Open SVAROG
Plan-first · Privacy-first · Multi-model

The embedded coder
that plans before it acts.

SVAROG is an AI coding terminal that thinks in plans, executes in a sandbox, and runs on infrastructure you control - including fully air-gapped. The agent power developers want, with the trust boundary enterprises require.

Plan-first by default
Sandboxed shell & code runner
Air-gap mode
Bring-your-own model
svarog - AI coding terminal · plan-first by default
svarog> add a contact form with server-side validation

▸ PLAN (review before anything runs)
  1. scaffold /components/ContactForm
  2. add POST /api/contact with input validation
  3. wire client fetch + error states
  4. add a sandbox test, run it, report results

svarog> proceed with the plan
 files written ·  test run in sandbox (no network) ·  4/4 passing
# ! to run shell · ↑↓ history · /plan to re-enable plan-first
The problem

AI coding tools moved fast - and broke trust.

The current generation of agentic coders is powerful but opaque: they act first and explain later, run with broad access, and ship your source to someone else's cloud. For regulated, security-conscious, and sovereignty-bound teams, that is a non-starter.

Acts before it asks

Autonomous agents edit, install and execute with little visibility. One wrong assumption becomes dozens of unwanted changes.

Your code leaves the building

Prompts and repositories are streamed to third-party model APIs - unworkable under strict IP, data-residency or air-gap rules.

Lock-in by design

You are tied to one vendor's model, pricing and roadmap - with no way to route to a local model or self-host the brains.

The solution

An AI coder you can actually deploy inside the perimeter.

SVAROG is built around three principles that flip the defaults: review intent before execution, keep work inside a controlled sandbox, and let the operator choose the model - including a fully local one.

  • Plan-first by default. SVAROG proposes a structured plan; you approve, edit or reject before a single change lands.
  • Privacy-first. Self-hostable backend with a built-in SVAROG provider - no code has to leave your network.
  • Multi-model. Route to the SVAROG model, or bring your own (Anthropic, Gemini and more) per task.
  • Air-gap ready. A no-network sandbox mode for the most sensitive codebases.
backend /api/health
{
  "status": "ok",
  "version": "2.1.0",
  "providers": {
    "svarog":    true,   # self-hosted, default
    "anthropic": false,  # opt-in BYO key
    "gemini":    false   # opt-in BYO key
  }
}
Product · how it works

Describe what to build. Review the plan. Watch it run - safely.

SVAROG is a single terminal interface backed by a self-hostable engine. Natural language becomes a reviewable plan; shell and code execution happen inside a sandbox; results come back inline.

1

Describe the task

Type what you want in plain language. Use ! to drop into a sandboxed shell, /plan to re-enable plan-first, and ↑↓ to walk history.

2

Get a plan, not a surprise

SVAROG returns a structured, numbered plan. Approve it ("proceed with the plan"), revise it, or stop - nothing executes until you say so.

3

Execute in a sandbox

Code runs in an isolated sandbox with a no-network bash mode. The model proposes; the sandbox contains the blast radius.

4

Build, preview, ship

Run code, preview output, connect a GitHub repo, and download the result. Air-gap mode keeps the whole loop offline.

Sandboxed runner

Run code and shell commands in isolation - output inline, network off when you need it off.

GitHub-native

Connect a repository and let SVAROG work in context, with changes you reviewed first.

Plan-first prompt

Every build starts as a reviewable plan - auditable intent before any mutation.

Air-gap mode

A no-network posture for classified, regulated or sovereignty-bound work.

Market opportunity

The teams left behind by cloud-only AI coders.

AI-assisted development is becoming standard practice - but the fastest-growing tools route source code through third-party clouds. That leaves an entire segment of high-value buyers underserved.

Self-host
Backend designed to run on the customer's own infrastructure
Air-gap
A serviceable posture cloud-only agents structurally cannot offer
BYO-model
Route per task across local and frontier models - no lock-in

Regulated & sovereign

Finance, healthcare, defense and public sector teams bound by data-residency and IP-confidentiality rules.

Security-first engineering

Platform and security orgs that want agentic productivity without an uncontrolled execution surface.

Privacy-conscious builders

Founders and consultancies who simply do not want client code training someone else's model.

Market framing is qualitative and illustrative; no specific sizing, revenue or customer figures are claimed.

Business model

Open core, monetized where trust matters most.

A developer-friendly free tier drives adoption; paid plans monetize the self-hosting, air-gap and governance capabilities that enterprises require. Illustrative structure shown below.

Developer
Free
  • Plan-first terminal
  • Sandboxed code & shell runner
  • GitHub connect
  • Bring-your-own model key
  • Community support
Start free
Team
Per seat / month
  • Everything in Developer
  • Hosted SVAROG model
  • Multi-model routing
  • Shared plans & history
  • Priority support
Talk to us
Enterprise · Self-hosted
Custom
  • On-prem / private-cloud deploy
  • Air-gap mode
  • SSO & audit-ready plan logs
  • Model governance & policy
  • SLA & dedicated onboarding
Request a deployment

Pricing tiers are illustrative of the intended model and not a current commercial offer.

Differentiation

Why SVAROG wins where cloud agents can't follow.

Trust as a feature, not an afterthought

Plan-first execution and a contained sandbox make every action reviewable. Trust is the product surface - not a setting buried in a menu.

Runs where the data lives

A self-hostable backend with a native model means the agent comes to the code, not the other way around. Air-gap is a supported mode, not a workaround.

Model-neutral by design

The same terminal routes to a local SVAROG model or an opt-in frontier API. Customers optimize for cost, latency or capability - without re-tooling.

One coherent interface

Chat, plan, shell, code execution, preview and GitHub live in a single terminal. Less context-switching, fewer integrations to govern.

Technology

A thin, fast client over a self-hostable engine.

SVAROG pairs a lightweight web terminal with a backend API (currently v2.1) that abstracts providers behind one interface - so the front end stays the same whether the brains are local or remote.

  • Provider abstraction. A single API exposes the native SVAROG model alongside opt-in Anthropic and Gemini routes.
  • Sandboxed execution. Shell and code run in isolation, with an explicit no-network mode.
  • Plan engine. Natural language is compiled into a structured, reviewable plan before mutation.
  • Deploy your way. Hosted, private-cloud, on-prem or air-gapped - the same client throughout.

Stack at a glance

SVAROG model BYO: Anthropic BYO: Gemini Sandboxed bash Code runner GitHub integration Plan-first engine Air-gap mode Backend API v2.1 Self-hostable

Source & integration reference: github.com/nattimmis/svarog-embedded-coder

Why now

Capability arrived. Governance didn't.

Agents went mainstream

AI coding agents are now in everyday workflows - and so are the questions about where code goes and what the agent is allowed to do.

Open models matured

Local and open-weight models are finally good enough to run real coding workloads inside a private boundary - making self-host practical, not theoretical.

Rules tightened

Data-residency, IP-protection and sovereignty mandates are hardening. The market needs an agent that satisfies them by architecture.

About

Built by engineers who wanted the agent without the exposure.

SVAROG comes from a developer-tools team that builds for the boundary cases: regulated industries, sovereign deployments and security-conscious shops. The conviction is simple - agentic coding should be powerful and private, with a human approving the plan and infrastructure the customer controls.

Developer tooling

Deep experience shipping fast, low-friction terminal and CLI experiences developers actually keep open.

Security & sandboxing

Focused on isolation, controlled execution and the architecture air-gapped customers depend on.

Applied AI

Practical model routing and plan-first orchestration that puts a reviewable step between intent and action.

Get started

Bring the agent inside your perimeter.

Try the live SVAROG terminal, connect a repository, or talk to us about a self-hosted and air-gapped deployment.