The Goal is simple, there should be an actual free editor
Hey HN, I'm Saai, one of the creators of Sylix. I made this open-minded version of Cursor where you can get all of the core features of Cursor but in a fully customizable IDE (Ctrl+K, @docs, parallel agents). We love Cursor so much, but there are so many other features we're building, including all things like multi-edit, parallel swaps, agent indexing (but not the traditional one), parallel LSP, or maybe... we might give agents a better understanding of the codebase via multi-semantic memory instead, alongside in-search grep for your system files or workspace. Sylix will be open source once…
In plain words
Sylix is a customizable AI-powered code editor built on Monaco that offers core features similar to Cursor, including Ctrl+K commands, documentation references, and parallel agents. Designed for developers seeking a free alternative, it provides multi-edit capabilities, parallel LSP support, and advanced codebase understanding through multi-semantic memory. The tool enables workspace file searching and agent indexing beyond traditional approaches. Sylix plans to become open source once stable.
written from the facts on this page · September 2026
From the sources
Sylix is a free AI code editor built in Rust. Local-first privacy, BYOK, verify loop, LSP autocomplete. Not a VS Code fork — built from scratch. Under 35MB.
In the maker’s words, at launch
Hey HN, I'm Saai, one of the creators of Sylix. I made this open-minded version of Cursor where you can get all of the core features of Cursor but in a fully customizable IDE (Ctrl+K, @docs, parallel agents). We love Cursor so much, but there are so many other features we're building, including all things like multi-edit, parallel swaps, agent indexing (but not the traditional one), parallel LSP, or maybe... we might give agents a better understanding of the codebase via multi-semantic memory instead, alongside in-search grep for your system files or workspace. Sylix will be open source once it's stable, but it's a fully customizable tool we've been wanting! Sorry for the delay; well, it's almost a year now. Well, I know developers were waiting for this. The hard part: we're building Sylix not as a traditional fork of VS Code but as a mixer of all things; Sylix is built on top of Monaco Editor along with the Monaco Editor API, backed natively in Rust. The VS Code repo helps a lot, along with its great documentation about the src/workbench files extension, but it's great as we got into it pretty deep. Since we leveraged the monaco-vscode-api, it was easy for us to embed it nicely into our React code. So it was a pretty decent thing for adding a new feature alongside a new UI. For Sylix, all the core systems behind all things built in Rust are done; building just a little polish over the UI is a task since we are not UI designers,s though. Now two things left: a polished UI and the marketplace for Sylix, since we already figured out how we canroute then extension core; just the UI left. One thing we're excited about is how we make things work out after trying over and over a VS Code fork, Void fork, and VS Code 1.58; after trying all those things, it finally works. It's like this: maybe the 6th or 7th version of Sylix works for us. The other benefit is that Sylix is going to be open source once it has a stable version, so we don't need to hide our prompts from what we built. We let you use Cursor's core features and functions right on your machine along with any of your existing subscriptions (like Codex, Claude Code, Kimi K3, DeepSeek) while we are working on it so that you can also use OpenCode Go as a provider. Sylix supports over 120+ models via your own providers; any model you want this lets you completely control your own data, and on-prem, a hosted model. There is a lot to talk about: how we build, and full disclosure, we have passed most of the early phase and currently have around 43 developers using it with their own subscription... thank you to them; we have come so far through their feedback. But we're super excited to cover the gap alongside Cursor. Let us know if there is anything you want to see Cursor-style in an actual Free Editor. Or feel free to shoot us a message.
Does a similar job
all alternatives →- VAVoid, an open-source Cursor/GitHub Copilot alternative2024 · github.com · ▲347
Hey HN, I'm Andrew, one of the creators of Void. I made this open source version of Cursor where you can get all of Cursor's core features but in a fully-customizable IDE (ctrl+k, ctrl+L). We love Cursor but there are so many other features we want to build, like allowing AI to edit multiple files at once, or giving AI better understanding of your file system. Void is the open-source, fully customizable tool we've been wanting. The hard part: we're building Void as a fork of vscode. The repo has great documentation for extensions, but going deeper gets pretty involved. All of the code is…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 19d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, July 2026
the whole month →- IR
I might be the only SRE on Earth with his own bowling center. It's a more in-depth gig than you'd think. My family and I bought an abandoned 8-lane bowling center in the rural mid-west. In our small town there weren't many recreation options for families. You've heard of a food desert? This is an R&R desert. It had been abandoned for a good reason. The roof leaks, the electrical system was constantly surging, and my 70-year-old bowling equipment (still) doesn't work perfectly. The system that keeps your score is particularly interesting to me. It's the thing you watch during your game, but…
Life & fun · Jul 2026
- 1W18 Words▲1,160
Life & fun · Jul 2026 · 18words.com
- BA
Over the past few months, our team has been building more and more slidedecks using web frontend technologies with coding harnesses like Claude Code, but a common complaint is to make even small edits we need to edit the code either manually or via the harness. To avoid this loop, I ended up creating Bento, a single HTML file with everything you need in a slide tool including animations and shared editing. There's no install or cloud login, everything works offline. The default deck is around 560 KB and it doesn't need to fetch anything once you got it. Open it in a browser and then you can…
Dev tools · Jul 2026 · bento.page
- GG
A few days ago I found myself trying out GLM 5.2 and was really positively impressed. The capabilities and security I was getting from this LLM are similar to those I've gotten from models like Claude or GPT, and this really surprised me. But then I thought, "I wonder how it would work on a normal computer like mine," and above all, "I wonder if it would work without going into OOM on a computer like mine." So I started working with the help of agents to test this possibility. I started converting the model to int4, understanding MTP usage, and if possible implementing DSA for long context.…
AI · Jul 2026 · github.com
