VaultGuard
Per-file permissions for your AI knowledge-base in Obsidian
What it does
Obsidian is the best thinking and knowledge-base tool ever built for one person. VaultGuard makes it work for a team. It adds encrypted sync, per-file permissions, share-links, AI chat, guest access and audit logs to the vault you already have — no migration, no new app to learn. You write exactly as you do today; VaultGuard protects who can view and work with the files. Point Claude or GPT at the vault and the AI inherits the same permissions your people do. Free if you self-host.
Share your Obsidian vault safely, put any AI on it, and scale it to your whole team. Encryption at rest and in transit, per file permissions, and fast sync. Self host the source available Community edition or use managed VaultGuard Cloud.
Share your vault safely with granular permissions and audit logs, put any AI on it, and scale it to your whole team. Free to self host. Open code you can audit. Nothing to migrate. You built something brilliant in Obsidian. Fast, linked, alive. Then you tried to grow it, and you hit the ceiling. You could build a real one from scratch. Learn retrieval, stand up a database, wire five tools together, spend six months, then train everyone on a system they never asked for. Most teams start, stall, and go back to the wiki nobody opens. So you are stuck between a tool that will not scale and a project that will not end. One living knowledge base that your whole team, and every AI you use, can…from vaultguard.cloud
Does the same job
all alternatives →
- CMCc-md – Zero-cost Obsidian sync across iPhone, Mac, and GitHubFeb 2026 · github.com · ▲8
Here's something I realized: the most AI-native knowledge base isn't a SaaS product with an API. It's a folder of markdown files on your disk. Obsidian stores everything as plain .md files. That means Claude Code (or any AI tool) can grep, read, write, and traverse your entire knowledge base with zero setup. No API keys. No OAuth. No middleware. Just local file I/O. The only missing piece was sync. I wanted my vault on iPhone (iCloud), on Mac (local), and on GitHub (backup + version history) — without paying $4/mo for Obsidian Sync. cc-md is ~400 lines of bash. iCloud handles Apple…
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 · 16d 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, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
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 · 16d ago · simedw.com