slotstream
Slotstream is a local AI engine that runs a very large model on Apple Silicon Macs with 16 to 64 GB of memory, for people who want offline AI without a cloud account.
What it is good for
- Running a large AI model offline on a Mac with limited memory
- Connecting Claude Code or Codex to a model running on your own computer
- Serving a local model to apps through Ollama or OpenAI-compatible APIs
- Embedding a local AI model in a Swift app
At a glance
- Who it is for
- Setup
- Guided command-line setup
Level 4 of 5. You copy and paste commands into a terminal by following the instructions. Comfortable territory for vibe coders.
- Cost
- Free and open source
- Type
- Agent app
- Tasks
- Works with
- Claude Code, Codex, Ollama, OpenAI API, Anthropic API, Pi
Momentum
- Rank this week
- Not ranked yet
- Best rank
- None yet
- GitHub stars
- 642
GitHub numbers as of Nov 2, 2026. Updated weekly.
Official links
Setup steps are on the official pages. We do not repeat them here, since they change.
Questions
- Is slotstream free?
- Yes. It is free and open source (MIT license).
- Do I need to know how to code to use slotstream?
- You do not need to write code, but setup means copying and pasting commands into a terminal by following its instructions.
- What does slotstream work with?
- According to its own documentation, it works with Claude Code, Codex, Ollama, OpenAI API, Anthropic API, and Pi.
- What is slotstream good for?
- Running a large AI model offline on a Mac with limited memory, connecting Claude Code or Codex to a model running on your own computer, serving a local model to apps through Ollama or OpenAI-compatible APIs, and embedding a local AI model in a Swift app.
Similar agents to slotstream
- LibreChat
LibreChat is a self-hosted chat app that runs AI agents, tools, and multiple AI models for teams that want their own ChatGPT-style interface.
- Octop
Octop is a self-hosted AI assistant that runs multiple specialized agents for households and small teams.
- KiroCrew
KiroCrew is a self-hosted development workspace that keeps agent work running between sessions for developers who want long tasks done unattended.
- Mercury
Mercury is an agent app that runs on your own machine and keeps working in the background, for people who want a personal assistant that remembers them and asks before acting.
- qwen-audio-agent
qwen-audio-agent is a realtime voice runtime that lets you talk to an AI agent while it keeps working on background tasks for you.
- MLX-Serve
MLX-Serve is a local model server and Mac app that runs AI models offline for chat, coding agents, and media for Mac users.