Documentation
Everything to ship on Voxell, real-time sync you self-host (Lux), the zero-trust embedding API (Forge), its public terminal client (forge-cli), and drop-in retrieval with grounded answers (Voxell Answers). This is an early hub; deep guides are landing.
Stuck? The Support Portal has a live FAQ that answers from these docs, or email [email protected].
Cross-device state you own
Lux serves reads from the browser and pushes every change across a user's devices over a live WebSocket. One small client, a lightweight Go broker you run on your own cloud account, no Kafka, RabbitMQ, or queue infrastructure.
Just activated from AWS Marketplace? Start with the Lux quickstart → deploy your broker and wire up LUX_LICENSE + LUX_API_KEY in three steps.
Install
- SDK github.com/VoxellInc/lux_sdk
- Deploy GCP / AWS Marketplace, your account
- Broker single Go process, Cloud Run + durable store
- Diagnostics
lux diag→ redacted .zip bundle
Full product overview on the Voxell Lux page, or browse the use-case guides (live dashboards, ops boards, agent state, collaborative UI, edge/device status, CDC).
Drop-in
// local-first read, live push on change import { lux } from '@voxell/lux' const store = lux('prefs', { endpoint: 'https://YOUR-broker.run.app/api/lux', apiKey: 'fw live …', realtime: true, }) store.load((data, meta) => render(data)) store.save({ theme: 'dark' })
The zero-trust embedding API
Turn text into vectors for search and RAG. OpenAI-compatible, three quality tiers, owned GPU infrastructure. Sign in with Google to get an API key. Turbo embeddings are free, no card.
curl https://api.voxell.ai/v1/embed \ -H "Authorization: Bearer $VOXELL_KEY" \ -d '{"texts":["how do I reset my password?"],"model":"turbo"}'
Product details on the Forge page. Plugging into n8n, Flowise, Dify and more? See the recipes.
Embeddings and corpus operations, from a shell
One static binary, no SDK to install. Embed a string, a file, or a whole directory; ingest and query a corpus; issue an mTLS identity. Drops into a container or a Kubernetes Job unmodified.
# install forge-cli - macOS, Linux (amd64/arm64). Windows: standalone .exe, see /cli/. curl -fsSL https://voxell.ai/install.sh | sh # a corpus backfill, resumable forge-cli embed --dir ./corpus/ --model pro --output vectors.jsonl --resume
Full command reference, Docker/Kubernetes recipes, and mTLS auth on the forge-cli page.
Upload a document. Ask a question.
Voxell Answers chunks, embeds, and indexes your documents, then answers questions grounded in them with citations, in two API calls. Load, then ask. The corpus is created on first upload.
# 1. load a document (auto-chunks + embeds) curl https://api.voxell.ai/v1/answers/handbook/documents \ -H "Authorization: Bearer $VOXELL_KEY" \ -d '{"name":"policy.md","text":"..."}' # 2. ask a question, get a grounded answer + sources curl https://api.voxell.ai/v1/answers/handbook/query \ -H "Authorization: Bearer $VOXELL_KEY" \ -d '{"query":"How many vacation days?","mode":"answer"}'
Full request/response reference (every field verified against the live handler) → Answers API reference. Product overview on the Voxell Answers page. (Pipeline stage: Mine → Forge → Ask.)
Need a hand?
The Support Portal has a Living FAQ that answers from these docs with citations.
Enterprise plans get priority tickets with a lux diag bundle. Or email
[email protected].