Aphelion is an open source desktop app for people who want character roleplay and writing tools alongside a local AI assistant. It runs on Windows, Apple Silicon macOS and x64 Linux. Conversations, prompts and models stay on your computer, and it works offline after the initial model download. It doesn't require an account or collect telemetry.
The creative workspace supports character chats, group conversations, story writing and branching dialogue trees. Expert assistants can help draft and analyze code or answer questions using reference material from your own PDFs and notes. The app reads relevant passages from folders you authorize rather than sending those files to a cloud service.
Aphelion can create PDFs with math and tables through Typst, save code, HTML and Markdown files, and open existing documents for editing. With an optional vision model, it can answer questions about pictures, describe images for coding work, or collect images matching a description into a PDF.
Its bundled llama.cpp engine runs GGUF models without a separate model service. The app selects a model to fit available memory; a GPU is strongly recommended, though it also runs on weaker hardware. It uses Vulkan on Windows and Linux and Metal on macOS.
The model has no independent access to files, the network or system commands. The app handles authorized file reads and document writes at your direction. Aphelion uses the MIT license; downloaded models retain their publishers' licenses.
The macOS and Linux builds are in beta and have had less testing than the Windows version.
Claim this page and we'll verify you by hand. Aphelion gets the verified badge, and you can upgrade the listing to be featured on localhosted. Proud to be listed? Put our badge on your site.
Want more people to find Aphelion?Promote it
Something wrong or outdated on this page?
46Updated 7 days agoAGPL-3.0
macOS · Windows · Linux · Browser Extension#Code execution#GGUF#llama.cpp backend
Vyact is an open source desktop workspace for people who want to use a local LLM with their documents, email and code. It runs on Apple Silicon Macs, Windows and Linux x64 under the AGPL-3.0 license. Intel Macs aren't supported.
136Updated 15 hours agoMIT
macOS · Windows · Linux · Web#LM Studio integration#MCP#Ollama integration
77.4KUpdated 1 year agoMIT
macOS · Windows · Linux · Docker#GGUF#llama.cpp backend#OpenAI-compatible API
11.9KUpdated 5 days agoAGPL-3.0
macOS · Windows · Linux · Android · Docker · Web#GGUF#Hugging Face integration#llama.cpp backend
2KUpdated 6 months agoAGPL-3.0
macOS · Windows · Linux#Code execution#LM Studio integration#MCP
1.3KUpdated 1 week agoGPL-3.0
Windows · Linux#GGUF#Image-to-image#Inpainting
AI Runner combines a personal AI companion with a layered art canvas, running both on your own hardware. It's for people who want private voice conversations and image creation in the same desktop app. The local experience works offline without an API key or subscription, and conversations, memories and companion settings stay on your machine.
Vellium brings character roleplay and fiction writing into a desktop AI app for macOS, Windows and Linux. It's for writers and people who want conversations with multiple characters, with control over their personas and fictional worlds. The app is open source under the MIT license and supports both Apple Silicon and Intel Macs.
GPT4All is a local AI chatbot for people who want to run language models on their own desktop or laptop and keep conversations on their machine. Its LocalDocs feature lets you ask questions about your own documents without sending them to a cloud service. It suits developers, teams and individuals who want control over their models and data.
KoboldCpp pairs local model inference with a browser interface built for chat, creative writing and roleplay. A fork of llama.cpp, it bundles KoboldAI Lite with tools for keeping character details and story context alongside your conversations. It's open source under AGPL-3.0.
Witsy is an AGPL-3.0 desktop AI assistant for macOS, Windows and Linux that connects MCP tools to local and cloud models. It's for people who want document chat, writing help and voice features in one app, with a choice of where their models run.