Atlarix

Atlarix

The Open-Weight Frontier Harness

A
@amariah
Last updated on Jul 24, 2026
Visit site
106 PeerPush
🥉
Ranked #3
Product of the Day
PeerPush

Details

Follow on
LinkedIn
Categories
Developer Tools
Pricing
Freemium from $19
Platforms
Desktop

Discovery signals

How AI and people discover Atlarix on PeerPush

Community award Jul 10, 2026Community awardA Product of the Day, Week, or Month award this product won from the community.
#3 Product of the Day

Jul 10, 2026

AI-readyAI-readyWhether this product carries the structured data - use cases, audiences, platforms - that lets AI match it to the right questions.
Structured

Described for AI to match

Described for AI with use cases, audiences, platforms and pricing so assistants can match it to the right questions.
Discoverable nowDiscoverable nowWhether this product is queryable through the PeerPush API and MCP right now.
Live

Via the PeerPush API and MCP

Queryable through the PeerPush API, MCP and semantic search from day one.

About Atlarix

Atlarix is a desktop AI coding harness built from the ground up for open-weight frontier models — DeepSeek, Qwen (Alibaba), Kimi (Moonshot), and MiniMax — instead of treating them as an afterthought behind a Claude/GPT-first UX. Most harnesses "support" open-weight models the way a universal remote supports your TV: technically works, never quite right. Atlarix is built the other way around. The core of that is Blueprint — a structural + lexical code-retrieval engine with no embeddings, no vector DB, no reranker step. It builds a real dependency graph of your codebase and hands the model a structurally-grounded context window instead of a nearest-neighbor guess. That matters most on exactly the models Atlarix targets: weaker context discipline and shorter effective reasoning windows than the frontier closed models, so retrieval quality is the difference between a model that's genuinely useful and one that hallucinates around gaps. Bring your own model, or run fully local. Use your own DeepSeek/Qwen key, run offline with Ollama or LM Studio, or top up pay-as-you-go credits and let Atlarix handle the model for you. The harness is the product — inference is always your choice, never locked in. What you get: - Five-mode workflow — Ask / Plan / Build / Debug / Review — so the model's autonomy matches the task, not the other way around - Approval-first execution — "AI that asks before it acts": every write, every terminal command, every MCP tool call routes through a real permission gate, not a checkbox you disable on day one - Real per-model context windows — no generic 128k assumption slapped on every provider - Automations — cron / GitHub-poll / MCP-poll triggers for unattended runs, with dangerous operations always denied and a hard execution budget - MCP support with OAuth (PKCE), tool descriptions treated as untrusted input, and a live consent gate — built by someone who's spent real time on the adversarial side of "AI agent with shell access" - Voice-to-text built in — talk to your codebase, free and local via Whisper 137 MB download — leaner than you'd expect from Electron, without cutting features Atlarix is built solo by one engineer (me) under NorahLabs, out of Nairobi. It's not venture-backed, it's not trying to be the biggest — it's trying to be the most honest, best-built option for developers who've picked their models on cost, sovereignty, or capability grounds and want a harness that actually respects that choice instead of quietly nudging them back to closed models.

Product Video

Watch a video demo of Atlarix.

Screenshots

Screenshot 1 of Atlarix
Screenshot 2 of Atlarix
Screenshot 3 of Atlarix
Screenshot 4 of Atlarix
Screenshot 5 of Atlarix
Screenshot 6 of Atlarix
Screenshot 7 of Atlarix

Product Updates (5)

A
@amariah

v14.16 — the app keeps working when the world around it doesn't

Two releases since 14.15, and they share a theme: no network, a background tab, a provider returning half a list — none of those should be your problem. The browser agent grew up. It can hold several tabs open at once, so opening a second page no longer destroys the first one's state — a signed-in session, a scroll position, a half-filled form. It can find an element by describing it ("login button", "search box") instead of reading the whole page first. And — embarrassing in hindsight — it can now press Enter. It couldn't before: no submitting a search box, no Escape to close a modal, no Tab between fields. You can also watch it work now: a cursor glides to each target and stays on screen, with a label naming what it just did. The app opens offline, in the time it takes to draw a window. It used to hang for minutes on a captive-portal or hotel wifi, which reads as "the app won't open". And an offline Pro user is no longer quietly dropped to Free for the session. Model lists can't shrink. A public model catalog is now the floor under every provider, so a truncated response from a provider can no longer make models vanish from your picker. Dictation is materially more accurate — bigger on-device model, the mic's call-tuned processing turned off, and your spoken language passed in rather than guessed at. 14.16.1 on top of that: you stay signed in across restarts (a 14.16.0 regression, my fault), a provider's models appear the moment you save its API key, sign in with Discord alongside Google and GitHub, and a new Settings → Community with the Discord invite and a link back here.

Product had at the time: 23 upvotes • 6 comments • 10 followers • 106 PeerPush

Comments (0)

No comments yet. Be the first to share your thoughts!

A
@amariah

What's new — 14.15

→ One surface for your running app. The separate Preview tab is gone — your dev server now opens in a regular Browser tab the agent can navigate, click, fill, and screenshot. One place to learn instead of two that did the same thing. → Runtime errors with real stack traces. The Errors tab now captures uncaught exceptions and unhandled rejections with their stack, straight from the running page — so the agent sees and fixes what actually broke, not just that something did. → Clickable URLs. Links in chat and the terminal — including bare localhost:PORT — open in a Browser tab (⌘/Ctrl-click for your system browser). → Sandbox that doesn't fight your toolchain. When a real tool needs to write somewhere new, Atlarix asks once, grants that exact path, and re-runs the command still sandboxed — so a first-run yarn/pnpm install no longer dies on a missing cache dir. No enumerated cache list to keep complete. → Live countdown on background jobs. Long-running commands moved to the background now show a wake timer you (and the agent) can see and adjust — set it, watch it tick, re-check when it fires. → Quieter + cleaner. New keyboard shortcuts (Cmd+T/W/J/I/O), device-spec awareness so the agent sizes parallel work to your machine, and a code-block render fix. Download for Mac, Linux & Windows → atlarix.dev (Windows unsigned; signing coming.)

Product had at the time: 22 upvotes • 6 comments • 10 followers • 94 PeerPush

Comments (0)

No comments yet. Be the first to share your thoughts!

A
@amariah

What's new — 14.14

→ Web search on Atlarix Core. Core models can now search the web themselves, pay-per-use through your credit wallet — no separate setup, no always-on plugin. (Citation strip lands in the next patch; results already work.) → Work across repos, not just one folder. The workspace is now a smart default, not a wall — the agent can read, grep, and edit files outside the current workspace (edits still go through the approval gate). No more shell-edit workarounds for dependency or cross-repo work. → Auto-update actually works now — all three platforms. macOS, Linux AppImage, and Windows auto-update were rebuilt on the correct native path for each OS. (One-time catch: installs on 14.13.2 or older need a single manual update to 14.13.3+, then it self-heals forever.) → Real model names on Atlarix Core. The Core provider page shows live names for Kimi , Qwen, DeepSeek, MiniMax , instead of "Core N" placeholders. Core badge now reads "Setup Complete" (no key needed). → Cleaner chat + honest tool cards. Injection-defense envelopes no longer leak into the UI. Markdown tables and inline code render correctly. Negative wallet balances explain themselves. → Reliability batch. Permission writes can't wedge a turn on a full disk; sandbox respects custom pnpm/cargo/etc. stores (fixes stalled installs); dead Core metering error removed; leaner agent prompting. → Faster model list. The 167-provider catalog no longer rebuilds on every window focus.

Product had at the time: 22 upvotes • 6 comments • 10 followers • 94 PeerPush

Comments (0)

No comments yet. Be the first to share your thoughts!

A
@amariah

What's new 14.13

-> Pricing reframe — Free + Pro + PAYG credits. No tier bundles AI. Atlarix Core is now pay-as-you-go prepaid credit on every tier — top up a wallet, spend it across any model. Free tier (BYOK/local), Pro ($19), and PAYG credits that work on all of them. Team tier removed. -> Real model pricing in the picker. Every provider's live per-token cost (via models.dev + OpenRouter's own pricing) now shows as a real $/M badge, so you see what a model actually costs before you run it. -> edit_file overhaul. Atomic multi-edit support plus Cursor-style merge with `// ... existing code ...` markers — deterministic stitching that refuses rather than corrupts. -> Co-author, not author. Commits are authored by your own git identity; Atlarix is credited only via a `Co-authored-by:` trailer, and it's fully toggleable. -> Harness reliability batch. Smarter wait/stall handling, an always-on live token counter, graceful image-model fallback, and paste/first-run fixes — tuned for driving weaker open-weight models without stalls. -> Security hardening. Plaintext-keychain hardening (chmod 600 + re-encrypt-on-recovery), privileged-IPC gating, and workspace-boundary read/write confinement.

Product had at the time: 22 upvotes • 6 comments • 9 followers • 66 PeerPush

Comments (0)

No comments yet. Be the first to share your thoughts!

A
@amariah

v14.11.0

New pricing model. No more capped free token pool. Run Atlarix free with your own model — DeepSeek, Qwen, or local via Ollama — or top up pay-as-you-go credits and pay only for what you use. Pro unlocks unlimited workspaces and the full tooling set. Voice-to-text. Talk to your codebase — free and local via Whisper. Performance. Message virtualization and a faster streaming pipeline keep the UI responsive on large repos and long sessions. Also in this release: live token counters, attachment dedup, and a range of stability fixes.

Product had at the time: 21 upvotes • 6 comments • 9 followers • 52 PeerPush

Comments (0)

No comments yet. Be the first to share your thoughts!

Reviews (4)

Average 4.8 out of 5

4.8

Based on 4 reviews

5
3
4
1
3
0
2
0
1
0

Comments (3)

omribenshoham
@omribenshoham

The structural code retrieval approach is brilliant - avoiding embeddings for context handling is smarter for coding tasks where exact matches matter. Built-in approval workflow before execution is a great safety feature. This is what local

A
@amariah

@omribenshoham yes indeed, it was quite a big idea in mind for us to build while thinking about devs who want everything to go local & private

galdayan1895
@galdayan1895

Really impressed by the focus on open-weight models like DeepSeek and Qwen. The code-retrieval approach with structured lexical engine seems well thought out for handling context better than traditional approaches. Definitely trying this ou

A
@amariah

@galdayan1895 thanks, would love to hear your experience with it when you do