Final rebrand: rename remaining Rust source file to complete the gsd → forge transition. All parser references already use forge_parser after earlier commits. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
11 KiB
Getting Started with SF
SF is an AI coding agent that handles planning, execution, verification, and shipping so you can focus on what to build. This guide walks you through installation on macOS, Windows, and Linux, then gets you running your first session.
Prerequisites
| Requirement | Minimum | Recommended |
|---|---|---|
| Node.js | 22.0.0 | 24 LTS |
| Git | 2.20+ | Latest |
| LLM API key | Any supported provider | Anthropic (Claude) |
Don't have Node.js or Git yet? Follow the OS-specific instructions below.
Install by Operating System
macOS
Step 1 — Install Homebrew (skip if you already have it):
/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"
Step 2 — Install Node.js and Git:
brew install node git
Step 3 — Verify dependencies are installed:
node --version # should print v22.x or higher
git --version # should print 2.20+
Step 4 — Install SF:
npm install -g sf-run
Step 5 — Set up your LLM provider:
# Option A: Set an environment variable (Anthropic recommended)
export ANTHROPIC_API_KEY="sk-ant-..."
# Option B: Use the built-in config wizard
sf config
To persist the key, add the export line to ~/.zshrc:
echo 'export ANTHROPIC_API_KEY="sk-ant-..."' >> ~/.zshrc
source ~/.zshrc
See Provider Setup Guide for all 20+ supported providers.
Step 6 — Launch SF:
cd ~/my-project # navigate to any project
sf # start a session
Step 7 — Verify everything works:
sf --version # prints the installed version
Inside the session, type /model to confirm your LLM is connected.
Apple Silicon PATH fix: If
sfisn't found after install, npm's global bin may not be in your PATH:echo 'export PATH="$(npm prefix -g)/bin:$PATH"' >> ~/.zshrc source ~/.zshrc
oh-my-zsh conflict: The oh-my-zsh git plugin defines
alias sf='git svn dcommit'. Fix withunalias sf 2>/dev/nullin~/.zshrc, or usesf-cliinstead.
Windows
Downloads: Node.js | Git for Windows | Windows Terminal
Option A: winget (recommended for Windows 10/11)
Step 1 — Install Node.js and Git:
winget install OpenJS.NodeJS.LTS
winget install Git.Git
Step 2 — Restart your terminal (close and reopen PowerShell or Windows Terminal).
Step 3 — Verify dependencies are installed:
node --version # should print v22.x or higher
git --version # should print 2.20+
Step 4 — Install SF:
npm install -g sf-run
Step 5 — Set up your LLM provider:
# Option A: Set an environment variable (current session)
$env:ANTHROPIC_API_KEY = "sk-ant-..."
# Option B: Use the built-in config wizard
sf config
To persist the key permanently, add it via System Settings > Environment Variables, or run:
[System.Environment]::SetEnvironmentVariable("ANTHROPIC_API_KEY", "sk-ant-...", "User")
See Provider Setup Guide for all 20+ supported providers.
Step 6 — Launch SF:
cd C:\Users\you\my-project # navigate to any project
sf # start a session
Step 7 — Verify everything works:
sf --version # prints the installed version
Inside the session, type /model to confirm your LLM is connected.
Option B: Manual install
- Download and install Node.js LTS — check "Add to PATH" during setup
- Download and install Git for Windows — use default options
- Open a new terminal, then follow Steps 3-7 above
Windows tips:
- Use Windows Terminal or PowerShell for the best experience. Command Prompt works but has limited color support.
- If
sfisn't recognized, restart your terminal. Windows needs a fresh terminal to pick up new PATH entries.- WSL2 also works — install WSL, then follow the Linux instructions inside your distro.
Linux
Pick your distro, then follow the steps.
Ubuntu / Debian
Step 1 — Install Node.js and Git:
curl -fsSL https://deb.nodesource.com/setup_24.x | sudo -E bash -
sudo apt-get install -y nodejs git
Fedora / RHEL / CentOS
Step 1 — Install Node.js and Git:
curl -fsSL https://rpm.nodesource.com/setup_24.x | sudo bash -
sudo dnf install -y nodejs git
Arch Linux
Step 1 — Install Node.js and Git:
sudo pacman -S nodejs npm git
Using nvm (any distro)
Step 1 — Install nvm, then Node.js:
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.0/install.sh | bash
source ~/.bashrc # or ~/.zshrc
nvm install 24
nvm use 24
All distros: Steps 2-7
Step 2 — Verify dependencies are installed:
node --version # should print v22.x or higher
git --version # should print 2.20+
Step 3 — Install SF:
npm install -g sf-run
Step 4 — Set up your LLM provider:
# Option A: Set an environment variable (Anthropic recommended)
export ANTHROPIC_API_KEY="sk-ant-..."
# Option B: Use the built-in config wizard
sf config
To persist the key, add the export line to ~/.bashrc (or ~/.zshrc):
echo 'export ANTHROPIC_API_KEY="sk-ant-..."' >> ~/.bashrc
source ~/.bashrc
See Provider Setup Guide for all 20+ supported providers.
Step 5 — Launch SF:
cd ~/my-project # navigate to any project
sf # start a session
Step 6 — Verify everything works:
sf --version # prints the installed version
Inside the session, type /model to confirm your LLM is connected.
Permission errors on
npm install -g? Don't usesudo npm. Fix npm's global directory instead:mkdir -p ~/.npm-global npm config set prefix '~/.npm-global' echo 'export PATH="$HOME/.npm-global/bin:$PATH"' >> ~/.bashrc source ~/.bashrc npm install -g sf-run
Docker (any OS)
Downloads: Docker Desktop
Run SF in an isolated sandbox without installing Node.js on your host.
Step 1 — Install Docker Desktop (4.58+ required).
Step 2 — Clone the SF repo:
git clone https://github.com/singularity-forge/sf-run.git
cd sf-2/docker
Step 3 — Create and enter a sandbox:
docker sandbox create --template . --name sf-sandbox
docker sandbox exec -it sf-sandbox bash
Step 4 — Set your API key and run SF:
export ANTHROPIC_API_KEY="sk-ant-..."
sf auto "implement the feature described in issue #42"
See Docker Sandbox docs for full configuration, resource limits, and compose files.
After Installation
Choose a Model
SF auto-selects a default model after provider setup. Switch anytime inside a session:
/model
Or configure per-phase models in preferences — see Configuration.
Two Ways to Work
Step Mode — /sf
Type /sf inside a session. SF executes one unit of work at a time, pausing between each with a wizard showing what completed and what's next.
- No
.sf/directory — starts a discussion flow to capture your project vision - Milestone exists, no roadmap — discuss or research the milestone
- Roadmap exists, slices pending — plan the next slice or execute a task
- Mid-task — resume where you left off
Step mode keeps you in the loop, reviewing output between each step.
Auto Mode — /sf auto
Type /sf auto and walk away. SF autonomously researches, plans, executes, verifies, commits, and advances through every slice until the milestone is complete.
/sf auto
See Auto Mode for full details.
Recommended Workflow: Two Terminals
Run auto mode in one terminal, steer from another.
Terminal 1 — let it build:
sf
/sf auto
Terminal 2 — steer while it works:
sf
/sf discuss # talk through architecture decisions
/sf status # check progress
/sf queue # queue the next milestone
Both terminals read and write the same .sf/ files. Decisions in terminal 2 are picked up at the next phase boundary automatically.
How SF Organizes Work
Milestone → a shippable version (4-10 slices)
Slice → one demoable vertical capability (1-7 tasks)
Task → one context-window-sized unit of work
The iron rule: a task must fit in one context window. If it can't, it's two tasks.
All state lives on disk in .sf/:
.sf/
PROJECT.md — what the project is right now
REQUIREMENTS.md — requirement contract
DECISIONS.md — append-only architectural decisions
KNOWLEDGE.md — cross-session rules and patterns
STATE.md — quick-glance status
milestones/
M001/
M001-ROADMAP.md — slice plan with dependencies
slices/
S01/
S01-PLAN.md — task decomposition
S01-SUMMARY.md — what happened
VS Code Extension
SF is also available as a VS Code extension. Install from the marketplace (publisher: FluxLabs) or search for "SF" in VS Code extensions:
@sfchat participant — talk to the agent in VS Code Chat- Sidebar dashboard — connection status, model info, token usage
- Full command palette — start/stop agent, switch models, export sessions
The CLI (sf-run) must be installed first — the extension connects to it via RPC.
Web Interface
SF has a browser-based interface for visual project management:
sf --web
See Web Interface for details.
Resume a Session
sf --continue # or sf -c
Resumes the most recent session for the current directory.
Browse all saved sessions:
sf sessions
Updating SF
SF checks for updates every 24 hours and prompts at startup. You can also update manually:
npm update -g sf-run
Or from within a session:
/sf update
Quick Troubleshooting
| Problem | Fix |
|---|---|
command not found: sf |
Add npm global bin to PATH (see OS-specific notes above) |
sf runs git svn dcommit |
oh-my-zsh conflict — unalias sf or use sf-cli |
Permission errors on npm install -g |
Fix npm prefix (see Linux notes) or use nvm |
| Can't connect to LLM | Check API key with sf config, verify network access |
sf hangs on start |
Check Node.js version: node --version (need 22+) |
For more, see Troubleshooting.
Next Steps
- Auto Mode — deep dive into autonomous execution
- Configuration — model selection, timeouts, budgets
- Commands Reference — all commands and shortcuts
- Provider Setup — detailed setup for every provider
- Working in Teams — multi-developer workflows