Installation

1. Prerequisites
2. Windows (PowerShell)
3. Linux (bash)
4. macOS (Terminal)
5. Install the toolchain
6. Packaged builds
7. Next

---

Prerequisites

Node.js (LTS). Everything else — Claude Code, Beads, Dolt, jq, graphify, cocoindex-code, Ollama — aiflow can install for you.

Windows (PowerShell)

git clone https://github.com/Cyber93de/aiflow.git
cd aiflow
./install.ps1            # creates the aiflow shim + adds bin to the user PATH
aiflow doctor            # works immediately in this window; other terminals: open a new one

VS Code note: the integrated terminal inherits PATH at launch — fully restart VS Code (or “Developer: Reload Window”) to pick up aiflow.

Linux (bash)

git clone https://github.com/Cyber93de/aiflow.git
cd aiflow
bash install.sh          # symlinks 'aiflow' onto your PATH (~/.local/bin or /usr/local/bin)
aiflow doctor

macOS (Terminal)

git clone https://github.com/Cyber93de/aiflow.git
cd aiflow
bash install.sh          # same as Linux; optional tools install via Homebrew when present
aiflow doctor

On every OS the installer asks once whether to also install git, Subversion (svn), and Ollama (via winget/scoop on Windows, Homebrew on macOS, the system package manager or official scripts on Linux). That way a later aiflow init only has to ask which Ollama models to pull.

Install the toolchain

aiflow doctor               # what's present / missing (+ per-project summary)
aiflow install-deps --all   # install the full toolchain (or run 'aiflow init', which offers it)

install-deps installs only what your project config enables; --all installs everything. It is user-space and never installs a container engine — install Podman or Docker yourself if you want the GitHub MCP or headless container runs.

Packaged builds

Prebuilt archives (Linux/macOS/Windows) are attached to each GitHub release.

Next

• Quick Start — build your first project.
• Command reference · Configuration