Ghostwriter – Structured thinking tool for teams using mind maps and AI
Hi HN, Longtime lurker, first time Show-er here. We built Ghostwriter to solve a problem we kept hitting: turning inconsistent, fragmented thoughts into something structured and useful, whether that’s a presentation, a project plan, or a meeting agenda. We’re 3 co-founders with backgrounds in consulting, engineering and design. Over the past two years, we’ve been working with clients: running workshops, giving status updates and solving complex problems together. Again and again, we wished for a tool that married collaborative thinking with smooth facilitation features and the ability to…
In plain words
Ghostwriter is a collaborative tool that transforms fragmented thoughts and notes into structured mind maps and polished outputs like presentations, project plans, and meeting agendas. Teams can input raw content—documents, transcripts, links, or notes—and the tool organizes them into hierarchical, question-led mind maps with supporting rationales. AI assists with generating and refining ideas throughout the process. Built by three co-founders with consulting, engineering, and design backgrounds, Ghostwriter combines collaborative thinking with facilitation features for teams working through complex problems together.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hi HN, Longtime lurker, first time Show-er here. We built Ghostwriter to solve a problem we kept hitting: turning inconsistent, fragmented thoughts into something structured and useful, whether that’s a presentation, a project plan, or a meeting agenda. We’re 3 co-founders with backgrounds in consulting, engineering and design. Over the past two years, we’ve been working with clients: running workshops, giving status updates and solving complex problems together. Again and again, we wished for a tool that married collaborative thinking with smooth facilitation features and the ability to create polished outputs. What Ghostwriter does: - You can start from scratch or bring in content like notes, documents, presentations, transcripts, links - It structures your inputs into a top-down, question-led mind map, with succinct answers supported by a clear rationale - AI helps you generate, refine, and reorganize ideas, all while staying grounded in your inputs using RAG - Export the result to PowerPoint, PDF, or keep working inside the tool - Use it for team problem-solving, meeting facilitation, planning, or creating presentations Ghostwriter has changed our own workflow: instead of collating multiple sources of info and ping-ponging deliverables back and forth with formatting and content changes, we now focus on pure thinking, collaborating in a shared space that maintains structure and clarity from initial ideation to final output. We’re in open beta and would love your feedback on what’s working, what’s unclear, and what you’d want it to do better. Sign up free at https://gwriter.io. Thanks!
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 · 26d ago · cactuscompute.com
Launched alongside, May 2025
the whole month →
- C9
Life & fun · 2025 · felixrieseberg.github.io
