What this is
A desktop coding harness built specifically around open-weight models like DeepSeek, Qwen and Kimi, instead of bolting them onto a Claude or GPT-first interface as an afterthought.
Our one-line summary — not the founder’s tagline.
- How it works
- A desktop AI coding harness built around open-weight models (DeepSeek, Qwen, Kimi, MiniMax) instead of Claude/GPT, using a structural + lexical code-retrieval engine (Blueprint) that builds a real dependency graph of the codebase rather than embeddings or a vector DB.
- What's different
- Built specifically for open-weight models' weaker context discipline, instead of treating them as an afterthought behind a Claude/GPT-first interface.
- Pricing
- Free.
- Best for
- Developers who want to use open-weight models like DeepSeek, Qwen, or Kimi for coding with retrieval built for their limitations.
- Watch out
- Depends on local tools like Ollama and MCP — offline/no-cloud setup requires configuring those dependencies yourself.
What we measured
Nobody else publishes this — it comes from knocking on the door every day.
- Watched by us
- 18 days
- Last checked
- 2d ago
Where it shows up
Every group here is a page of its own — each one checked daily.
The numbersIs it still shipping, is it overpriced, where did it land — and what the price is built from.
League price & chart
No money. No seat. It goes on your record — and in 28 days reality settles it.
Calls are closed while we rebuild accounts. You can still read every one of them.
Dev. Launched 18d ago on PeerPush, where it placed #562. Today, the site itself changed 2d ago — evidence it's still shipping, not just announcing.
Quiet for 2 days — no penalty yet, but quiet doesn't stay free.
We check this site every day, ourselves. A founder can post “still working on it” — a claim like that doesn't price. What we price is what we can verify from the outside: evidence, not announcements. The real question isn't “will this be huge?” — it's “will they still be moving in four weeks?”
Shipping record
1 separate day we saw this ship · source: page changed
Beyan değil kanıt: founder “çalışıyoruz” diye post atabilir, ama sevk ettiyse izi kalır. ⚠️ Kaydı olmayan ürün “sevk etmedi” demek değildir — o üründe izleyecek bir kaynağımız yok demektir.
The market viewHow this launch is priced and ranked in our league — the investor side of the page.
ranked by the reality anchor, not the market price
It placed #562 on PeerPush with 22 votes.
No matter how much money goes in. There is no pump here — you can't make yourself right by buying more. The line only moves on things that actually happened: an award, revenue that grew, a new platform, code that shipped — or silence.
En eski 1 hareket bu listede yok — toplam 13 olay var. 4 quiet days in between are left out — nothing happened on them. A launch that goes quiet eases down a little at a time — never a cliff you could have run from the night before.
How the launch is moving on its own board, day by day — the crowd's attention.
A flat line is normal: votes stop within a day or two of launch, on every board. What's unusual — and what actually counts — is a launch that keeps pulling votes long after its day is over.
About
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.
Where it launched
1 platform| Platform | Votes | Counts toward price | Link |
|---|---|---|---|
| PeerPush | 22 | sets the price | ↗ |
The board it did best on sets the price. Every other board only adds to it if the launch also placed high on that board too — because just showing up somewhere isn't an achievement. Listing on twelve directories is free; placing well on them isn't.
Discussion (0)
No thesis posted yet. Be the first.