Introducing the Mulu CLI
Build from your terminal with the same AI power as the desktop app. One command, any project, all 17 models. The CLI is here — fast, lightweight, and ready to ship.
Product updates, tutorials, engineering deep dives, and community stories. Learn how we're building the future of software development.
xAI's Grok 4.2 is now available in Mulu with a massive 2M token context window, reasoning toggle, and a multi-agent variant. Here's what it can do.
Our most capable Mulu model. 400K context, adjustable reasoning depth, and $1.50/$8.00 per million tokens. Built for complex coding tasks where you need real thinking power.
Our built-in security scanner runs in a Worker Thread, checks for OWASP top 10, dependency vulnerabilities, and secret leaks. Here's how it works under the hood.
A step-by-step walkthrough: describe what you want, let the AI build it, preview in real time, and deploy with one click. No code, no config, no fuss.
1M context, ultra-fast inference, and incredible value at $0.50/$1.25 per million tokens. Meet Mulu Agent 1 Flash — built for speed without compromise.
Most AI dev tools cost $20–$50/month. We charge $1. Here's how we make it work, why we think pricing is broken, and what it means for builders everywhere.
Deployed apps were taking too long to spin up. Here's how we approached the problem: lazy module loading, connection pooling, and the edge architecture behind our hosting stack.
Describe your endpoints in plain English, add authentication, connect a database, and deploy. A complete walkthrough for building REST APIs without writing code.
Speak clearly, use short commands, and let the AI fill in the details. Practical tips for getting the most out of Mulu's voice input.
Small changes in how you describe what you want can dramatically improve the code Mulu generates. These five patterns work across every model.
CLI launch, new models, voice improvements, cloud deploy enhancements, and more. Everything that shipped this month.
We added GPT-5.4 to Mulu today. OpenAI says it reaches 57.7% on SWE-Bench Pro, 75.0% on OSWorld-Verified, and 82.7% on BrowseComp.
Our indexing pipeline froze the app for 30+ minutes. Here's how we moved CPU-heavy work to Worker Threads and fixed it for good.
Walk through building an analytics dashboard with charts, user auth, and a billing page — from a blank project to a live URL using plain English prompts.
Mulu supports Claude, GPT-4o, and Gemini. This post covers how we decide which model to use, how fallback chains work, and automatic model selection.
Most dev tools are built behind closed doors. We chose the opposite approach. Here's why we share our roadmap, engineering decisions, and even our mistakes openly.
Pick 2–4 AI models, assign them roles like frontend, backend, or reviewer, and watch them collaborate on a shared blackboard. Claude, GPT, Gemini, and more.
Everything that shipped this month: agent improvements, deploy updates, UI polish, and bug fixes.
A lightweight version of Mulu for quick edits and prototyping. Same AI, smaller footprint. Perfect for when you just need to get something done.
Tree-sitter gives us real ASTs, incremental reparsing, and cross-language support. A look at how we integrated it into our indexing pipeline.
Break tasks into steps, give context upfront, use checkpoints. Practical advice for getting better results from Mulu's autonomous agents.
GLM-5 brings a rewritten agent runtime, intelligent model routing that picks the right AI for each task, and a redesigned deploy pipeline. The biggest update yet.
An honest look at where Mulu shines compared to VS Code, Cursor, and Windsurf — and where traditional IDEs still have the edge.
How we built a deploy system that goes from local project to live URL. Cloudflare Workers, edge caching, and the approach that makes it work.
Mulu is built for people who've never written code. Here's our approach to making AI tools accessible — the UX decisions and the features we cut.
Vague instructions, missing context, skipping examples — common prompting mistakes that lead to bad output. Here's how to avoid them.
A short note on where we're headed and why we think everyone should be able to build software, not just developers.