Tabotec Atlas — your knowledge, on your hardware.

A self-hosted retrieval-augmented generation platform. Upload documents, ask questions, get cited answers. Choose your LLM provider — Anthropic, OpenAI, Gemini, or a local model — and switch on the fly.

Buy a licence Try it free for 30 days

One docker compose up Postgres + pgvector Local-first inference option

Why Atlas

Built for organizations that can't ship their data to the cloud.

Self-hosted by default

Atlas runs entirely inside your network. Your documents, embeddings, and answers never leave the box unless you point a provider at the public internet.

Pluggable providers

Anthropic Claude, OpenAI, Gemini, and any OpenAI-compatible local endpoint (Ollama, vLLM, llama.cpp). Per-user fallback order. One model fails, the next takes over.

Cited answers, not vibes

Every answer ships with the chunk-level citations it was built from. Reviewer agent runs after synthesis to flag hallucinations and unsupported claims.

Multi-workspace

One install, many isolated knowledge bases. JWT auth, workspace-membership checks on every endpoint, role-based access. Built for teams.

Production-grade observability

Structured JSON logs, request IDs, Prometheus metrics, OpenTelemetry tracing across the agent pipeline. Drops into your existing Grafana / Honeycomb stack.

Works with our language stack

Pair Atlas with Tabotec Tigrigna and Tigvoice to build a Tigrigna-first knowledge interface — voice-in, cited-answer-out, Geez script throughout.

Help is built in. Atlas reads its own guides at install, so you can ask Atlas how to use Atlas and get a cited answer, offline. We call it Atlas Compass.

How it's built

Boring, well-understood pieces.

Atlas is FastAPI on the back, React on the front, Postgres + pgvector for storage. Nothing exotic, nothing you can't hire for, nothing you can't operate. The agent pipeline is four small steps — router, retrieval, synthesis, reviewer — each with its own span in the trace.

Python 3.11+ / FastAPI / SQLAlchemy
Postgres 16 + pgvector for vector search
React 19 + Vite + TypeScript frontend
Pluggable embedding model (any OpenAI-compatible)
Per-user provider fallback order via context-var
Pre-commit secret scanning + GitHub Actions CI

Architecture

Agent pipeline

# /ask flow

POST /api/v1/ask
  ↓
RequestIDMiddleware     # X-Request-ID
  ↓
JWT auth               # Bearer token
  ↓
workspace check        # 403 if not member
  ↓
AgentOrchestrator
  ├─ router             # classify intent
  ├─ retrieval          # pgvector top-k
  ├─ synthesis          # cited answer
  └─ reviewer           # hallucination check
  ↓
Response { answer, citations[] }
  + Prometheus metrics
  + OTel spans

Pricing

One licence. Your hardware. Your data.

Atlas Personal licence

$249 first year

then $129 a year to keep updates flowing

For one person, private use; up to 3 workspaces
Runs on your own server or Mac; documents never leave it
Software and model updates for the licence year
Licence, receipts and renewals in your Tabotec account

✓ 30-day money-back guarantee

Talk to us to buy

Teams and firms

Licences for 25, 100 or more people with shared workspaces, seat management and priority support. Priced per organisation.

Talk to us

Managed install

We deploy Atlas onto your hardware (cloud or on-prem), configure providers, set up monitoring, and stay on call. Quarterly upgrades included.

Annual contract

Get a quote

Atlas + language stack

Atlas pre-wired to Tabotec Tigrigna and Tigvoice. Voice-in, cited-answer-out, all Tigrigna. Built for ministries, NGOs, and broadcasters.

Custom engagement

Talk to us

Prices in USD; sales tax is added at checkout where it applies. See the refund policy and terms of sale.

Try Atlas for 30 days.

A trial licence for up to 3 people and 2 workspaces. It arrives by email; paste it into Atlas → Settings → Licence, or into the installer. When it ends, Atlas keeps working — updates pause and a watermark appears until you renew.