cactus-compute / cactusLinks
Framework for running AI locally on mobile devices and wearables. Hardware-aware C/C++ backend with wrappers for Flutter & React Native. Kotlin & Swift coming soon.
☆993Updated this week
Alternatives and similar repositories for cactus
Users that are interested in cactus are comparing it to the libraries listed below
Sorting:
- Enable LLMs to Program Themselves.☆623Updated 2 months ago
- Big & Small LLMs working together☆994Updated this week
- ☆93Updated last week
- Running any GGUF SLMs/LLMs locally, on-device in Android☆387Updated last week
- React Native binding of llama.cpp☆550Updated last week
- An implementation of the CSM(Conversation Speech Model) for Apple Silicon using MLX.☆359Updated last month
- ☆234Updated this week
- MLX Omni Server is a local inference server powered by Apple's MLX framework, specifically designed for Apple Silicon (M-series) chips. I…☆424Updated 2 weeks ago
- A single interface to use and evaluate different agent frameworks☆499Updated this week
- A minimalistic framework for transparently training language models and storing comprehensive checkpoints for in-depth learning dynamics …☆284Updated 2 weeks ago
- LiteRT continues the legacy of TensorFlow Lite as the trusted, high-performance runtime for on-device AI. Now with LiteRT Next, we're exp…☆595Updated this week
- Real Time Speech Transcription with FastRTC ⚡️and Local Whisper 🤗☆661Updated last week
- Fast Streaming TTS with Orpheus + WebRTC (with FastRTC)☆294Updated 2 months ago
- Agent File (.af): An open file format for serializing stateful AI agents with persistent memory and behavior. Share, checkpoint, and vers…☆636Updated last month
- Run LLMs with MLX☆1,125Updated last week
- Production-Ready MCP Server Framework • Build, deploy & scale secure AI agent infrastructure • Includes Auth, Observability, Debugger, Te…☆628Updated last week
- Run LLMs inside a PDF file.☆585Updated 2 months ago
- Open source multi-modal RAG for building AI apps over private knowledge.☆2,696Updated this week
- The Supabase of AI era. A modular, open-source backend for building AI-native software — designed for knowledge, not static data.☆308Updated 3 weeks ago
- Supporting PyTorch models with the Google AI Edge TFLite runtime.☆678Updated this week
- WebAssembly binding for llama.cpp - Enabling on-browser LLM inference☆750Updated 3 weeks ago
- Bytebot is the container for desktop agents.☆727Updated this week
- FastMLX is a high performance production ready API to host MLX models.☆308Updated 3 months ago
- ☆754Updated 2 months ago
- ☆577Updated this week
- ☆475Updated last month
- 🦛 CHONK your texts with Chonkie ✨ — The no-nonsense RAG chunking library☆1,538Updated this week
- Apple MLX engine for LM Studio☆630Updated this week
- Dynamiq is an orchestration framework for agentic AI and LLM applications☆882Updated last week
- An open-source tool for seamless migration from other LLMs to Llama, and for general prompt optimization.☆493Updated this week