AI Engineer · Full Stack Architect · Founder @ NorahLabs

Building production AI systems from Nairobi, Kenya. Coding-agent harnesses, agentic orchestration, and native desktop applications — serious AI tooling that runs on your own machine, on any model you bring, without cloud lock-in.

The private AI workstation: desktop, browser, and PR review. A native desktop workspace where your team drives an AI to plan, build, review, debug and test real projects, a Chrome extension that brings the same agent into your own browser, and a reviewer for your pull requests. It keeps notes on your codebase and gets sharper on your system the longer you use it.

macOS / Linux / Windows · Chrome · GitHub · atlarix.dev

Atlarix is a workstation you bring any AI model into — it uses AI, it doesn't make it. What lets a weaker or local model punch above its weight isn't a bigger prompt, it's the harness: enforced tool approvals, an OS-level execution sandbox, and verified edits mean the model's mistakes are caught by the system, not trusted on faith. Any-model BYOK, local-first execution, and every change behind your approval. Run a local model and your code never leaves the machine.

Three surfaces, one product:

• Desktop app — the full workstation: plan, build, debug, review and test with a real terminal, a sandbox, and hunk-by-hunk approval.
• Chrome extension — the same agent in the browser you're already signed into: it reads pages, works across tabs, fills forms (never submits without asking), and hands the desktop agent your real session when a task needs your logins.
• Atlarix Reviewer — a GitHub App that reads the pull requests on repositories you choose and posts its findings as a review (file, line, what's wrong, and the fix). It never writes to your code and never runs it.

What makes it different:

• The harness, not the model — a weaker or local model performs reliably because the system enforces correctness, rather than hoping the model gets it right. Bring your own key across 220+ providers, run local models through Ollama or LM Studio, or use Atlarix Auto and skip keys entirely.
• Atlarix Auto — picks the right model for each step of the work (exploring, building, planning, reviewing, reading a screenshot or PDF) instead of running a whole session on one model. Free in the desktop app with a daily allowance; private on Pro or credit.
• Harness-managed agent control — tool approvals, background commands, waits, and sub-agents are enforced by the harness, not the prompt, so a weaker model can't emit a premature completion or mismanage a wait.
• Verified edits — in Build / Debug the agent runs the project's own checks (tsc/eslint/ruff/mypy/pytest) through a sandboxed terminal and can't declare a task done while they fail. A command that exits non-zero, or an edit that didn't land on disk, goes back to the agent — not to you.
• OS-level execution sandbox — per-OS write-confining command execution (Linux Landlock, Windows AppContainer, macOS Seatbelt), an approval queue with hunk-level diff accept/reject, a danger gate, and committable permission + hook rules at a single execution funnel. It can't reach past the project you opened.
• Fast search, no index — bundled-ripgrep grep and glob over your workspace: no index to build, no embeddings, no background watcher, constant low memory at any repo size.
• Parallel sub-agents — up to five workers per turn: read-only scouts and architects, plus implementers whose edits come back as proposals for the main agent to review.
• Long sessions that hold up — one compaction system that summarises before it deletes anything, plus session_search so the agent can look back through the full transcript instead of asking you to repeat yourself.
• Real workspace — interactive PTY terminal (persists across restarts), a browser the agent drives for testing your app, @ file/folder mentions scoped to the current workspace, and any MCP server or Agent Skill dropped straight in.
• Automations — put it on a schedule or an MCP trigger (a nightly test run, a weekly dependency review); it runs, then reports back.

Work modes: Explore (read-only) · Plan · Build · Debug · Review (correctness + security)

Pricing: the app is free, with every feature. Free Atlarix Auto on the desktop, your own keys and local models cost nothing. Pro ($19/month) adds Atlarix Reviewer and included managed inference across all three surfaces.

As an open-source contributor, I've landed production code into major repositories using Atlarix on open-weight and local models — including Remix (merged by its co-creator), Caddy, Traefik, Valkey, TanStack Query, Apollo Client, Crawlee, and vim. Each is a public, verifiable merge — the code is AI-assisted (the agent appears as a commit co-author) and reviewed and merged by the projects' own maintainers.

Blueprint: Section-Scoped Structural Graph Retrieval and Post-Turn Compression for Agentic LLM Coding in Multi-Repository Workspaces Amariah Abishai, NorahLabs — 2026 · published research

A peer-reviewed paper documenting the Blueprint architecture — a section-scoped structural index (Universal Ctags symbol graph + ast-grep edges + SQLite FTS5) that handed the agent structural understanding in ~6,500 tokens instead of a whole-repo dump — alongside post-turn tool-result summarisation and results from a controlled A/B evaluation on a production multi-repository workspace, including a counterintuitive finding: structural confidence lets the agent explore more, using more total context but producing stronger results. Blueprint was a research effort; Atlarix's current retrieval takes a different, lexical approach.

atlarix-skills — Community Agent Behaviors registry. SKILL.md files teaching agents language patterns and framework conventions across React, Next.js, Python, TypeScript, Go, Rust, Docker, MCP, and more. Apache 2.0.

atlarix-mcps — MCP server registry for Atlarix. Connections to Gmail, Calendar, Drive, and more from within the agent environment. Apache 2.0.

atlarix-releases — Desktop app release builds for macOS, Linux, and Windows.

Praxia — AI healthcare assistant with MONAI X-ray analysis (pneumonia, fractures, tumours), multilingual symptom diagnosis, real-time WebSocket chat, and a Docker/Nginx/Celery production stack.

Commit Checker — Open source CLI for Git commit analysis.