惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
爱范儿
爱范儿
H
Help Net Security
V
Visual Studio Blog
J
Java Code Geeks
Stack Overflow Blog
Stack Overflow Blog
Microsoft Security Blog
Microsoft Security Blog
Apple Machine Learning Research
Apple Machine Learning Research
MyScale Blog
MyScale Blog
The Cloudflare Blog
Martin Fowler
Martin Fowler
D
Docker
腾讯CDC
F
Fortinet All Blogs
雷峰网
雷峰网
GbyAI
GbyAI
G
Google Developers Blog
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
Recent Announcements
Recent Announcements
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
Blog — PlanetScale
Blog — PlanetScale
Engineering at Meta
Engineering at Meta
博客园 - 聂微东
博客园 - 叶小钗

Show HN

Show HN: AI agents for UK GDAD PCF roles and their skills The Two Pillars: Mixer Mode and Meta-Software in the Reorganization of Software Work After AI GitHub - JaiCode08/teleport-env What 1,000+ Harness Experiments Taught Me About Self-Improving Agents Show HN: Liiists, a Markdown-first, iOS and CLI list app SwiperTab – Get this Extension for 🦊 Firefox (en-US) GitHub - kouhxp/fftext: Summarize, explain, fact-check, or translate any text, URL, or file. No GPU. No cloud. One command GitHub - sweetpad-dev/sweetpad: Develop Swift/iOS projects using VSCode GitHub - dogmaticdev/IRON: IRON a.k.a. Intermediate Representation Object Notation is a Interpreter/Database that is used to create Programming Languages. GitHub - sjhalani7/vaen: Package your AI coding harness into a portable .agent file, and share it across repos, teams, & the community without ever having to copy-paste instructions, skills, MCP config, or secrets. Show HN: Gandalf the Grader Show HN: Citadeld – replay any CI failure locally from a single file GitHub - tdortman/cuSBF: High-Performance GPU Super Bloom Filter coral-ai/claude-code-token-xray at main · Coral-Bricks-AI/coral-ai GitHub - ulyssestenn/funes: Funes is a Git-based framework for LLM-managed knowledge work: an AI Librarian ingests raw sources, builds an interlinked Markdown knowledge base, and uses it to produce cited reports, analyses, and other outputs. GitHub - ThatXliner/gah: Git Add Hunk, built for agents to use GitHub - harmont-dev/harmont-cli: Command-line client for the Harmont CI platform GitHub - brooksmcmillin/mcp-authflow: OAuth 2.0 Authorization Server framework for MCP servers GitHub - javaid-codes/audit-supply-chain-agents GitHub - amorey/gochan: A small library of common channel architectures for Go, inspired by Rust GitHub - arifozgun/OpenGem: Free, Open-Source AI API Gateway with Gemini, OpenAI & Anthropic Compatibility in 1 file GitHub - Pranesh950/BioPetals: 🌸 Run BIOxAI models at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading GitHub - cnguyen14/bounty-doctor: Diagnose a GitHub bounty issue before you waste hours: detects honeypot scam repos, AI-bot attempt swarms, and stale contests. Show HN: CoreMCP – MCP Server for On-Prem DBs Show HN: KittyHTML – Render HTML/CSS as an inline image in your terminal GitHub - bingud/filemat: Web-based file manager Show HN: TruthLens – Free multi-signal deepfake image detector GitHub - apexlocal-jz/claude-usage-tray: Windows system-tray app showing your Claude Code rate-limit usage at a glance. Zero deps, ~300 lines of PowerShell. Cross-IDE (works regardless of VS Code, Cursor, plain terminal). Release v0.1.2.1 · kouhxp/yapsnap GitHub - noopolis/moltnet: Self-hostable chat network for AI agents. Pre-built bridges for Claude Code, Codex, and the Claws. Rooms, DMs, history. No Slack bots, no Matrix, no glue code.
GitHub - dys5315/domvault: An AI-augmented second brain y...
quietdrift_0 · 2026-06-21 · via Show HN

Domvault — a universe of brains: own your stack, share by consent, credit by default

A Markdown-native knowledge engine (Obsidian + Claude) with a repeatable ingestion pipeline, a self-synthesis loop that generates new connections while you sleep, and an opt-in publishing layer that lets brains share knowledge into a shared galaxy — Constellation.

Domvault is the engine, not the content. You bring your own notes; the repo ships the structure, the workflows, the scripts, and the agent instructions that make a plain folder of Markdown behave like a living, self-improving graph.


Why this exists

Most "second brain" templates are just empty folders. Domvault adds three things on top:

  1. An agent contract (CLAUDE.md) — so Claude (Code, web, or Cowork) knows your conventions, origin-tracking scheme, and the exact repeatable workflows for ingesting screenshots, chats, and research.
  2. A self-synthesis loop — a scheduled job that generates cheap "sparks" (half-ideas linking two notes) and promotes the best into full "neuron" synthesis notes. Your graph compounds without you touching it.
  3. Constellation (opt-in) — you explicitly choose which notes/frameworks to publish. Published nodes form a shared, credited knowledge graph that others can browse and pull. This is the consensual substrate for a future marketplace — never a backdoor into anyone's private vault.

The cosmology (how the marketplace scales)

🌌  Universe        →  the whole Constellation network (all public knowledge)
 ✨  Galaxy          →  a topic cluster or an org (e.g. "AI Engineering", "Acme Inc")
   ☀️  Solar system  →  one person's brain (their published nodes only)
     🪐  Planet       →  a single published note / framework
       🌙  Moon       →  a version or fork of a note

Everything inside a solar system is owned and gated by its owner. A planet only appears in the Universe if its owner published it. Pulling someone's planet into your own brain creates a linked copy that keeps attribution back to the origin star. That's the whole trust model: nothing moves without consent, and credit travels with the node.


What's in this repo

Path What it is
template/ The empty, scrubbed vault skeleton. Clone-and-go.
plugin/ One-command installer that scaffolds a new brain.
registry/ The opt-in publish/pull spec + manifest schema for Constellation.
constellation/ Design + mock for the universe visualization (web app).
frameworks/ Genericized mental models that passed the Publish Rubric — example shareable content.
docs/ Philosophy, architecture, getting-started, workflows, IP/licensing, the publish rubric.
scripts/ Portable ingestion scripts (ChatGPT export → notes, etc.).

Quick start

# 1. clone
git clone https://github.com/<you>/domvault.git && cd domvault

# 2. scaffold a brand-new brain wherever you want it
./plugin/install.sh ~/my-brain

# 3. open ~/my-brain in Obsidian, point Claude at it, start capturing

Full walkthrough: docs/03-getting-started.md.


Privacy & consent (read this)

Domvault never phones home. The base engine has no network calls. Constellation publishing is:

  • Opt-in per note — nothing is shared unless you run publish on it.
  • Explicit — you see a diff of exactly what leaves your machine.
  • Attributed — your name/handle travels with every published node.
  • Revocable — unpublishing removes the planet from the Universe.

There is no telemetry, no silent sync, no analytics on your private notes. If you ever find code that violates this, it's a bug — open an issue.


License & credit

Source-available under PolyForm Noncommercial 1.0.0: use it, study it, modify it, share it freely for any non-commercial purpose — but you may not sell it or build a commercial product on it without permission, and you must keep the attribution. The author retains all commercial rights. See docs/06-ip-and-licensing.md for plain-English details.

Required Notice: Copyright (c) 2026 Dom Sadarangani (Domvault / Constellation)