repositories
97%
of the visible star count comes from this organization's top three repositories.
835
stars per repository in this same snapshot.
Python
is the most common language here, with 6 repositories updated in the last 90 days.
Why this rank
This organization stands out because one flagship repo drives 58% of its visible star count.
Flagship share 58%Breakout repo: needle
Organization pages work best when you separate portfolio breadth from flagship concentration. In Cactus Compute, Inc.'s case, the visible top three repositories account for about 97% of total stars in this snapshot, which helps explain whether the organization is known for one breakout project or for a broader repeatable portfolio.
The dominant language mix here is Python (7), C++ (3), TypeScript (3). That makes this page useful not just for popularity checks, but also for seeing what technical shape an organization's public ecosystem actually has.
Top Repositories
| # | Repository | Language | Stars |
|---|---|---|---|
| 1 | cactus-compute/needle 14MB foundation model for tiny devices; phones, wearables, smart home, and robots. | Python | 9.3K |
| 2 | cactus-compute/cactus Quantization, kernels, runtime and inference engine for mobiles, wearables, smart home and robots. | C++ | 5.9K |
| 3 | cactus-compute/cactus-hybrid On-device models that know when they're wrong: every answer carries a confidence score for cloud handoff. | Shell | 255 |
| 4 | cactus-compute/cactus-react-native Cactus React Native package: Run AI locally in your React Native apps | C++ | 178 |
| 5 | cactus-compute/cactus-kotlin Cactus Kotlin Multiplatform library: Run AI locally in your Kotlin apps | Kotlin | 74 |
| 6 | cactus-compute/cactus-flutter Cactus Flutter plugin: Run AI locally in your Flutter apps | C++ | 71 |
| 7 | cactus-compute/functiongemma-hackathon Getting started repo for the Cactus x DeepMind Hackathon | Python | 40 |
| 8 | cactus-compute/demo-cactus-chat Repo for the Cactus Chat app - please contribute! | TypeScript | 28 |
| 9 | cactus-compute/voice-agents-hack Get started with Cactus x Google DeepMind x Y Combinator - Gemma 4 Voice Agents | 17 | |
| 10 | cactus-compute/cactus-gemma4 Cactus-Gemma-4 Demo App | TypeScript | 6 |
| 11 | cactus-compute/depth-over-specialization | Python | 4 |
| 12 | cactus-compute/cq-convert | Python | 1 |
| 13 | cactus-compute/needle-environments | Python | 0 |
| 14 | cactus-compute/opencode The open source coding agent. | TypeScript | 0 |
| 15 | cactus-compute/openclaw Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞 | 0 | |
| 16 | cactus-compute/homebrew-cactus | Ruby | 0 |
| 17 | cactus-compute/fmtp Optimized/Lightweight LoRA Multi Token Prediction | Python | 0 |
| 18 | cactus-compute/fast-mtp | Python | 0 |
| 19 | cactus-compute/dllm dLLM: Simple Diffusion Language Modeling | 0 |
Next step after the organization read
Open a flagship repository, compare a couple of portfolio leaders, or return to the organization map when you want a broader concentration read.
Learn and methodology
Keep trust-building context reachable, but behind the first data read instead of ahead of it.
How to read this organization snapshot
Total stars are useful as a discovery signal, but they do not tell you whether a team maintains every repository equally. Pair this page with release cadence, maintainer activity, and the flagship concentration shown above before making adoption decisions.
For broader background on GitStar's ranking logic and editorial guidance, see Methodology & Editorial Standards.