Run agents on your own machine

Training

Mlx

MLX: An array framework for Apple silicon

Voice

whisper.cpp

C/C++ port of OpenAI's Whisper speech-recognition model, dependency-free and optimized for on-device inference

Connectors +1

JiuwenSwarm

JiuwenSwarm is an intelligent AI Agent built on openJiuwen. It extends the powerful capabilities of large language models directly to your f

Coding

LiteRT

On-device runtime (formerly TensorFlow Lite) for running models at the edge.

Deployment +2

Foundry Local

Foundry Local is an end-to-end local AI solution for building applications that run entirely on the user's device.

Deployment

Roboflow Inference

Server and SDK for running vision models locally or in the cloud behind a simple API.

Coding

MNN

Lightweight deep learning engine for on-device inference and training, with runtimes for local LLMs and diffusion models

Training

Olive

Simplify ML Model Finetuning, Conversion, Quantization, and Optimization for CPUs, GPUs and NPUs.

Voice

FluidVoice

Fastest and only macOS Dictation app with on-device STT and custom trained AI enhancement model. A local Wispr Flow alternative. ⭐ helps a t

Coding +1

Cindy

Consider it done. The open-source AI agent that works out of the box · 想到，就能做到。开源、开箱即用的 AI Agent。

Inference +1

OpenSquilla

Token-efficient microkernel AI agent with an on-device model router, persistent memory and pluggable multi-provider support

Interface +1

Apfel

The free AI already on your Mac. CLI tool, OpenAI-compatible server, and interactive chat — all on-device via Apple Intelligence. No API key

Inference

BigMoeOnEdge

Run MoE models bigger than your RAM. Frontier-size MoE on a 12 GB phone, CPU only, lossless, on stock llama.cpp

Interface

OpenDroid

Your Open Autonomous Android Agent — A production-ready, self-planning AI assistant powered by local/remote LLMs and accessibility-driven sc

Interface

Hermex

Native iPhone app for your Hermes agent

Inference

LiteRT Torch

Inference

LiteRT-LM

Generative media +2

OGAM

The Swiss Army Knife of Offline AI. Chat, see, speak, and generate images on your phone or Mac — GGUF LLMs, vision, Whisper speech-to-text,

Inference +1

Pocket TTS

A lightweight text-to-speech (TTS) application designed to run efficiently on CPUs.

Connectors

PicoClaw

Single-binary Go assistant for $10-class hardware, running in under 10MB RAM with 16+ chat channels

Voice

Silero VAD

Pre-trained enterprise-grade Voice Activity Detector

Inference

MLC LLM

Machine-learning compiler and engine for deploying LLMs across AMD, NVIDIA, Apple, and Intel GPUs, browsers, iOS, and Android

Data wrangling +1

OpenMed

On-device clinical NLP for biomedical entity extraction and HIPAA PII de-identification, running fully offline from phones to GPU servers

Voice +1

OpenLive

Opensource, on-device voice + vision layer for AI agents. Bring any model or coding agent; the whole speech loop (VAD, STT, TTS, barge-in) r