Install SourceVault

One command on macOS, Linux, and Windows. Every install includes a 7-day free trial with one indexed source. No account or card required.

No GPU, or under 8 GB of RAM?

Try lite mode: it skips models and the vector store

Set SOURCEVAULT_LITE=1 and SourceVault leaves out the model stack entirely. It runs without Ollama — and there is no vector database service to run in any mode — so the only requirement is Node. You get keyword + symbol-graph code search through the same ranking pipeline, exact file reads, the dashboard, and the MCP server for your agents — everything except semantic search and grounded Ask answers, which decline with an honest message instead of degrading silently. If you later add the full stack, unset the flag and reindex: the same install upgrades in place.

SOURCEVAULT_LITE=1 npm run index-codebase -- <repo-name>
SOURCEVAULT_LITE=1 npm start

Lite mode is the fastest way to evaluate SourceVault on a laptop that can't run local models. The Sentinel policy layer, audit chain, licensing, and trial behave identically in both modes.

macOS · Homebrew (recommended)

One command installs everything

Node, Ollama, and SourceVault itself, with config and secrets generated locally at install time. Vectors live in a local SQLite file — there is no database service to run.

# One-time: trust the tap (Homebrew 6+), then install
brew trust sourcevault-ai/tap
brew install sourcevault-ai/tap/sourcevault

# Pull the local models once (~270 MB embeddings + ~6 GB reasoning).
# The installer and the server pick the reasoning model by RAM:
# qwen3.5:9b on 16 GB+, qwen3.5:4b on 8–12 GB.
ollama pull nomic-embed-text
ollama pull qwen3.5:9b

# Start the stack (launchd services, restart at login)
brew services start ollama
brew services start sourcevault-ai/tap/sourcevault

# That's every service: no vector database to start — code vectors and
# git history live in a local SQLite file. (An install that indexed on
# ChromaDB before keeps using it until you migrate; see the docs.) The
# optional Qdrant history engine needs no install either: enable it in
# Settings and SourceVault downloads, verifies, and runs it for you.

# Get your dashboard token
grep DASHBOARD_TOKEN "$(brew --prefix)/etc/sourcevault/sourcevault.env"

# Open the dashboard and put it in your Dock
sourcevault app
open ~/Applications/SourceVault.app

sourcevault app creates a real macOS app that opens your dashboard, so you get a Dock icon from day one. If you'd rather use the browser, open http://localhost:9000 lands in the same dashboard, where Chrome and Edge show an install icon in the address bar (or Settings → About → Install app) and Safari installs via File → Add to Dock.

From the dashboard, connect GitHub/GitLab/Bitbucket and index your first repository. Or from the terminal:

cd "$(brew --prefix)/opt/sourcevault/libexec"
npm run code-repos -- add <git-url>
npm run index-codebase -- <repo-name>

Apple Silicon or Intel, macOS 13+. Recommended: 8+ cores, 16 GB+ RAM, 100 GB free disk — the standard profile (qwen3.5:9b, ~6 GB; measured 11–13 tokens/s even CPU-only). 8–12 GB machines get the compact profile (qwen3.5:4b, 20–31 tokens/s CPU-only) automatically; no GPU is required for either. Published benchmark numbers are from the 9b model. Upgrades: one click in the dashboard — Settings → About → Check for updates — or brew update && brew upgrade sourcevault. Either way the service restarts itself and open tabs reload themselves; there is no manual step.

Linux · Ubuntu / Debian

Pipe the install script to bash

Downloads the latest release (sha256-verified), installs dependencies (Node 24 and Ollama, GPU-aware via Ollama's official installer — no vector database and no Docker: vectors live in a local SQLite file, and ChromaDB is installed only with --with-chroma or kept when an existing install already runs it; anything already on the box, including an already-running Ollama API, is detected and left alone), generates secrets, and registers systemd user services:

curl -fsSL https://sourcevault.ai/install.sh | bash

To see the plan first, preview without changing anything:

curl -fsSL https://sourcevault.ai/install.sh | bash -s -- --dry-run

The script is short and readable. Inspect it here before piping it, as you should with any installer. Updates are one click from the dashboard (Settings → About → Check for updates), or re-run this same command — either updates SourceVault in place, preserving your index and history.

Windows · via WSL2 Ubuntu

Start in PowerShell, land in WSL2

SourceVault runs inside WSL2 Ubuntu on Windows. This sets up WSL2 + Ubuntu if needed (first-time WSL installs need one reboot; just re-run the command after), enables systemd, and runs the Linux installer:

irm https://sourcevault.ai/install.ps1 | iex

WSL2 forwards localhost automatically, so the dashboard at http://localhost:9000/dashboard/ works straight from your Windows browser (and installs as a desktop app from there). Updates are one click from the dashboard: Settings → About → Check for updates. Inspect the script.

Team server · Docker Compose

One stack, every OS connects via the browser

Run SourceVault on one box (a GPU box for Ollama is optional; ChromaDB only via --profile chroma for deployments that indexed on it); teammates on Windows, macOS, or Linux use the dashboard over the network, installable as a desktop PWA. The optional Qdrant history engine needs no compose entry either: SourceVault manages it inside its own container and state volume when enabled.

docker compose up --build -d

Front it with a TLS reverse proxy for production; the deploy guide in your bundle covers nginx, Caddy, and Traefik.

After the trial

Licensing

The 7-day trial covers the full core product with one source plus the SourceVault Gateway on that repository — access policy, secret redaction, the audit chain, provenance, agent identity — so what you evaluate is the governed path, not just search. A license key continues past the trial with the Gateway still on, raises the source cap, and from Pro up unlocks multi-repo Ask. Enter it in the dashboard under Settings → Plan & licence; it verifies offline, with no phone-home.

  1. Pick a plan. Starter and Pro check out instantly, and your key arrives by email.
  2. Paste the key in Settings → Plan & licence → Unlock.
  3. Lost your key? Recover it here with your purchase email.