The workstation built for the open-weight frontier.
DeepSeek, Qwen, Kimi, MiniMax — Atlarix Core ships the open-weight frontier labs, Blueprint makes any model perform like it knows your codebase, and every change still waits for your approval. Any model BYOK. Local-first. Built in Nairobi.
macOS · Linux · Windows · No mandatory API key
Built for the open-weight frontier
The frontier isn't closed anymore. DeepSeek, Qwen, Kimi, and MiniMax ship frontier-class models at open-weight prices — and Atlarix is the harness built to make them perform. Blueprint, the local structural index, gives any model a live map of your codebase, so an open-weight model in Atlarix works like it knows your project.
You choose how you connect:
Atlarix Core — the open-weight frontier
Four managed models from the frontier open-weight labs — DeepSeek, Qwen, Kimi, MiniMax — with predictable monthly usage and zero API-key setup.
Your own accounts
Bring the AI providers you already pay for — OpenAI, Anthropic, Gemini, OpenRouter, or any OpenAI-compatible endpoint.
Ollama / LM Studio
Run open-weight models on your own machine for zero external upload — free, offline, air-gapped when policy demands it.
Mix and match
Choose per project, workspace, or conversation — stay flexible as needs change.
If a vendor changes terms, doubles prices, or goes down — you switch in one click. No retraining. No migration panic. Your AI strategy stays yours.
Blueprint
Why open-weight models punch above their weight here
A model is only as good as what it can see of your code. Blueprint gives any model a live, structural map of your codebase — locally, with no embeddings and nothing uploaded — so an open-weight model in Atlarix works like it already knows your project.
A structural map, not a guess
Blueprint parses your repo with Universal Ctags and ast-grep into a graph of files, the symbols inside them, and how they connect — imports, calls, definitions. The model gets the real architecture, not a similarity hunch.
grep, reranked by relevance
A disk-backed SQLite FTS5 index reranks grep so the most relevant files surface first, each hit annotated with its enclosing function or class — so the model jumps straight to the right symbol instead of scrolling.
Bounded, predictable context
Instead of dumping hundreds of thousands of raw tokens, Blueprint hands over section-scoped slices — a few thousand tokens of real structure — with exact file:line citations. Context stays small, sharp, and verifiable.
No embeddings. All local.
No embedding model, no vector database, nothing uploaded — the same no-index approach Claude Code and opencode take. It lives on disk per workspace, so it scales to any repo at constant, low memory.
The payoff: structural understanding stays bounded and predictable, retrieval scales to any repo size, and the frontier open-weight labs — DeepSeek, Qwen, Kimi, MiniMax — navigate your codebase like they have it memorized.
74 developers across 12 countries · Amazon Nova AI Hackathon Winner · Featured on HackerNews
How it works
Connect your workspace
Open any project folder. Atlarix reads your codebase structure without uploading anything.
Ask the AI to do something
Write a task in plain language. The AI analyzes your code and builds a plan.
Approve before it acts
Review every proposed file change. Approve what you want. Reject what you don't. Nothing executes until you say so.
See Atlarix in action
Watch the open-weight frontier at work.

Feature walkthroughs
Built-in Browser & Web Access
A full browser inside your workspace. Load docs, test live endpoints, and research without leaving the app. The agent can read what's on screen.
Agent-Assisted Development
Watch the agent plan, write, and verify in real time. Every file write and shell command goes through an approval queue. Accept or reject individual hunks before anything touches your repo.
Sub-agents & Activity
Spawn scoped helpers for exploration and review while your main session keeps running. The Activity panel tracks every tool call across all agents.
Real Terminal & Live Preview
Full interactive shells with tab completion, colours, and persistent scrollback across restarts. Preview your app live alongside the agent. Build, run, and see results without switching context.
Any model, including ones you already have
Atlarix Core ships DeepSeek, Qwen, Kimi, and MiniMax built in. Or bring your Anthropic, OpenAI, or Gemini key — or run fully offline with Ollama and LM Studio. No new subscriptions required.
Nothing executes without your sign-off
The AI shows you its plan. You approve or reject each change before a single file is touched — and allow-once / always-allow decisions are scoped to the workspace, so approvals in one project never carry to another.
One app for your whole team
Manage models, tools, and permissions for every team member without leaving Atlarix.
Open-weight economics, local-first by design
Most AI coding tools assume you have a $20/month plan, a mandatory API bill, and a fast connection.
Atlarix is built on open-weight economics instead: the Core models — DeepSeek, Qwen, Kimi, MiniMax — cost a fraction of closed APIs, and Ollama and LM Studio run entirely free on your own machine.
No cloud dependency. No recurring API bill if you don't want one. Your code never leaves your machine unless you choose it to.
Works on a slow connection. Works air-gapped. Works anywhere.
Simple pricing. No surprises.
| Solo — Free | Studio — $19/mo | Team — from $79/mo | |
|---|---|---|---|
| Price | $0 | $19/month | $79/month |
| Seats | 1 | 1 | Up to 5, then $10/seat |
| Workspaces | 1 | Unlimited | Unlimited |
| Atlarix Core (all four models) | Starter allowance | Higher allowance | Largest — shared team pool |
| BYOK / Local Models | ✓ | ✓ | ✓ |
| Approval Queue | ✓ | ✓ | ✓ |
| MCP servers | 1 / workspace (manual) | 10 / workspace | 10 / workspace |
| Agent Behaviors | 10 / workspace | 10 / workspace | 10 / workspace |
| MCP & Skills Marketplace | — | ✓ | ✓ |
| Integrations | — | Database, GitHub Actions | + Slack, Jira, GitHub, Log Streamer |
| Repo skill priority | — | — | ✓ |
| Shared Blueprint (commit to git) | — | — | ✓ |
| Team management & org billing | — | — | ✓ |
Solo — Free
Price$0
Seats1
Workspaces1
Atlarix Core (all four models)Starter allowance
BYOK / Local Models✓
Approval Queue✓
MCP servers1 / workspace (manual)
Agent Behaviors10 / workspace
MCP & Skills Marketplace—
Integrations—
Repo skill priority—
Shared Blueprint (commit to git)—
Team management & org billing—
Studio — $19/mo
Price$19/month
Seats1
WorkspacesUnlimited
Atlarix Core (all four models)Higher allowance
BYOK / Local Models✓
Approval Queue✓
MCP servers10 / workspace
Agent Behaviors10 / workspace
MCP & Skills Marketplace✓
IntegrationsDatabase, GitHub Actions
Repo skill priority—
Shared Blueprint (commit to git)—
Team management & org billing—
Team — from $79/mo
Price$79/month
SeatsUp to 5, then $10/seat
WorkspacesUnlimited
Atlarix Core (all four models)Largest — shared team pool
BYOK / Local Models✓
Approval Queue✓
MCP servers10 / workspace
Agent Behaviors10 / workspace
MCP & Skills Marketplace✓
Integrations+ Slack, Jira, GitHub, Log Streamer
Repo skill priority✓
Shared Blueprint (commit to git)✓
Team management & org billing✓
Team is $79/mo for up to 5 seats, then $10/seat — cheaper per developer than individual Studio seats from five on up, with a shared Core pool the whole team draws from. Every plan runs all four Atlarix Core models; tiers differ by monthly allowance.
Rolling Atlarix out to a team?
The same approval queue, audit log, and per-workspace model and tool controls give leads one place to govern what the AI can do — no scattered API keys, no "I don't know what it changed."
Also works for teams →Frequently Asked Questions
Does my code get sent anywhere?
Only if you use a cloud AI provider and choose to. With Ollama or LM Studio, nothing leaves your machine. Ever.
Does Atlarix save my chat history?
In a workspace, yes — on your machine. Messages are stored as sessions in the sidebar so you can resume where you left off. You need an open workspace to chat; there is no separate global chat. Nothing is sent to Atlarix servers unless you use a cloud model. The right-panel terminal keeps command output until you start a new chat or close that shell. MCP servers, skills, and project memory under `.atlarix/` are scoped to each workspace.
What AI models does Atlarix support?
We fully support openweight models, specifically the ones from DeepSeek, Qwen, Kimi, and MiniMax. However we allow users to bring their own models as well
What's Atlarix Core?
Atlarix Core is our included model catalog — four managed open-weight models (Core 1, fastest, through Core 4, most capable) from the frontier open-weight labs: DeepSeek, Qwen, Kimi, and MiniMax. Every plan gets all four models; plans differ only by monthly allowance — Solo includes a starter allowance, paid plans add more. You can always bring your own provider keys instead.
Is the approval queue on every plan?
Yes. The approval queue is on every plan including free. It's not a paid feature. It's how Atlarix works.
Stop hoping the AI didn't change something important.
See exactly what Atlarix does before it does it.
Ready to Get Started?
Download Atlarix for your platform and start building smarter today.
These artifacts are the same Electron builds developers run locally: signed/notarized macOS bundles, Linux packages, and Windows installers as they roll through the public release repo. Verify checksums on GitHub before you deploy across a team.
macOS
Choose architecture
Notarized and code-signed — macOS trusts it out of the box.
Windows
Setup.exe
View on GitHubWindows Build — Uncertified
Atlarix for Windows has NOT been code-signed or certified yet. Windows Defender will show a "Windows protected your PC" screen before install — this is expected. To proceed, click "More info" then "Run anyway".
By downloading this build you confirm you understand it is currently unsigned and are choosing to proceed at your own discretion. Full code signing is coming soon.
If you need a certified build today, macOS is fully notarized and signed.
Unsigned build — Windows Defender SmartScreen will warn before install; this is expected.
Linux
Choose format
Early Access Notice
Atlarix is actively evolving.
While we continue improving workspace handling, we strongly recommend using Atlarix on duplicate or non-critical project folders. This helps ensure your primary codebases remain fully safe as we ship rapid updates.
SHA256 checksums available for download integrity verification