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

cs.AI updates on arXiv.org
cs.AI updates on arXiv.org
SecWiki News
SecWiki News
Recent Commits to openclaw:main
Recent Commits to openclaw:main
Forbes - Security
Forbes - Security
Schneier on Security
Schneier on Security
W
WeLiveSecurity
cs.CV updates on arXiv.org
cs.CV updates on arXiv.org
Google Online Security Blog
Google Online Security Blog
O
OpenAI News
Exploit-DB.com RSS Feed
Exploit-DB.com RSS Feed
S
Secure Thoughts
PCI Perspectives
PCI Perspectives
人人都是产品经理
人人都是产品经理
Blog — PlanetScale
Blog — PlanetScale
S
SegmentFault 最新的问题
Help Net Security
Help Net Security
G
GRAHAM CLULEY
Latest news
Latest news
V
Visual Studio Blog
The Cloudflare Blog
T
Troy Hunt's Blog
Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
Stack Overflow Blog
Stack Overflow Blog
GbyAI
GbyAI
I
InfoQ
Know Your Adversary
Know Your Adversary
B
Blog RSS Feed
V2EX - 技术
V2EX - 技术
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
H
Heimdal Security Blog
Y
Y Combinator Blog
Security Archives - TechRepublic
Security Archives - TechRepublic
The GitHub Blog
The GitHub Blog
P
Palo Alto Networks Blog
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
T
Tor Project blog
T
Threat Research - Cisco Blogs
博客园 - 三生石上(FineUI控件)
Cloudbric
Cloudbric
博客园 - Franky
博客园 - 叶小钗
S
Security @ Cisco Blogs
cs.CL updates on arXiv.org
cs.CL updates on arXiv.org
阮一峰的网络日志
阮一峰的网络日志
WordPress大学
WordPress大学
T
Threatpost
MongoDB | Blog
MongoDB | Blog
V
Vulnerabilities – Threatpost
Martin Fowler
Martin Fowler

Show HN

CSP Radar GitHub - awebai/aweb-team-coord-worktrees: An aweb team template for a minimum team with a permanent coordinator and worktrees with local developers. GitHub - fujibee/agmsg GitHub - lucastononro/notify: 100% local, free, offline attention skill for Claude Code: plays a sound and speaks a short status update when a long task finishes, blocks, or needs a decision. GitHub - sebastianwessel/skills: AI Skills tivatdoar / workout-to-work · GitLab GitHub - enumura1/py-sql-cleaner: Find, format, and safely extract embedded SQL from Python files. GitHub - intent-bench/intent-bench: Intent fulfillment benchmark for agentic AI engineering GitHub - steveking-gh/firmion: Firmion is DSL and engine for firmware image generation. GitHub - villagesql/villagesql-skills: Agent skills for VillageSQL - gemini-cli-extension; claude-code-plugin GitHub - 0gsd/enough: a personal language system for planning, writing, and translation. GitHub - Kaelio/ktx: ktx is an executable context layer for data and analytics agents 🐙 Allow Claude Code, Codex, and any AI agent to query data accurately through MCP with skills, memory and a semantic layer GitHub - ThatXliner/xtras: Xliner's Claude Code Skills GitHub - flightdeckhq/flightdeck: Observability and control plane for AI agents. GitHub - search-router/simple-search: Open-source reference app on top of the Search Router API: FastAPI + Jinja metasearch service with pluggable backends, deterministic mocks (no API key needed), RTL UI, Redis cache, and a demo ads cabinet. CSP Radar GitHub - Light-Heart-Labs/DreamServer: Turn your PC, Mac, or Linux box into an AI server. LLM inference, chat UI, voice, agents, workflows, RAG, and image generation. GitHub - Diplomat-ai/diplomat-agent-ts: What can your TypeScript AI agent do to the real world? Scan your code. See which tool calls have zero checks Code Block Selector - Visual Studio Marketplace Prometheus dependency graph — interactive showcase | Riftmap Show HN: I made a vi-like modal keyboard plugin for Figma GitHub - run-llama/liteparse: A fast, helpful, and open-source document parser GitHub - dalemyers/Roar: A macOS CLI tool for notifications GitHub - district-solutions/open-agent-tools-coder: Enables small-to-large self-hosted ai models to use local source code when running tool-calling agentic workloads. We actively data mine 20,900+ (2+ TB) popular github repos using large and small ai models to create reuseable: json, markdown and parquet files for local-first tool-calling models. GitHub - progapandist/stripeek: A local TUI proxy for real-time Stripe API debugging, built for navigating complex payloads fast. GitHub - sir1st/hermes-desktop: All-in-one cross-platform desktop app for Hermes Agent — bundles Python + hermes-agent + hermes-web-ui GitHub - astefanutti/shaderbang: Shebang for Shaders Show HN: Generate Claude Code Workflows using Spec Driven Development approach GitHub - nixys/nxs-universal-chart: The Helm chart you can use to install any of your applications into Kubernetes/OpenShift 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 - tamerh/enju: Coordinating Humans, AI Agents, and Compute as Peers on a Shared Workflow Graph Show HN: Continuity-auth – Respect-weighted rate limits for the open web GitHub - luml-ai/luml: AI lifecycle platform where engineers and agents track experiments, train models, and ship to production. GitHub - mrdanielcasper/CoreTex: A UNIX-inspired, biomimetic, flat-file AI harness and knowledge engine. GitHub - clemg/pierre-github: Pierre's diffs.com and trees.software for Github GitHub - lyriks-io/unspaghettit: Behavior-driven AI development without prompt spaghetti. GitHub - sofumel/claude-handoff-revive: Resume Claude Code work after rate/usage/context limits without replaying the prior transcript. Auto-saves at 90%/95% usage. Plugin-installable, 10 languages. GitHub - dotexorg/saferpc: Typed, end-to-end encrypted RPC over any bidirectional channel. GitHub - BeeZeeAgent/beezee: Agent harness orchestration Legato Next.js Boilerplate for Internal Tools · CoreUI GitHub - clark-labs-inc/clark-hash: Clark Hash, 32x smaller searchable sketches for embeddings GitHub - ZeroPointRepo/youtube-mcp: The fastest YouTube transcript + YouTube search MCP for AI agents. Try for free. Typing Mastery — climb toward 100+ WPM, deliberately GitHub - Andebugulin/Awareen GitHub - fayzan123/claude-workflow-composer: Visual desktop app for composing multi-agent coding workflows. Drag agents, attach skills and MCPs, wire handoffs, export to .claude/ GitHub - StackOneHQ/stack-nudge We hardened an LLM agent. Each defense we added made it more exploitable. GitHub - alkait/WhatsKept: Agent-queryable WhatsApp history from an iOS backup — a single Go binary. GitHub - octelium/cordium: Open-source, general-purpose sandbox platform for devs and AI agents that provides identity-based secure access to infrastructure without credentials. GitHub - scosman/videowright: Build animated explainer videos with your coding agent GitHub - dipankar/dscode: The code editor you can take apart. GitHub - zoharbabin/web-researcher-mcp: MCP server (Go) for AI assistants: web search, content extraction, academic/patent/news research. Multi-provider routing, 4-tier scraping, search lenses. Works with Claude, Cursor, and any MCP client. GitHub - scanaislop/aislop: Catch the slop AI coding agents leave in your code: narrative comments, swallowed exceptions, as-any casts, dead code, oversized functions. 50+ rules across 7 languages (TypeScript, JavaScript, Python, Go, Rust, Ruby, PHP). Sub-second, deterministic, no LLM at runtime. MIT-licensed. GitHub - kouhxp/cheap-im: CPU-only voice agent approximating Thinking Machines' Interaction Models demo GitHub - unprovable/OrchidMantis: Orchid Mantis — standalone framework for Zero-Knowledge Proofs of eXploit (ZKPoX). GitHub - TangibleResearch/Halgorithem: A Algo designed to detect AI Hallucitions GitHub - CarpseDeam/Aura-IDE: An AI coding harness that shaped itself - Planner/Worker agents, repo awareness, surgical edits, validation, recovery, and safe diff approvals. GitHub - chojs23/concord: A feature-rich TUI client for Discord GitHub - aerf-spec/aerf: Agent Evidence Receipt Format (AERF) — an open specification for tamper-evident, independently verifiable records of AI agent actions. GitHub - Jwrede/tokentoll: Catch LLM cost changes in code review. Infracost for LLM spend. GitHub - samchon/ttsc: A `typescript-go` toolchain for compiler-powered plugins and type-safe execution + 500x faster lint integrated into compiler GitHub - Higangssh/homebutler: 🏠 Manage your homelab from chat. Single binary, zero dependencies. GitHub - olalie/tapmap: See where your computer connects and what stands out on a live world map. GitHub - Diplomat-ai/diplomat-agent: What can your AI agent do to the real world? Scan your code. See which tool calls have zero checks GitHub - Bajusz15/beacon: Open-source agent for secure remote access, monitoring, and deploys across home-lab and self-hosted machines like Raspberry Pi, N100, or any Linux server. Open web based TTY or tunnel Home Assistant and other local services securely without opening ports. BigTech AI News - Chrome 应用商店 GitHub - vinhnx/VTCode: VT Code is an open-source coding agent with LLM-native code understanding and robust shell safety. Supports multiple LLM providers with automatic failover and efficient context management. GitHub - Lumen-Labs/brainapi2: BrainAPI is a knowledge graph–powered AI memory layer that transforms unstructured data into structured knowledge, enabling intelligent search, recommendations, and contextual memory for AI agents and applications. GitHub - familiar-software/familiar: Let AI watch you work. Familiar lets your AI update its memory, skills, and knowledge by watching your screen. make sidebar/address bar rounded corner toggleable
GitHub - Dromena-xyz/quire: Long-form writing in Obsidian: scenes, drafts, a combined Galley editor, and compile. Releases and docs here; source is closed. Bugs and requests welcome in Issues.
dromena · 2026-06-12 · via Show HN

Long-form writing in Obsidian.

Start a Quire project anywhere in your vault and build it up scene by scene. Arrange the scenes into a nestable outline, write across them as one continuous document, and compile the result into a finished manuscript for a reader or editor. It's made for work that outgrows a single note: a novel, a dissertation, a screenplay, and more.

A Quire project: the nested scene list beside the editor

What you get

Projects and scenes. A Quire project is a folder of scenes. Create one anywhere, then fill it in. Every scene you add shows up in the Quire pane as a reorderable, nestable outline. Drag to reorder, nest one scene under another, and move a parent to carry its children with it. They stay ordinary notes throughout, so the rest of Obsidian keeps working on them.

The Quire pane showing a project's scenes as a nested outline

Galley. Open a scene together with its children, or hand-pick any set of scenes, and write them as one flowing document. Your edits save back into each individual scene as you type, so you get the focus of a single page without losing the outline underneath. Writers who know Scrivener will recognize the idea as Scrivenings. Galley is Quire's version, rebuilt for Obsidian.

A Galley: several scenes flowing together as one document with dividers between them, the scene list on the left

Compile. Turn your scenes into one finished manuscript. You assemble a workflow from steps that tidy the text on the way out, dropping frontmatter, stripping the wikilinks and callouts and other Obsidian markup that shouldn't reach a reader, prepending scene titles, setting your own separators, and writing the result to any note. Scenes can sit out of a compile without being deleted, and every project keeps its own workflow, so a novel and a research paper export differently.

The Compile tab: a workflow's steps with their Scene and Join roles

Drafts. Branch a copy of any scenes, or the whole book, and rework it beside the version you trust. Each draft is its own subfolder of scenes inside the project folder. Switch between them in the pane, write and compile each on its own, then merge the keepers back scene by scene, or promote a draft to become the manuscript outright. The bold rewrite stops being a risk.

Buy a license

Two ways to pay, and both unlock everything. Launch pricing runs through the end of July 2026.

A subscription converts to a permanent license after ten monthly payments. After conversion, the subscription keeps billing until you cancel it. If you'd like to stop there, cancel it yourself in your Link account, which your receipt and billing emails link to.

Anything past the tenth payment is patronage, plain and simple, and it goes straight into Quire's development. We're grateful if you keep it going.

Your license key arrives by email right after you buy. Keep that email and store the key somewhere safe. It's how you activate Quire, and how you reactivate after a reinstall. One license covers five activations (see Where your license works).

Install

Quire installs from GitHub rather than from Obsidian's plugin directory (the Community plugins list in Obsidian's settings), which isn't accepting new closed-source plugins for now. There are two ways in, and both finish at the same activation step.

With BRAT (recommended)

Tip

BRAT is a free, third-party community plugin that installs and updates other plugins straight from GitHub. It's the simplest way to install Quire and keep up with new releases.

  1. Install BRAT: open Settings → Community plugins → Browse, search for BRAT, then install and enable it.
  2. Open Settings → BRAT and select Add beta plugin.
  3. Enter Dromena-xyz/quire, then select Add plugin. BRAT installs Quire and afterward checks the repo for new releases.
  4. Open Settings → Community plugins and make sure Quire is enabled.
  5. Open Settings → Quire, paste the license key from your purchase email, and select Activate.

Adding Dromena-xyz/quire as a BRAT beta plugin

By hand (you control updates)

  1. From the latest release, download main.js, manifest.json, and styles.css.
  2. In your vault, create the folder .obsidian/plugins/quire/ and put the three files inside it.
  3. In Obsidian, open Settings → Community plugins and enable Quire (turn off Restricted mode if prompted).
  4. Open Settings → Quire, paste your license key, and select Activate.

Note

Quire tells you when a new version is out, but never updates itself. BRAT can pull updates as they ship; installing by hand lets you decide exactly when Quire changes, which is handy in the middle of a draft.

Getting started

The New Quire project item in a folder's right-click menu

  1. Create a project. Right-click any folder and choose New Quire project, then give it a name. Quire makes a fresh project folder for it. A project can sit anywhere in your vault, but not inside another Quire project.
  2. Open the Quire pane. Select the Open Quire ribbon icon, the open book. Your project and its scenes appear on the Scenes tab.
  3. Add and arrange scenes. Type a title into the New scene field to add one. Drag a scene between two rows to reorder it, drop it onto another scene to nest it as a child, or drop it below the list to move it to the top level. Right-click a scene for Outdent/Indent if you'd rather move one level at a time. Select several scenes (modifier-click, or Add to selection in the menu) to move, nest, delete, or ignore them as a group, children included.
  4. Write in Galley. Right-click a scene and choose Open in Galley to write it and its children together as one continuous document, or select several scenes and open those as one. Your edits save back into each scene as you go.
  5. Compile. Switch to the Compile tab, choose or build a workflow, and select Compile. Quire writes the finished manuscript into your vault and tells you where it landed.

For a closer look at each feature, see the documentation.

Coming from Longform?

Quire imports your existing Longform projects. Run Import a Longform project from the command palette, or open Settings → Quire and select Import a project under "Switching from Longform." Quire finds your Longform projects and brings them in without changing or deleting anything Longform owns. You can copy a project into a new folder, or add a Quire index in place next to the Longform one. Either way Quire shows you exactly what will happen before it writes anything, and a copied project's Longform drafts come across with it, as Quire drafts inside one project.

Where your license works

One license covers five activations, where an activation is one vault on one device. For example:

  • One vault synced to your laptop and desktop uses two.
  • A second vault, kept apart from the first, on that laptop uses a third.
  • Those two vaults on a third machine use the last two.

Quire ties an activation to a vault and a device because that's the granularity Obsidian gives a plugin for storing a license securely. The key lives in that vault's own secure storage, on the machine where you activated it, and Obsidian doesn't carry it between vaults or machines. So syncing or sharing a vault's files never spends an activation on its own. Opening that vault on a new device is what does. Done with one? Deactivate it from that vault's Quire settings to free the slot.

Requirements

Obsidian 1.11.5 or later, on macOS, Windows, or Linux desktop.

Note

Mobile is on the roadmap, not in this release. We want it to work cleanly with Quire's per-device licensing before we ship it. See Roadmap.

Roadmap

Quire launches lean and keeps growing. The goal behind every release is to bring what writers love about Scrivener into something fully Obsidian-native, built on notes. Some of what's ahead:

  • Mobile. Write on phone and tablet once we can support it without the licensing quirks noted above.
  • An account page. Manage your license and devices from the web, not only from inside the plugin.
  • More compile power, and closer parity with the tools writers come from.

Lineage

None of this is a new idea, and that's a compliment to the writers and tools that arrived first. Apps like Scrivener taught a generation to work in scenes, draft them together, and compile the result. Longform brought that way of working to Obsidian and carried it for years as a free, open-source labor of love that plenty of us, this author included, wrote real words on.

Quire owes Longform a real debt. The scenes-as-files model, the index that orders them, compile as a stack of small steps: that shape is Longform's, and Quire carries it forward. The code is its own, written from scratch in Svelte 5, but the lineage isn't something to paper over.

Where Quire goes its own way: Galley, a Scrivenings-style editor that writes back to every scene at once; scenes that nest as parent and child, so structure travels on reorder; and being a paid product, which is how a tool like this stays actively maintained (a lot to ask of volunteer time alone). A few familiar touches make their own calls, too; a running word count isn't in Quire today. Real gratitude to what came before, and to the writers still using it.

Support

Found a bug or have a feature request? Open an issue on GitHub. For anything to do with your license or a payment, reply to your purchase email.

Privacy and network use

Quire is local-first. Your writing stays on your machine: it never sends scene text, file names, or any document content anywhere, and it collects no analytics, telemetry, or tracking of any kind.

It uses the network for three things only: buying or activating a license, the occasional license re-check while a subscription is active, and asking GitHub whether a new version is out. A one-time license validates once, at activation, and never again on its own. Everything else works fully offline.

A license check sends only what's needed to confirm the license, never your notes. Your license is kept in your computer's secure storage rather than inside the vault, which is why syncing or sharing a vault never shares your license along with it.

A paid license is required for full access; activation lives in the plugin's settings. The full specifics are in the privacy policy.

License

The contents of this repository, and all artifacts attached to its releases, are released under a proprietary license. Source lives in a private repository. Use of Quire is subject to the Terms of Use.