Markra
Minimal WYSIWYG Markdown with native AI, fully local
What it does
Markra is a local-first, WYSIWYG Markdown editor with native AI collaboration. Built with Tauri, it weighs under 6MB and runs on macOS, Windows, and Linux. Unlike editors that bolt an AI chat panel onto the sidebar, Markra treats AI as a core part of the writing flow — select text to rewrite, translate, or summarize in context. Your files stay on disk, fully portable, fully yours.
Does the same job
all alternatives →- AOAn open-source, collaborative, WYSIWYG Markdown editor2023 · editor.vrite.io · ▲460
Inspired by the design and UI/UX of apps like Notion, and utility of open-source apps like StackEdit, I decided to create a minimalistic, local-only WYSIWYG Markdown editor. Some features worth highlighting: - Monaco editor and Prettier integration for code snippets - Tables (apparently the holy grail of WYSIWYG editing) - Embeds (for CodePen, CodeSandbox and YouTube, most useful for HTML or JSON exports) - Accepts Markdown paste-in, and "exports"/generates HTML, Markdown and JSON outputs - Collaboration (with real-time awareness and initial commenting system, available only when…
FunBlocks AI Markdown Editor Oct 2025 · ▲382Experience the joy and speed of pure text, with AI copilot
- KWKraa – Writing App for EverythingDec 2025 · kraa.io · ▲127
Hello HN! We're a team of three building a new kind of web-based markdown editor. There are many editors out there, so one is spoiled for choice, but Kraa's approach is a little different. It's trying to be both a minimal and distraction-free experience while being feature-rich and allowing for tons of use cases. What Kraa's good for: - Distraction-free writing & reading (minimal UI, performant, styling logic completely separated from the editing experience) - Quick sharing of any written text – compared to many other writing tools, your content can be easily shared just by posting a link…
- MAMarky – A lightweight Markdown viewer for agentic codingApr 2026 · github.com · ▲75
Hey HN, In this age of agentic coding I've found myself spending a lot of time reviewing markdown files. Whether it's plans or documentation that I've asked my agent to generate for me, it seems that I spend more time reading markdown than code. I've tried a few different solutions to make it easier to read such as Obsidian however I've found their Vault system to be quite limiting for this use case and I've found TUI solutions to not quite be as friendly to read as I've wanted so I made Marky. Marky is a lightweight desktop application that makes it incredibly easy to read and track your…
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 · 18d 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, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
- NW
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com
- FM
Dev tools · May 2026 · github.com