cactus

Kernels & AI inference engine for phone chips

Stars: 3256

Visit

Cactus is an energy-efficient and fast AI inference framework designed for phones, wearables, and resource-constrained arm-based devices. It provides a bottom-up approach with no dependencies, optimizing for budget and mid-range phones. The framework includes Cactus FFI for integration, Cactus Engine for high-level transformer inference, Cactus Graph for unified computation graph, and Cactus Kernels for low-level ARM-specific operations. It is suitable for implementing custom models and scientific computing on mobile devices.

README:

Energy-efficient kernels & inference engine for phones & tiny AI-native devices.

Why Cactus?

Phones run on battery, GPUs drain energy and heat the devices.
70% of phones today don't ship NPUs which most frameworks optimse for.
Cactus is optimsed for old and new ARM-CPU first, with NPU/DSP/ISP coming.
Fast on all phones & ARM-devices with negligible battery drain and heating.

Performance

LLama.cpp is the fastest possible alternative, so we benchmark against llama.cpp on Qwen3-INT8-0.6B

Framework	Configuration	iPhone 13 Pro	Pixel 6a
Cactus	CPU only	38-40 toks/sec	15-18 toks/sec
Llama.cpp	CPU only	20-24 toks/sec	10-13 toks/sec
Llama.cpp	CPU + GPU	33-37 toks/sec	N/A

File Size Comparison

Format	Size (Qwen3-0.6B-INT8)
Cactus	370-420 MB
ONNX/TFLite/MLX	600 MB
GGUF	800 MB
Executorch	944 MB

Design

┌─────────────────┐
│   Cactus FFI    │ ←── OpenAI compatible C API for integration  
└─────────────────┘
         │
┌─────────────────┐
│  Cactus Engine  │ ←── High-level transformer engine
└─────────────────┘
         │
┌─────────────────┐  
│  Cactus Graph   │ ←── Unified zero-copy computation graph 
└─────────────────┘
         │
┌─────────────────┐
│ Cactus Kernels  │ ←── Low-level ARM-specific SIMD operations
└─────────────────┘

Cactus Graph & Kernels

Cactus Graph is a general numerical computing framework that runs on Cactus Kernels. Great for implementing custom models and scientific computing, like JAX for phones.

#include cactus.h

CactusGraph graph;

auto a = graph.input({2, 3}, Precision::FP16);
auto b = graph.input({3, 4}, Precision::INT8);

auto x1 = graph.matmul(a, b, false);
auto x2 = graph.transpose(x1);
auto result = graph.matmul(b, x2, true);

float a_data[6] = {1.1f, 2.3f, 3.4f, 4.2f, 5.7f, 6.8f};
float b_data[12] = {1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12};

graph.set_input(a, a_data, Precision::FP16);
graph.set_input(b, b_data, Precision::INT8);
graph.execute();

void* output_data = graph.get_output(result);
graph.hard_reset();

Cactus Engine & APIs

Cactus Engine is a transformer inference engine built on top of Cactus Graphs. It is abstracted via Cactus Foreign Function Interface APIs. Header files are self-documenting but documentation contributions are welcome.

#include cactus.h

const char* model_path = "path/to/weight/folder";
cactus_model_t model = cactus_init(model_path, 2048);

const char* messages = R"([
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "/nothink My name is Henry Ndubuaku"}
])";

const char* options = R"({
    "temperature": 0.1,
    "top_p": 0.95,
    "top_k": 20,
    "max_tokens": 50,
    "stop_sequences": ["<|im_end|>"]
})";

char response[1024];
int result = cactus_complete(model, messages, response, sizeof(response), options, nullptr, nullptr, nullptr);

With tool support:

const char* tools = R"([
    {
        "function": {
            "name": "get_weather",
            "description": "Get weather for a location",
            "parameters": {
                "properties": {
                    "location": {
                        "type": "string",
                        "description": "City name",
                        "required": true
                    }
                },
                "required": ["location"]
            }
        }
    }
])";

int result = cactus_complete(model, messages, response, sizeof(response), options, tools, nullptr, nullptr);

Using Cactus in your apps

Cactus SDKs run 500k+ weekly inference tasks in production today, try them!

Getting started

Demo

Contributing or Using the Repo

You can run these codes directly on M-series Macbooks since they are ARM-based. Vanilla M3 CPU-only can run Qwen3-600m-INT8 at 60-70 toks/sec, use the following:

Generate weights from HuggingFace model:

python3 tools/convert_hf.py Qwen/Qwen3-0.6B weights/qwen3-600m-i8/ --precision INT8

Build and test:

./tests/run.sh # remember to chmod +x any script first time

Roadmap:

Gemma, SmolVLM, Liquid, Kitten, Vosk etc.
SMMLA, NPU & DSP for high-end phones.
INT4 support for 1B+ models.
Python tools for porting Torch/JAX to cactus.

Limitlations

While Cactus can be used for all Apple devices including Macbooks, for computers/AMD/Intel/Nvidia generally, please use HuggingFace, Llama.cpp, Ollama, vLLM, MLX. They're built for those, support x86, and are all great!

For Tasks:

Click tags to check more tools for each tasks

run inference tasks implement custom models optimize ai performance integrate ai into apps conduct scientific computing

For Jobs:

mobile app developer ai engineer software engineer machine learning engineer data scientist

Alternative AI tools for cactus

Similar Open Source Tools

cactus

github

: 3.3k

unsloth

Unsloth is a tool that allows users to fine-tune large language models (LLMs) 2-5x faster with 80% less memory. It is a free and open-source tool that can be used to fine-tune LLMs such as Gemma, Mistral, Llama 2-5, TinyLlama, and CodeLlama 34b. Unsloth supports 4-bit and 16-bit QLoRA / LoRA fine-tuning via bitsandbytes. It also supports DPO (Direct Preference Optimization), PPO, and Reward Modelling. Unsloth is compatible with Hugging Face's TRL, Trainer, Seq2SeqTrainer, and Pytorch code. It is also compatible with NVIDIA GPUs since 2018+ (minimum CUDA Capability 7.0).

github

: 46.2k

cellseg_models.pytorch

cellseg-models.pytorch is a Python library built upon PyTorch for 2D cell/nuclei instance segmentation models. It provides multi-task encoder-decoder architectures and post-processing methods for segmenting cell/nuclei instances. The library offers high-level API to define segmentation models, open-source datasets for training, flexibility to modify model components, sliding window inference, multi-GPU inference, benchmarking utilities, regularization techniques, and example notebooks for training and finetuning models with different backbones.

github

: 69

ScaleLLM

ScaleLLM is a cutting-edge inference system engineered for large language models (LLMs), meticulously designed to meet the demands of production environments. It extends its support to a wide range of popular open-source models, including Llama3, Gemma, Bloom, GPT-NeoX, and more. ScaleLLM is currently undergoing active development. We are fully committed to consistently enhancing its efficiency while also incorporating additional features. Feel free to explore our **_Roadmap_** for more details. ## Key Features * High Efficiency: Excels in high-performance LLM inference, leveraging state-of-the-art techniques and technologies like Flash Attention, Paged Attention, Continuous batching, and more. * Tensor Parallelism: Utilizes tensor parallelism for efficient model execution. * OpenAI-compatible API: An efficient golang rest api server that compatible with OpenAI. * Huggingface models: Seamless integration with most popular HF models, supporting safetensors. * Customizable: Offers flexibility for customization to meet your specific needs, and provides an easy way to add new models. * Production Ready: Engineered with production environments in mind, ScaleLLM is equipped with robust system monitoring and management features to ensure a seamless deployment experience.

github

: 418

UMbreLLa

UMbreLLa is a tool designed for deploying Large Language Models (LLMs) for personal agents. It combines offloading, speculative decoding, and quantization to optimize single-user LLM deployment scenarios. With UMbreLLa, 70B-level models can achieve performance comparable to human reading speed on an RTX 4070Ti, delivering exceptional efficiency and responsiveness, especially for coding tasks. The tool supports deploying models on various GPUs and offers features like code completion and CLI/Gradio chatbots. Users can configure the LLM engine for optimal performance based on their hardware setup.

github

: 94

Janus

Janus is a series of unified multimodal understanding and generation models, including Janus-Pro, Janus, and JanusFlow. Janus-Pro is an advanced version that improves both multimodal understanding and visual generation significantly. Janus decouples visual encoding for unified multimodal understanding and generation, surpassing previous models. JanusFlow harmonizes autoregression and rectified flow for unified multimodal understanding and generation, achieving comparable or superior performance to specialized models. The models are available for download and usage, supporting a broad range of research in academic and commercial communities.

github

: 1.4k

CopilotKit

CopilotKit is an open-source framework for building, deploying, and operating fully custom AI Copilots, including in-app AI chatbots, AI agents, and AI Textareas. It provides a set of components and entry points that allow developers to easily integrate AI capabilities into their applications. CopilotKit is designed to be flexible and extensible, so developers can tailor it to their specific needs. It supports a variety of use cases, including providing app-aware AI chatbots that can interact with the application state and take action, drop-in replacements for textareas with AI-assisted text generation, and in-app agents that can access real-time application context and take action within the application.

github

: 24.1k

agentic_security

Agentic Security is an open-source vulnerability scanner designed for safety scanning, offering customizable rule sets and agent-based attacks. It provides comprehensive fuzzing for any LLMs, LLM API integration, and stress testing with a wide range of fuzzing and attack techniques. The tool is not a foolproof solution but aims to enhance security measures against potential threats. It offers installation via pip and supports quick start commands for easy setup. Users can utilize the tool for LLM integration, adding custom datasets, running CI checks, extending dataset collections, and dynamic datasets with mutations. The tool also includes a probe endpoint for integration testing. The roadmap includes expanding dataset variety, introducing new attack vectors, developing an attacker LLM, and integrating OWASP Top 10 classification.

github

: 1.2k

agentops

AgentOps is a toolkit for evaluating and developing robust and reliable AI agents. It provides benchmarks, observability, and replay analytics to help developers build better agents. AgentOps is open beta and can be signed up for here. Key features of AgentOps include: - Session replays in 3 lines of code: Initialize the AgentOps client and automatically get analytics on every LLM call. - Time travel debugging: (coming soon!) - Agent Arena: (coming soon!) - Callback handlers: AgentOps works seamlessly with applications built using Langchain and LlamaIndex.

github

: 4.1k

pixeltable

Pixeltable is a Python library designed for ML Engineers and Data Scientists to focus on exploration, modeling, and app development without the need to handle data plumbing. It provides a declarative interface for working with text, images, embeddings, and video, enabling users to store, transform, index, and iterate on data within a single table interface. Pixeltable is persistent, acting as a database unlike in-memory Python libraries such as Pandas. It offers features like data storage and versioning, combined data and model lineage, indexing, orchestration of multimodal workloads, incremental updates, and automatic production-ready code generation. The tool emphasizes transparency, reproducibility, cost-saving through incremental data changes, and seamless integration with existing Python code and libraries.

github

: 805

CrackSQL

CrackSQL is a powerful SQL dialect translation tool that integrates rule-based strategies with large language models (LLMs) for high accuracy. It enables seamless conversion between dialects (e.g., PostgreSQL → MySQL) with flexible access through Python API, command line, and web interface. The tool supports extensive dialect compatibility, precision & advanced processing, and versatile access & integration. It offers three modes for dialect translation and demonstrates high translation accuracy over collected benchmarks. Users can deploy CrackSQL using PyPI package installation or source code installation methods. The tool can be extended to support additional syntax, new dialects, and improve translation efficiency. The project is actively maintained and welcomes contributions from the community.

github

: 63

island-ai

island-ai is a TypeScript toolkit tailored for developers engaging with structured outputs from Large Language Models. It offers streamlined processes for handling, parsing, streaming, and leveraging AI-generated data across various applications. The toolkit includes packages like zod-stream for interfacing with LLM streams, stream-hooks for integrating streaming JSON data into React applications, and schema-stream for JSON streaming parsing based on Zod schemas. Additionally, related packages like @instructor-ai/instructor-js focus on data validation and retry mechanisms, enhancing the reliability of data processing workflows.

github

: 134

LTEngine

LTEngine is a free and open-source local AI machine translation API written in Rust. It is self-hosted and compatible with LibreTranslate. LTEngine utilizes large language models (LLMs) via llama.cpp, offering high-quality translations that rival or surpass DeepL for certain languages. It supports various accelerators like CUDA, Metal, and Vulkan, with the largest model 'gemma3-27b' fitting on a single consumer RTX 3090. LTEngine is actively developed, with a roadmap outlining future enhancements and features.

github

: 57

cua

Cua is a tool for creating and running high-performance macOS and Linux virtual machines on Apple Silicon, with built-in support for AI agents. It provides libraries like Lume for running VMs with near-native performance, Computer for interacting with sandboxes, and Agent for running agentic workflows. Users can refer to the documentation for onboarding, explore demos showcasing AI-Gradio and GitHub issue fixing, and utilize accessory libraries like Core, PyLume, Computer Server, and SOM. Contributions are welcome, and the tool is open-sourced under the MIT License.

github

: 9.7k

rank_llm

RankLLM is a suite of prompt-decoders compatible with open source LLMs like Vicuna and Zephyr. It allows users to create custom ranking models for various NLP tasks, such as document reranking, question answering, and summarization. The tool offers a variety of features, including the ability to fine-tune models on custom datasets, use different retrieval methods, and control the context size and variable passages. RankLLM is easy to use and can be integrated into existing NLP pipelines.

github

: 411

hud-python

hud-python is a Python library for creating interactive heads-up displays (HUDs) in video games. It provides a simple and flexible way to overlay information on the screen, such as player health, score, and notifications. The library is designed to be easy to use and customizable, allowing game developers to enhance the user experience by adding dynamic elements to their games. With hud-python, developers can create engaging HUDs that improve gameplay and provide important feedback to players.

github

: 181

For similar tasks

cactus

github

: 3.3k

CopilotKit

github

: 24.1k

kitchenai

KitchenAI is an open-source toolkit designed to simplify AI development by serving as an AI backend and LLMOps solution. It aims to empower developers to focus on delivering results without being bogged down by AI infrastructure complexities. With features like simplifying AI integration, providing an AI backend, and empowering developers, KitchenAI streamlines the process of turning AI experiments into production-ready APIs. It offers built-in LLMOps features, is framework-agnostic and extensible, and enables faster time-to-production. KitchenAI is suitable for application developers, AI developers & data scientists, and platform & infra engineers, allowing them to seamlessly integrate AI into apps, deploy custom AI techniques, and optimize AI services with a modular framework. The toolkit eliminates the need to build APIs and infrastructure from scratch, making it easier to deploy AI code as production-ready APIs in minutes. KitchenAI also provides observability, tracing, and evaluation tools, and offers a Docker-first deployment approach for scalability and confidence.

github

: 88

react-native-executorch

React Native ExecuTorch is a framework that allows developers to run AI models on mobile devices using React Native. It bridges the gap between React Native and native platform capabilities, providing high-performance AI model execution without requiring deep knowledge of native code or machine learning internals. The tool supports ready-made models in `.pte` format and offers a Python API for custom models. It is designed to simplify the integration of AI features into React Native apps.

github

: 949

Mortal

Mortal (凡夫) is a free and open source AI for Japanese mahjong, powered by deep reinforcement learning. It provides a comprehensive solution for playing Japanese mahjong with AI assistance. The project focuses on utilizing deep reinforcement learning techniques to enhance gameplay and decision-making in Japanese mahjong. Mortal offers a user-friendly interface and detailed documentation to assist users in understanding and utilizing the AI effectively. The project is actively maintained and welcomes contributions from the community to further improve the AI's capabilities and performance.

github

: 1.2k

AIInfra

AIInfra is an open-source project focused on AI infrastructure, specifically targeting large models in distributed clusters, distributed architecture, distributed training, and algorithms related to large models. The project aims to explore and study system design in artificial intelligence and deep learning, with a focus on the hardware and software stack for building AI large model systems. It provides a comprehensive curriculum covering key topics such as system overview, AI computing clusters, communication and storage, cluster containers and cloud-native technologies, distributed training, distributed inference, large model algorithms and data, and applications of large models.

github

: 4.6k

crabml

Crabml is a llama.cpp compatible AI inference engine written in Rust, designed for efficient inference on various platforms with WebGPU support. It focuses on running inference tasks with SIMD acceleration and minimal memory requirements, supporting multiple models and quantization methods. The project is hackable, embeddable, and aims to provide high-performance AI inference capabilities.

github

: 412

For similar jobs

sweep

Sweep is an AI junior developer that turns bugs and feature requests into code changes. It automatically handles developer experience improvements like adding type hints and improving test coverage.

github

: 7.1k

teams-ai

The Teams AI Library is a software development kit (SDK) that helps developers create bots that can interact with Teams and Microsoft 365 applications. It is built on top of the Bot Framework SDK and simplifies the process of developing bots that interact with Teams' artificial intelligence capabilities. The SDK is available for JavaScript/TypeScript, .NET, and Python.

github

: 502

ai-guide

This guide is dedicated to Large Language Models (LLMs) that you can run on your home computer. It assumes your PC is a lower-end, non-gaming setup.

github

: 159

classifai

Supercharge WordPress Content Workflows and Engagement with Artificial Intelligence. Tap into leading cloud-based services like OpenAI, Microsoft Azure AI, Google Gemini and IBM Watson to augment your WordPress-powered websites. Publish content faster while improving SEO performance and increasing audience engagement. ClassifAI integrates Artificial Intelligence and Machine Learning technologies to lighten your workload and eliminate tedious tasks, giving you more time to create original content that matters.

github

: 668

chatbot-ui

Chatbot UI is an open-source AI chat app that allows users to create and deploy their own AI chatbots. It is easy to use and can be customized to fit any need. Chatbot UI is perfect for businesses, developers, and anyone who wants to create a chatbot.

github

: 27.7k

BricksLLM

BricksLLM is a cloud native AI gateway written in Go. Currently, it provides native support for OpenAI, Anthropic, Azure OpenAI and vLLM. BricksLLM aims to provide enterprise level infrastructure that can power any LLM production use cases. Here are some use cases for BricksLLM: * Set LLM usage limits for users on different pricing tiers * Track LLM usage on a per user and per organization basis * Block or redact requests containing PIIs * Improve LLM reliability with failovers, retries and caching * Distribute API keys with rate limits and cost limits for internal development/production use cases * Distribute API keys with rate limits and cost limits for students

github

: 953

uAgents

uAgents is a Python library developed by Fetch.ai that allows for the creation of autonomous AI agents. These agents can perform various tasks on a schedule or take action on various events. uAgents are easy to create and manage, and they are connected to a fast-growing network of other uAgents. They are also secure, with cryptographically secured messages and wallets.

github

: 1.3k

griptape

Griptape is a modular Python framework for building AI-powered applications that securely connect to your enterprise data and APIs. It offers developers the ability to maintain control and flexibility at every step. Griptape's core components include Structures (Agents, Pipelines, and Workflows), Tasks, Tools, Memory (Conversation Memory, Task Memory, and Meta Memory), Drivers (Prompt and Embedding Drivers, Vector Store Drivers, Image Generation Drivers, Image Query Drivers, SQL Drivers, Web Scraper Drivers, and Conversation Memory Drivers), Engines (Query Engines, Extraction Engines, Summary Engines, Image Generation Engines, and Image Query Engines), and additional components (Rulesets, Loaders, Artifacts, Chunkers, and Tokenizers). Griptape enables developers to create AI-powered applications with ease and efficiency.

github

: 2.2k