:do.search.hypothesis.faceted~local-first

dweb

https://hypothes.is/a/vKsdGAREfGnmhyIpWeWQ

dweb

research~local-first

local-first cyberpsace

re-use, re-purpose, refactor, exapt, revise, extend

for: IndyWeb

hosting servers

local-first

WwbXR flips it on it's head

l1cs

This objective deserves a

new design approach to software, a "reverse design" approach that starts from the value driven objective of local-first, offline first approach that helps to "Lock the Web Open" and make it

• human centric,

• instead of being provider centric, that

• for the benefit of the participants in the long tail of the internet

• instead of big tech

• maximize autonomy for people

• scale their unenclosable reach

• helps them to find the Other and collaborate

• private, permanent custody of all their data

• along with the open commons based peer produced capabilities that they make use of

• facilitating interpersonal trusted secure communication

• unenclosable carrier

• and ownership of the means of computations interaction

Detailed Summary

1. You own your data, in spite of the cloud.
Section summary:
Local-fist software tries to solve the problem of ownership, agency and data lock-in present in cloud-based software, without compromising cross-collaboration and improving user control.

Section breakdown
§1: SaaS
Pros: Easy sync across devices, real-time collab Cons: loss of ownership and agency; loss of data is software is lost.

§2: Local-fist software

• Enables collaboration & ownership
• Offline cross-collaboration
• Improved security, privacy, long-term preservation & user control of data

§3 & §4: Article Methodology

• Survey of existing storage & sharing approaches and their trade-offs
• Conflict-free Replicated Data Types (CRDTs), natively multi-user
• Analysis of challenges of the data model as implemented at Ink & Switch
• Analysis of CRDT viability, UI
• Suggestion of next steps

2. Motivation: collaboration and ownership
Section summary:
The argument for cross-device, real-time collab PLUS personal ownership

Section breakdown
§1: Examples of online collabs
§2: SaaS increasingly critical, data increasingly valuable
§3: There are cons
§4: Deep emotional attachment to your data brings feeling of ownership, especially for creative expression
§5: SaaS require access to 3rd party server, limitation on what can be done. Cloud provider owns the data.
§6: SaaS: no service, no data. If service is shut down, you might manage to export data, but you may not be able to run your copy of the software.
§7: Old-fashioned apps were local-disk based (IDEs, git, CAD). You can archive, backup, access or do whatever with the data without 3rd party approval.
§8: Can we have collaboration AND ownership?
§9: Desire: cross-device, real-time collab PLUS personal ownership

3. Seven ideals for local-first software
Section breakdown
§1: Belief: data ownership & real-time collab are compatible
§2: Local-first software local storage & local networks are primary, server secondary
§3: SaaS: In the server, or it didn't happen. Local-first: local is authoritative, servers are for cross-device.

3.1.1 No spinners
SaaS feels slower because if requires round-trip to a server for data modification and some lookups. Lo-Fi doesn't have dependency on server, data sync happens on the background. This is no guarantee of fast software, but there's a potential for near-instant response.
3.1.2 Data not trapped on one device
Data sync will be discussed in another section. Server works as off-site backup. The issue of conflict will also be discussed later.
3.1.3 The network is optional
It's difficult to retrofit offline support to SaaS. Lo-Fi allows CRUD offline and data sync might not require the Internet: Bluetooth/local Wi-fi could be enough.
3.1.4 Seamless collabs
Conflicts can be tricky for complex file formats. Google Docs became de facto standard. This is the biggest challenge for Lo-Fi, but is believed to be possible. It's also expected that Lo-Fi supports multiple collab.

TBC

proritize local

• storage
• networks

interpersonal computing

• local first
• offline first
• async eventual consistent replication
• real-tim when participant are available

dream space

• conversations that are continuous- without being syncronous

yet

• contiguous and
• eventual consistent

with the partiipant's entire

• HyperInterPlexed
• interpersonal
• named
• permanent
• evergreen indranet.work spaces

-

It is possible to create software

• that has all the advantages of cloud apps,
• while also allowing you to retain full ownership of
• the data, documents and files you create.

Local-first software

You own your data, in spite of the cloud

Truly seminal paper, best of class

used Orbitdb 6 years ago

It did seem to work perfectly

namedlocal first replicated databases

allyouneed it seemed back in 2018

All time most important web paper

Al saber los riesgos de confiar plenamente en una plataforma, recordar ser recursivos creando copias de seguridad que nos brinden tranquilidad

Comparto la idea de que, aunque la información que almacenamos en la nube esté en Internet, sigue siendo nuestra y está protegida por nuestro derecho a la privacidad. Por lo tanto, a pesar de su ubicación digital, la privacidad debe prevalecer.

ejemplo de lo que exactamente hacemos en la sesión colaborando con diferentes puntos de vista y comentandolo

Production of explicit knowledge

la importancia de un CRDT en la creación de un software

from : https://hyp.is/VavmcmdsEe6r09ueLwuRvg/github.com/orbitdb/orbitdb/tree/helia

top rated - Essential Learning

by https://opencollective.com/open-learning-commons/projects/indy-learning-commons

tablet for thinking

to :

for people, individuals, not user looser

autonomous Actors in their own(ed) networks

built from trust for trust

CRDT data structures that are

• multi-user from the ground up while also being fundamentally local and private. CRDTs have the potential to be a foundational technology for realizing local-first software.

local-first include

• the ability to work offline and
• collaborate across multiple devices,

while also improving the

• security,
• privacy,
• long-term preservation, and
• user control of data.

despite of the cloud

这一个 part 就是在讲现有的工具和技术无法满足前面设定的要求

可以跳过

不需要依赖特定的网络载体

这不总是对的

SaaS 的速度问题主要在于加载速度，对于笔记应用来说，在不同笔记直接切换的速度，SaaS 和 local-first 有相当大的差别

Often over looked in historical research it is important to collect local first hand accounts or family retellings of historical events. While they are not always accurate they can help show from what perspective did the people of that time made their desicions from and what impact certain events had on communities after they occered.

2026-01-29

Peergos+IPF/NS interplay is getting clearer and how it can result in local first Universal Resource Names that are amnable to the PUN to be use dto actually retrieve them

The key to this is tha anyone can run IPFS Gateway locally in their own browser

This would server as a nice minimal viable exemplar of

• open
• commons based
• local-first
• person-first
• permanent
• evergreen
• inter
  • personal
  • planetary

networked co-laboration initiated n the annotation margins

with a mutually beneficial interplay between the Centralized Web and the permanent interplnetary Autnonomous People Centered Web, the emergent alternative: IndyWeb

<3

Para Cardumem el enfoque, como he dicho en otros lados es diferente, eligiendo una arquitectura federada, que incluye los servidores ejecutándose localmente y con menores complejidades arquitectónicas.

Una arquitectura donde cada cual pueda fácilmente descargar y ejecutar un servidor completo y comunicarlo con otros, es para efectos prácticos una arquitectura federada, con la posibildad de convertirse en P2P.

Una arquitectura federada/P2P no es garantía de descentralización, como vemos pasó con la web, diría yo debido a la dificultad de montar y desplegar servidores. Y si bien se ejercen fuerzas extremas de centralización sobre sistemas como el correo electrónico y los podcast, estos continúan siendo federados. Además, el fediverso ha adquirido un nuevo auge tras la compra de Twitter, pero enfrenta sus propios desafíos.

Diría que se requiere no sólo una manera frugal de poner a funcionar la tecnología, sino de disponerla a terceros para sus usos colectivos. Acá pareciera ser que el cuello de botella es el hospedaje y habría que mirar cómo hacerlo barato y amigable.

A menos que cada uno tuviera su propio servidor y los servidores centralizados fueran usados sólo para coordinar comunicaciones, como ocurre con Fossil y ocurrirá con Cardumem. Así, la centralización ofrece conveniencia pero no usa asimetría fundamental de capacidad o poder, como ocurre actualmente y servicios/protocolos de descubrimiento de servidores podrían ser implementados sobre la infraestructura cliente servidor actual, en caso de que algún servidor sea dado de baja.

Acá hay transiciones en los siguientes cuadrantes:

Cardumem toma una ruta alterna y más sencilla para explorar transiciones similares.

1. Inicia por el wiki, como software documental asíncrono.
2. Se conectará con HedgeDoc como software documetal síncrono.
3. Se conectará con Hypothesis como software dialógico asíncrono.
4. Implementará progresivamente funcionalidades síncronas vía sistemas hipermedia en tiempo real.

La idea de local primero ocurrirá debido a que el servidor puede correr de manera local o remota.

But we must have all, available local-first yet omni present ready to share and collaborate autonomously. Tha tis the promise of IPFS

local first

person-first

and

self-hosted

the future of HyperText is HyperPlex

Hypertext Mark Up Language

HyperPlex Mark-in Notation HPMI

reimaginging HTML

local-first person-first self-husted autopoietic

Open commons based

Peer produced

Extendable

Integral Omnioptional omnipresent

emergent Open Stadards

not just open source

but Open Constructs

embodied Open de factor co-evolutionary Standards

liveing lively organicallly vo-evolving

field of emergent practices self-describing self-explicating

= local-first-reflections

auto-nomous/poeietic permanent evergreen interpersonal social networked intentionally transparent conversational structures and colaboration and ownership for users

Blocked by Firefox from becomming a stadard

WebSQL it was called

to https://developer.chrome.com/blog/sqlite-wasm-in-the-browser-backed-by-the-origin-private-file-system

lucid CID WebTils

layer gossip hub

service worker gatewy

static website service worker

• local-first,
• person-first,
• autonomous,
• evergreen, -verifiably attributed,
• interpersonal,
• named networked
• co-evolving ,
• emergent,
• massive multiplayer,
• collaborative
• mutual learning by doing spaces

Weaving the Mutual Indy Learning Commons

Not just Open Source

but Open Sauce

con-structs/stellations for

• One Player-first
• born Multi Player
• cascades of scaling

where computer support for individual work

• is itself considered to be born collaborative,
• where 1 player collaborates with their past selves

born InterPersonal

• In-fo/fra-structures

that constitute and support

• local-first -Web/Browser Native
• InterPlanetary
• Permanent
• Evergreen

named massive multiplayer

• social networked dedicated Colaboratories for

• individuals their connections and everyone who encounters their work and able to connect and have conversations that are continupus wihout being synchrionous and contiguous with the particiants entire work spaces

• communities

and networks of networks of those

Not just Open Souce

but Open Sauce

• con-structs/stellations for

• One Player-first

• born Multi Player

  • where computer support for individual work is itself considered to be born collaborative, where 1 player collaborates with their past selves

• InterPersonal

• In-fo/fra-structures

  • that constitute and support

• local-first

• WebNative

• InterPlanetary

• Permanent

• Evergreen

  • named

• massive

• multiplayer

  social networked dedicated Colaboratories for

• individuals and

• communities

• and networks of networks of those

Weaving the Personal First interpersonal IndyWeb of

Open Sauce con-structs/stellations for Person-first InterPersonal In-fo/fra-structures that constitute and support local-first WebNative InterPlanetary Permanent Evergreen named massive multiplayer social networked dedicated Colaboratories for individuals and communities

Back to the Past

With Personal digital Assistants Palm delivered a sweetspot.. with 1000 fold smaller computing resources it created Personal Mobile computing

where every app used the same storage mechanism

the index gives you a place to note an item's location

Flip that

Give any 1 a

• singular
• private
• local-first
• named digital workspace

that is accessible from all 1's devices to keep all information that 1

• creates
• curates
• gathers. engages with, drawn form across the web
• to keep capture and save in your own space
• keep around for the long term
• everything that 1 pays attention to and engages with on the web.

Keeping track of where they were found as provenance of information ingested

instead of creating an index

name them and connect them to other named items of information in your won space so that meaningful indeces witll emerge thorugh engagements

providing a personal dynamic, emergent, HyperMaps of all information in the context of relevant activites, pursuites and engagements,

ready to share and collaborate on with others

local-first No Server, No sign in, No sign up

control your data

control your destiny

https://hyp.is/ExUYsOEaEe6IHYM1bUkGyQ/book.peergos.org/overview/overview.html

Peergos

is building the next web - **the private web, where end users are in control. **

your private online space

Peergos

motto

encrypted and to end and local first

https://stopa.io/post/296

Certainly! Here’s a summary and key insights from the article "A Graph-Based Firebase" by Ivan Stopa.

Summary: "A Graph-Based Firebase"

The Problem

Modern, delightful apps like Figma, Notion, and Linear share three standout features:

• Optimistic updates (instant UI feedback)
• Multiplayer collaboration
• Offline mode

Building these features is hard. Most frameworks and databases don’t make it easy-especially when you want all three together.

Existing Solutions & Their Limits

• Firebase: Great at optimistic updates, offline mode, and reactivity. But it falls short for complex data relations and permissions.
• Supabase & Hasura: Support relations (thanks to SQL/Postgres), but lack robust local/offline abstractions and have limited permission systems for complex apps.
• Custom Architectures: Apps like Figma/Notion/Linear end up building their own stack: normalized in-memory stores, custom permission layers, manual syncing, and more.

The Core Insight

All these apps end up re-inventing a kind of database, but one that works both locally (in the browser) and remotely (on the backend), with:

• Graph/relational queries
• Expressive permissions
• Built-in reactivity, offline, and optimistic updates

The Proposed Solution: Instant

Ivan and his co-founder built Instant: a graph-based, Firebase-like platform with:

• Triple store backend (instead of SQL), enabling flexible relations and recursive queries.
• Datalog-inspired query language (instead of SQL or GraphQL), for nested, relational data.
• Unified local/remote architecture: The same query/mutation language runs in the browser and on the server.
• Expressive, Facebook-like permissions: Functions for allow/deny rules, not just boolean expressions or row-level policies.
• Lightweight and easy to start: No heavy schemas or large client libraries.

Why Not SQL?

• SQL is heavyweight (1700+ page spec), not optimized for nested/recursive queries common in UIs.
• Frontend needs nested data, but SQL returns flat rows-requiring GROUP BY, JSON hacks, or complex post-processing.
• Implementing full SQL reactivity and sync is overkill for most app needs.

The Vision

A new abstraction-something like a graph database in the browser-could make it dramatically easier to build fast, collaborative, offline-capable apps. If the local and backend database speak the same language, you get:

• Real-time sync
• Optimistic updates
• Offline support
• Powerful, maintainable permissions
• Simple, nested queries for UI

Key Takeaways

• Modern app UX is a database problem: The hardest parts of delightful apps (speed, collaboration, offline) are really about how data is managed and synchronized.
• Existing tools force trade-offs: You can have relations or offline support, but not both. You can have permissions or reactivity, but not both.
• A new kind of database abstraction is needed: One that combines the best of Firebase (local-first, reactivity) with the best of SQL/Graph (relations, permissions).
• Triple store + Datalog is promising: It enables flexible, nested queries and is easier to make reactive and local-first than SQL.

If You’re a Developer…

• If you’ve struggled to build fast, collaborative, offline-friendly apps, you’re not alone.
• Watch for tools like Instant (or similar local-first, graph-based databases).
• The future of app development may look a lot more like building with a distributed, reactive, permissioned graph database-on both client and server.

Let me know if you want a deeper technical breakdown, a comparison table, or actionable recommendations for your own projects!

Citations: [1] A Graph-Based Firebase https://stopa.io/post/296 [2] A Graph-Based Firebase https://stopa.io/post/296

Oerweb Pillar

• the Peronal first Local First interpersunal Web the IndyWeb

A respiratory virus that causes rashes and fevers

Easily preventable disease with vaccinations

Could be because of the anti-vaccine belief becoming more popular during and after COVID

The most north east county in Ohio

Summary of JavaScript Frameworks - Heading into 2025 by Ryan Carniato

General Reflections on 2024

The pursuit of simplicity hasn’t simplified web development:

"The quest for simplicity hasn't resulted in making web development simpler."

Despite advancements, the overall complexity of web development persists.

Economic pressures have led to a cautious approach:

"Global economy tightening budgets and keeping solutions on the safe path."

The industry has recognized that complex problems have no silver bullet solutions.

A call for reflection and reassessment:

"It is a sobering thought but it gives me hope in 2025 that we can take some time and re-evaluate."

Returning to fundamentals has shown the need for a better balance.

The Server-First Movement

Resurgence of server-first frameworks:

"Making things 'server-first' has been the narrative over the last 5 years in the front end."

New meta-frameworks (SvelteKit, Astro, Remix, SolidStart, Qwik) and upgrades (Next, Nuxt).

Tension between SPA and MPA models:

"SPA-influenced isomorphic approaches up against MPA-influenced split-execution approaches."

New technologies such as Out-of-Order Streaming and Server Islands emerged.

Complexity in feature integration:

"When you assemble all these features, things are not so simple anymore."

It remains uncertain whether these advancements are truly solving core issues.

Return to traditional server approaches:

"Not wanting to wade through this mess, has led the conversation back to more traditional server approaches."

Server-side rendering (SSR) is being reconsidered, despite its lack of novelty.

Compilation as a Core Component

The role of compilation in modern development:

"Compilation is an ever-present aspect of JavaScript development."

It addresses shortcomings, improves performance, and introduces new capabilities.

React and Svelte’s contrasting compiler approaches:

"On one side we have the React Compiler... on the other, you have Svelte 5 Runes."

React optimizes re-renders, while Svelte adopts a fine-grained signals model.

Increased complexity due to compiler-driven optimization:

"Both choices come at the expense of increased complexity in tooling."

The trade-offs between simplicity and capability continue to evolve.

AI and Development Tools

AI's growing role in developer tooling:

"AI's impact on JavaScript frameworks themselves is still minimal."

While AI aids prototyping, it has yet to revolutionize core development.

AI-assisted performance optimization:

"MillionJS developer Aiden Bai got our attention again with React Scan."

Tools now analyze apps for re-render issues, though challenges remain.

Shift towards integrated AI support:

"Supporting tools rise up to meet that."

Projects like VoidZero suggest the future of integrated AI development workflows.

Emerging Trends for 2025

Pendulum swinging back to SPA-friendly approaches:

"We already have started seeing some of the swing back of the pendulum."

Frameworks like SvelteKit and SolidStart now offer SPA modes.

Local-first and sync engine technology gaining traction:

"How that is to manifest itself is still left to be seen."

Sync-first approaches may play a larger role in future web applications.

Slow and steady adoption of stable frameworks:

"Both Vue and Angular are frameworks I'd have my eye on this next year."

Reliable, well-supported frameworks remain attractive in uncertain times.

Challenges in adopting signals-based architectures:

"Developers are starting to understand the depths of tradeoffs present."

While signals improve performance, they come with complexity and learning curves.

Final Reflections

No major technological leaps anticipated in 2025:

"I'm not predicting some big technology leap in the next 12 months."

The focus is on refinement and thoughtful development.

Complexity remains a persistent challenge:

"We live in a world full of complexity and that doesn't appear to be changing."

Balancing complexity and usability is an ongoing struggle.

Encouragement to tackle interesting problems:

"Between you and me, this is the type of environment I thrive in."

Developers are encouraged to embrace problem-solving in a complex ecosystem.

This summary captures the key insights from the article while preserving clarity and depth, offering a comprehensive understanding of the current state and future outlook of JavaScript frameworks.

Hey @ConsilienceProject what would you all do if you had control of the Media? Ever ask that question? What kind of Consent do you want to Manufacture.

portable components

move freely

stay in sync

once you do that IndyNet should provide you local first personal IPFS gateay

gateways nullify

best.for - ipfs gatways nullifify

• IPFS

bets.for - Peergos

Peergos's true value is

• creates human meaningful names wowen in a

named trust networks of humans

combined with

human meaningful named networks of

• interest,
• pusruits,
• auto poietic nomous capabilities
• externaizations of human inter

in a local first, Open source local first

server based info-communication-capabilitiy-conersations service infrastuture where the "servers" can be operated locally but with global reach

can act as IPFS gateways that are unenclosable and unstopable private cariers themsleves

The vision for the IndyWeb

Interpersonal computing on the Autonomous Interpersonal Web

we

• the We here is presumably refers to corporations. on the IndyWeb people cn do it for themselves

start to link these computers together with sophisticated networks and great user interfaces,

• sophisticated user inerfaces, yes,
  • but those interfaces will be malleable born interPlayeable, MultiPlayer from the outset yet private, and local-first

we’re starting to be able to create clusters of people working on a common task — literally in 15 minutes worth of set up

offline first local first

no server

real-time multiplayer

composer

an extensible app platform where

developers can

• organize and sync their knowledge across their devices, and
• collaborate with others real-time or offline.

Open-source. Multiplayer. Local-first. Private.

not just distributed but personal first, local first, interpersonal interest based autonomous social networks

for

• hyperpost

Decentralization is a decent shifting of the Cenetralized Paradigm

permission less innovation is a clear advance

We could Flip the paradigm by pursuing

local-first, Personal first, Centrered InterPersonal Info-Intercommunication in Open Mutual Learning Networks

where each participant in the network is empowered to "serve" their own(ed) content with edge/browser native capabilities in the long tail of the internet to go with them There by become Autonomous participant in their owned trust networks that operate for the benefit of the participants not the aggregators, with full attribution, verifiable provenance for all their mutual contributions and recapitulate-able history and co-evolution of ideas and innovations themselves.

In a word it supports attributed open innovation accelerating innovation and all associated value flows.

Leaving no scope for enclosing carriers to introruced permissioned recentralization as the system is based on trust and mutual permissions

bad actors/aggregators can simply be locked out

and create the space for 1000 aggregators to emerge as interest based autnomous communities mutually scaling reach for everyone

since global permissionless discoverability and permanence can be baked into the the very fabric of IndyWeb

Gien is talking about Indyweb - a Web 3.0 stack In contrast to central servers - (broadcast) Indyweb = small trust networks (no limits) People centred Interpersonal Local First Information owned by PERSON and stored locally Give people permission to others to share Assign trust levels to different people Surf web - store locally - visiting sites as a PROCESS FB and LI stores YOUR search on THEIR server Store my own queries - as a constellation MindPlex is a current name External representation of a digital life - recorded and locally Network the mindplexes together We each have our own Mindplex Our own salient ideas Share parts of our network that are SALIENT We share information Interpersonal communications channels Indyweb - SW development project - Douglas Engelbart - Ted Nelson - transclusion - Vannavar Bush - Memex - Guyrie has a phd around these ideas INformation commons

IDK I tried playing with Solid, and it is a little too hard to get up and running. And the apps don't really work dokie.li.I am looking at you

Interoperability is the key

Open interoperable and ubiquitous

Interpersonal Computing

Intentional Autonomous Personalize-able Software local-first Personal first interpersonal conversations that are continuous without being synchronous

contrast that with BigIdea

Presentational State Transition with Human Actor in the Loop

not automation people centered interactions

instead of transferring state

transition state for the User By the User and communicate

self-coherent, consitent complete states in a local first offline first Named Info Storage

That is globally accessible

Put the User into the picture

with local-first offline first owned

State undergoing Represenatationsl State Transitions

Not transferring stateless represenations of a state

What a hopeless idea that was

on the page that it effects

intentionally transparent coherent, meaningful state transitions tat are themsleves immutable ind linked

bnoth in chronological term and with everything else that b ares upon the transition

unconstrained invocation of recorded permanent verifialble code and information connected to the Human Actor's responsible for creating holding them

memex moving to the cloud from local first

follow up

BitTorrent + Markdown + Native UI + Content Authoring = Local-First Web

great

Offline first

local first

Observable says files are where modern development is focused. Because it aids the agency of the user of their tool, mostly through interoperability. This is [[Technologie kleiner dan ons 20050617122905]] en [[Local First Software 20190531162132]]

A great article on the history of reading online that might just nudge me into trying out and eventually becoming a Reader paid subscriber.

Great. I love this local-first, Markdown-based design.

I'm a bit surprised at the conclusion: Evernote still the best and can't be supplanted easily. Seriously?

But there are some naked truths about Tana and Mem (and Mem X). The Second Brain guy didn't mince words.

I think he is too harsh on Obsidian. You can't have your cake and eat it. If local-first philosophy is of utmost importance to you, you've got to learn where the vaults are stored locally. Duh!

Welcome to ODD SDK!

ODD SDK is Fission's true local-first, edge computing stack.

ODD SDK empowers you to build fully distributed web applications with auth and storage without needing a complex backend. To learn more, check out the ODD SDK docs.

Dialog is a work-in-progress

• strongly eventually consistent data store

that combines

• content-addressable storage,
• the rich distributed query semantics of Datalog, and
• the flexible security model of cryptrees.

It builds off of existing ideas from the WebNative SDK

• to empower developers
• to build new types of local-first applications.

Events to the rescue?

Should not bake a server into a lofi software as a mean to sync. It needs to outlive the server.

URLs as collaboration sites been found handy.

They could be treated as "compilation sites" on a subject.

Where each user could have their own compiled view.

I.e., they are IDs of subjects. Note: ID not= content. Content is user-specific. A personal compilation / view on it.

Would it be valuable to have it generic?

Same time-travel interface for all the apps.

The mentioned "one user sets state on a task to one state and another to another" happened. As mentioned, it's not clear how to resolve. So they did encounter merge conflicts. I guess these conflicts are not app-specific and conflict resolution can be implemented in a generic way as well. Such as present users with choice which delta to adopt.

CouchDB is a meh local-first backend (storage).

Rather "thick-client local-first apps". As "thick-client" on it's own does not imply local-first, there may be a server.

Web apps can be thick clients.

Optionally they can be loaded gradually. E.g., with granularity down to components, as shown by ReactJS.

Having loaded the entirety - they can potentially work offline.

Making web app and its components content-addressable would allow to load them with no regard to location / some authoritative service.

Local Storage is not a good solution for persistence.

Sending git diffs as text over emails or other medius is the way it's been meant to use, if I'm not mistaken.

I.e., software engineers may be best keen to adopt lofi concepts.

Because it captures snapshots and not deltas.

There is no "shared master branch" in git. Subsequently, no authority that decides what's in it. Each git user is free to adopt any changes they see fit.

In an event when the sync service is down and you lose local copy - you won't be able to restore.

For this case it's better to have multiple sync options. Such as your other devices and incentivized third-parties.

Whereas it is the opposite in reality. Devices are the primary sites of intent they issue. And server is merely an aggregation site.

Given email is signed.

Git alone does not dictate how one transfers stuff.

Loosing a PHD paper, especially after it has been published and some other papers already referred to it / based their reasoning on top of it, would be a serious hit to humanity's knowledge. Sadly, this is the reality today, may happen.

Would be nice for lofi software to make it as seemless as replicating across chosen parties automatically.

E.g., in your account you linked your devices, and chosen them as replication sites. In addition you chosen a third-party, e.g., Web3Storage.

So you can use apps and rest worry-free about persistence of your data.

Even better if software uses known data model, such as RDF, and so you're not locked onto the tool.

Perhaps even better to capture your intent as events and have data models derived out of it. This way you're not even locked at e.g., RDF ecosystem.

I.e., don't rely on third-party as a medium to express yourself. Otherwise they're in control what you can express.

E.g., Twitter/X, Google Docs and their bans.

I have dread in my head every time I use cloud service that there is an issue about to happen. There will be a data breach, data loss, service becoming unavailable (e.g., they don't like you anymor, e.g., Github can block you from your private repos at their will), it's just a matter of time.

So I need to get my data out, back it up, if service been kind to allow for that. But that's a burden. It's a hidden cost you learn to recognize over time. May not be apparent from the start to everybody.

This needs explanation.

This stems from the design that there is a mutable place and some authority over it. E.g., a Google Doc, Wikipedia page.

Would be nicer to embrace people as primary sites of their intent. And allow to compose them. This way a person who would previously need to request changes to a doc, would simply have a kind of forked doc locally, where he would make the change. And that delta may be shared with the original doc's authors, who may accept or reject it. With no regard to their decision, the forked version stays as intented, with the delta.

I.e., docs are sites that aggregated some deltas. Have a site per person. Allow sites to exhcange deltas. This allows for having personal views on a subject.

Akin to how it's done in Git. If only it tracked deltas and they can be arbitrary.

I.e., NextGraph gets it pretty damm right.

Also RhizomeDB is this spirit.

For the cases when you do wish to send op to a remote party you'd still need a spinner. Given you embrace distributed compute.

Local-first has most responsive UX due to operations being performed locally, as opposed to sending them to the server.

Optimistic UI / Optimistic Updates may actually fail at the source being updated (suprise-suprise, the word "optimistic" is in the definition).

SQL may not be that familiar for web devs.

GraphQL and dot.notation is what they're used to.

Have authority to sign / process updates.

I.e., there's an authority, e.g., a shop, and it would need to process requests.

What the architecture can do is to abstract from URLs/exact endpoints, having ID of the authority instead, and abstract away transport layer, i.e., nodes in network talk with each other and we don't care how, all we care is expressing intents in data and they get passed around somehow.

Iniciar desde un enfoque local respecto al idioma, con la visión de ser una comunidad más amplia, sin limitar la participación de contribuir en inglés, al contrario, invitando a la participación de la traducción del documento

local first

I've been following the work of inkandswitch, an independent research lab for the past 4 years, Attended two of their presentations at Fission Show and Tell calls. I encountered their work on Local-first software a year after I've discovered OrbitDb as the best in class technology for developing personal first interpersonal networked thinking tools. It was great to see other people converging on the same possibility

much of their output presents a systematic treatment of the same problems that we are working on

This is a comprehensive proof of the idea that problems define their own solutions

As I am engaged in bringing into a coherent working system all these ideas I find it helpful to revisit their work.

Building on this work is accelerating our work as it allow us to focus on articulating those aspect of our current work that goes beyond theirs and incorporate and reference much of their work and make contributions that accellarates the development of shared goals.

local-first

app that is loyal to them

Capstone A tablet for thinking

Capstone is an experimental tool for creative professionals to develop their ideas. It explores questions about digital information curation; how creative people come up with good ideas; and what we at Ink & Switch think the future of power-user computing interfaces could look like. from : https://hyp.is/MpzzIGdwEe6qCavKpwgKcQ/www.inkandswitch.com/local-first/ by

local-first

to : https://hyp.is/ZXL96GdsEe6iOWPdHxYGKg/www.inkandswitch.com/local-first/

security token offering

//

This is a call for the interpersonal indy.net where people are autonomous actors in their ow(ed) local first, private first, offline first, evergreen, interpersonal trust networks

If this is a 'return to the web' as stated then why a new protocol? The web already has its protocols. Creating your own for your app and saying well if the app goes the protocol is still there for you to build your own is exactly what silo's like Evernote also did (there's always our own xml-based export format, you're not locked in, and they actually are not wrong).

!- big idea : documents become virtual with MindGraph

• vision : IndyNet powered by TrailMarks
  • powered by IPFS
  • is to bootstrap a Global Giant Single
  • InterPlanetary, Permanent, EverGreen
  • Commons Based, Peer Produced
  • Co-Evolving,
  • Symmathetic Inetntional Graph
  • with People as the Primary Autonomous Actors
  • local first ownership of all their data along
  • with the evergreen capabilities they use
  • to create and interact with them
  • for (Inter)personal first
  • Collective Evergreen coevolutionary InterIntellect
  • where "documents" are virtual renderings of
  • curated,intetwingled, deep rearrangements of
  • intentional associative complexes
  • organized by TrailMarked Clues
  • as Thought Vectors in Concept Space
  • empowering People to roll their own(ed)
  • Autonomous Habitable Digital Spaces for their own
  • intents and purposes
  • leading to deep synthesis in
  • self-organizing emergent networked communities
  • where everything IS deeply intertwingled
  • People, ideas, articulations, knowledge of all things
  • with full provenance of reading and
  • inter personal conversations and actions
  • Ted Nelson's Dream Machine
    • Open Commons-based Peer Produced
    • Tinkerable, Inter(changeable|operable)
  • for 'User Liberation'
  • Bootstrapping a People Centered Software Internet
  • that works for People
  • empowering them to weave their own(eed)

Very nice

could make it offline first, local-first with IndyWeb and async

yes

Networked Thinking/Learning tool

Roam Research like but local first, Personal First

making it interpersonal on the IndyWeb

designing constellation for information creation/curation/conversational collaboration harnessing decen(tralized) protocols

decentralization shifts the parading from centralized silos to a decent/distributed modes, at the edges, where we, the people operate, with increase in autonomy.

But what is needed is to flip the centralized paradigm and put people at the center.

Interpersonal trust networks build for trust from trust,

Empowering individuals and communities to create their own

• autonomous digital spaces of their own

that are born interoperable with anything in that

• space of permanent hypermedia
• HyperDocuments,

that are

• local first,
• offline first for all participants

yet supports interpersonal collaboration in all collaborative modalities,

• real-(time,
• eventually consistent async messaging,
• continuous without being synchronous,

while maintaining

• full contiguity of their own personal/community work and digital engagements

independent of the tools they use for that purpose.

As the IndyVerse/Web/Net/Lab/Learning Commons is piloted at the moment

it also offers deep integration with

• web annotation services like Hypothesis and Memex, but any other system can readily be bi integrated (two ways) as plug-outs ready to be integrated into individuals' own(ed) workflows

the IndyWeb also makes use of TrailMarks (generalized into HyperMarks in the IndyVerse of Intentional Morphic HyperDocuments

that itself has 'Universality' in the sense of "Universal Machines'

providing a universal way of designating info structures on the fly, as one writes, and intended interpretation across hypermedia content decouple from the means that were used to create them Where documents are not considered enclosures but dynamic views in a global giant emergent permanent digital spaces

in the first place. Think of TrailMarks as a plain text Symmathetic Mark-In notation that can be added to any content unobtrusively along with the machinery needed to play this intentional/semanttic/symmathetic game

That's what the indyWeb/Net/Hub/Lab pilots

It aims to complete existing systems, including centralized ones.

Centralized system offer global reach, at the risk of censorship, decentralized systems are uncensorable but very limited in reach as they represent technical and other barriers to on-boarding.

On the IndyWeb that Flips the web from server/provider centric to People-centric

IndyNet offers zero friction on-boarding and proogressiver trust networks with potential eventually global reach where servi

for

• flipped web
• offline first

• determine what is urgent to me

bring to me in a form that I

• want

• when

• and how

• I store the app's data

  • local-first
  • offline first

• apps have to authenticate with me

• // better still have it available even offline with cryptographic guaranties of authenticity and versioning in a way that Apps can become Evergreen, future proof, born FAIR interoperable as all work on my own(ed) data!

• shape my own (not user) experience. coherent that works across all apps

• compose them to provide my own workflow

• bring the app to the data

  • // The Apps to me so I can compose my own Workflows

• have visibility and control over who sees my data

really should giver it a whirl at least for personal use

I want to understand how Cambria resolves this too. The dates are signifiers for breaking API changes... It seems to me that you wouldn't want anything other than a single linear migration path. Though I guess the argument here is for local first software where you may end up hitting a mix of newer and older version endpoints. The entirely tricky thing here is that it's easy enough to reason about what's a backwards breaking change but technically any new field becomes a forward breaking change. Resolving that seems like a challenge.

local "pocket infrastructures", which are simple, extensible, self contained, local first, and work in a wide variety of hardware and connectivity settings. Such pocket infrastructures will host, interconnect adapt and extend "The Kit" to Global South contexts and circumstances, starting with our local ones.

No puedes dar por sobre entendido que la gente sabe qué son las infraestructuras de bolsillo y, siendo el párrafo central de la propuesta, no está muy claro qué quieres hacer.

All the commentator would have their own(ed) local first, Personal first, offline first, interpersonal wiki both able to connect with others or even form their own interest based groups and social networks as their own IndyNet.

can't get :

mutual sovereignty

• no tools to embody power dynamic

• between - groups & individual

• sugerting :

• instead of power dynamics

• consider interpersonal connectivity

• trusted, but verifiable connections between individuals and communities

• with full permanent provenance of interconnections

• maintained by participants of emergent named peoples networks

• participating as autonomous actors

• local first, offline first, permanent, evergreen information means of procesing that information too

knowledge-work interoperability

across time and space

= IndyHub

• need constellations for that supports interoperabily all conceivable combination of time and space aspects

make all communication and storage affordances interchangeable

communication

• synchronous
• asynchronous

storage

• local first
• off line first
• private personal first
• open commons based globally discoverable
• online + private
• online + permissioned

- synchronous communication

= morphic

• make = graphic design - easier
• solve : problem - with = cross-platform usability

make the web :

• a boundariless
• people cantered ecosystem
• autonomous
• local first,
• off line first
• permanent
• interpersonal
• intentionally/meraningluffy/self-revealing
• networks of information and
• autonomous morphic collaborative hypermedia spaces at the edges, in the long tail completing and enhance the value of the existing web, while overcomming its limitations and problems

search = morphic

• for = morhic digital experiences over the web in autonomous interpersonal digitsl spaces at the edges
• completing the existing web

examples for : = the power of names = problems define their own solution

• as in morphic user interfaces
  • morphjc, lively, autonomous personal and collaborative digital experiences, with permanence and full provenance of evolution of ideas, connections and attention

= IndyWeb

• combine local first ownership of data across owned devices
• strong privacy guarantees with permanence

what is = The IndieWeb

• people-focused alternative to the "corporate web"

what - is = The IndyWeb

• inspired by the IndieWeb
• delivers all the values of the IndieWeb
• with zero friction onboarding
• completing the existing Web

bootstrapping :

• commons based,
• peer co-evolving
• constellations
• for webnative, local first apps
• at the edges

• an interpersonal autonomous network of networks
• build from trust for trust
• combine local first ownership with permanence
• full control of sharing
• scaling reach with
• full provenance
• personal custody of all contributions
• connecting people, ideas and webnative capabilities
• at the edges
• for the benefit of the participants
• not aggregatorsi

it - is : bootstrapped: on top of the InterPlanetary Permanent Hypermedia Protocol: IPFS - as

• commons based
• peer produced
• constellations
• for the future of the web at the edges

offers :

• boundless interoperability
• tinkerability
• plays nice with the exiting web
• aims to complete not to compete

all data is local first exists on user's own devices synced

the problem is:

• do not have great ways to connect blogs together

response :

• need to connect bloggers as individuals and communities first

weaving a

• local first
• offline first
• permanent
• interpersonal networks
• inter communities of care

eventually connecting everything :

• people
• communities
• ideas
• mutual learnings with full provenance
• conversations that are continuous without being synchronous

Virtual Documents - form = Permanent HyperMedia Spaces - that are

• local first
• private first
• offline first
• personal first
• interpersonal
• interplanetary
• permanent
• people centred
• networked - with
• verifiable provenance

referred to as = PermaMedia Spaces

*opi near, at against

vision = OpiDox

documents go :

• virtual
• networked : connecting eventually everything
• people : as autonomous actors in their own(ed) right
• ideas
• things
• machine capabilities

= hypermedia spaces - that are

• local first
• private first
• offline first
• personal first
• interpersonal
• interplanetary
• permanent
• people centred
• networked - with
• verifiable provenance
• open
• commons based
• peer produced
• high resolution (intent|meaning)fully addressable
• where the intent|meaning is situationally explicated
• along with the means of structuring, processing, interpretation and morphic lively presentation/affordances

= following - twitter : @holochain

• end-to-end
• open source
• p2p
• app framerwork

= creating = an ecosystem of apps - that are

• decentralized - with
• distributed
• user-controlled-storage

= constrast - with = IndyWeb

• open
• commons based
• peer Co-created
• emergent
• networked
• ambient
• ubiquitous
• born interoperable
• inter(personal|communities)
• build from trust for trust, but verify
• Intentional Constellations
• of
• multi-player
• evergreen
• local first
• off-line first
• end-end-encrypted conversational
• eco system of apps
• player controlled owned
• permanent
• private
• universal storage
• networked capabilitiies

• concept : far edge database for local-first apps

this is sure to happen when doing zero friction onboarding of local first, offline first, commons based peer produced permanent long tail software or PWAs

• related to : App Owned Login
• https://hyp.is/ucu7XExZEe2O7ucGgoCnhA/discord.com/channels/478735028319158273/790825713094754364/1014889315844767824

!- concept : Progressive Login

Nice to see that you are thinking about zero friction engagement and progressive on-boarding too. This is particularly appropriate in a webnative setting that is ultimately heading towards the long tail of software where the apps come to people instead of people flocking to apps.

Local first Sync

Instead of LiveProgramming

let's have local first, offline first, evergreen, trust networks of Inter (Personal|Planetary) Autonomous Intentional HyperMedia Spaces

powered by

• commons based
• peer produced
• Intentional Software Internet as a Conversation
• for the people, by the people
• built on trust, for trust

Very much inspired by SmallTalk's software internet

except that with IPFS the network becomes what used to be an isolated SmallTalk Image

• ecosystem
• on top of Holochain
• hosts and users

!- contrast : IndyNet

• IndyViDuals are Actors.
• host data coupled with capabilities needed to manage them
• local first, offline first and permanent on IPFS

!- flip : the Current Web

• no more silos

• All of People's data resides on their own devices

• or on the Permanent Web fully

• under their control

• forming networks of trust

• trust but verify

• full provenance

• recapitulalble history of exchanges

• capabilities as IndyApps and IndyComputations come to you, the actor, the inidvidual - instead of people flocking to them - accept take it or leve it terms - People set their own terms

universal reuse is an impossibility

reuse like use is situated pick an adjacent existing delivered use case

instead need to intentionalize conceptualize

symmathesize #Symmathesy Mutual Learning

common "use cases" and do that in a form that is amenable to be tinkered reused and repurposed for future purposes intents as they arise

in any situation there are core intents that are universal

ensure that "data" is captured along with the means of supporting those intents across all conceivable "constellations" for provisioning

ranging from local first, personal first, to in house closed silos to global interplanetary scales open or closed, taking into account delivery platforms desktop mobile metaverse whatever

https://hyp.is/xb0pkOoSEeyRaQudeRD78g/www.linkedin.com/posts/alanmorrisontoday-i-attended-a-thought-provoking-conversation-activity-6940722530403983360-fCeE/?utmsource=linkedinshare&utmmedium=memberdesktopweb

who maintains? who has authority for changes, how to deal wqith paradox of choice?

multiplayer

need people themselves to be first class

local first data and use capablities that are swappable

collaborative local first applications

4 IndyWeb

personal first but interpersonal

(NB: this is in response to the question Why not just use wordpress + wysiwyg editor similar to *docs, and you're done?.)

This is a good of an explanation as any for local-first software.

A natural response (to potatolicious's comment) is, "Well, somebody has to maintain these no-code Web apps, too, right? If there's someone in the loop maintaining something, the question still stands; wouldn't it make more sense for that something to be e.g. a WordPress instance?"

Answer: yeah, the no-code Web app model isn't so great, either. If service maintenance is a problem, it should be identified as such and work done to eliminate it. What that would look like is that the sort of useful work that those Web apps are capable of doing should be captured in a document that you can copy to your local machine and make full use of the processes and procedures that it describes in perpetuity, regardless of whether someone is able to continue propping up a third-party service.

local-first

There's an unnecessary dichotomy here between uses JS and page is served as HTML. There's a middle ground, where the JS can do the same thing that it does now, but it only does so at edit time—in the post author's own browser, but not in others'. Once the post author is ready to publish an update, the client-side generated content is captured as plain HTML, and then they upload that. It still "uses JS", but crucially it doesn't require the visitor to have their browser do it (and for it to be repeated N times, once per page visit)...

local first but accessible globally

headline

decentralized publishing platform

this is great,I understand it is local first, and Personal first How about making it People centered by being able to act as their own hub in their owned network of connections forming interpersonal network connecting people ideas and communities in an emregent network of netwroks?

I've looked a lot into the file-saving problem over the years. Tom describes the problem in a succinct enough way:

Let’s say you’re building a graphics editor and someone can save their work as file.svg. If this were a desktop application, they could press ⌘s to save again. Or you might even auto-save to the file. You can’t do this on the web: every time you save a file, it’ll go through the same “Save as…” workflow, which asks you to choose a location and confirms if you overwrite an existing file.

The reality is that this is cumbersome, but it's not a showstopper. Any application author caring to let you run local-first applications where you own the data can do so.

The effect that the new file system API is likely to have is to see it abused to the point that lots of people lose even more control of their data and (because of that) others are wary of granting permissions at all, due to overbroad privilege requests. The status quo, even cumbersome as it is, is actually more of an enabler for user-controlled, local-first applications and strong data ownership "rights".

The API designers should step back from the current kitchen sink design for file access and narrowly address the specific ergonomics issues described in the quoted bit relating to ⌘s and file overwrites.

(One workaround that I've come up with to the file overwrite problem is to pack up opaque "checkpoint" files and educate the user that the correct way to work is to save them all to a common directory. You generate a unique name each time, so while even though the user must explicitly do a little bit of a dance with the system filepicker dialog, they are never prompted with the "[Are you sure you want to overwrite...?]" warning. The dance with the filepicker is also minimal, since the browser remembers the last location, so it more or less amounts to an explicit notification that the app is saving new data with an optional way for the user to seize control and write it elsewhere if they choose. When it comes time to open up a previous project, rather than picking a single file, they point at the directory containing all the checkpoint files. The app reads these in and reconstructs the state. [Side note: the ZIP format's internal data structures work passably for this. The concatenation of the content of all the checkpoint files files comprises the ZIP bytestream.] It sounds janky, but on reflection this is really only true because it violates some expectations about how things should work based on familiarity with other workflows. Doing things this way means also that you can get version history almost for free—something that otherwise takes a lot of intentional and clever design and generally only shows up in mature apps with lots of engineering resources. But, to repeat, using this "ZIP-chunks" approach, you get it as a byproduct of having to work within the constraints of the browser sandbox. Sometimes constraints are useful for creation.)

Meanwhile, not only does the scope of this tool not merit the Big Sur requirement, it doesn't even require a Mac. It interaction style is so free of intracies that it could be developed (and distributed) as a single HTML file with a text input and some script blocks.

This tool should be a "codebook"—a downloadable document meant to be stored in an offline copy e.g. on the user's local disk, a la PDF (except still actually HTML, as here). I shouldn't need to "go to" anywhere to use it; that should only be necessary to get it the first time.

I think this might need to be a principle of its own

https://getdweb.net/

Wordle's spread on social media was enabled in part by its low-tech approach for e.g. sharing scores.

One low-tech approach that could've been used here for data persistence would be to generate and prompt the user to save their latest scorecard in PDF or Word format—only it's not a PDF or Word format, but instead "wordlescore.html" file, albeit one that they are able to save to disk and double click to open all the same. When they need to update their scorecard with today's data, you use window.open to show a page that prompts the user to open their most recent scorecard (using either Ctrl+/Cmd+O, or by navigating to the place where they saved it on disk via bookmark). What's not apparent on sight alone is that their wordlescore.html also contains a JS payload as an inline script. When wordlescore.html is opened, it's able to communicate with the Wordle tab via postMessage to window.opener, request the newest data from the app, and then update wordlescore.html itself as appropriate.

local=first plain text

Desired workflow:

1. I navigate to the APL login page https://austin.bibliocommons.com/user/login
2. I invoke a bookmarklet on the login page that opens a new browser window/tab
3. In the second tab, I navigate here—to a locally saved copy of (a facsimile of) my library card
4. I invoke a bookmarklet on my library card to send the relevant details to the APL login page using window.postMessage
5. The bookmarklet set up in step 2 receives the details, fills in the login form, and automatically "garbage collects" the second tab

Some other thoughts: We can maintain a personal watchlist/readlist similarly. This document (patron ID "page") itself is probably not a good place for this. It is, however, a good place to reproduce a convenient copy of the necessary bookmarklets. (With this design, only one browser-managed bookmarklet would be necessary; with both bookmarklets being part of the document contents, the second bookmarklet used for step 4 can just be invoked directly from the page itself—no need to follow through on actually bookmarking it.)

开源、本地优先、基于 markdown 这三点貌似是现在的标配了

Sure hope that it interfaces with the networked notetaking apps (e.g. Roam) so that the search is interoperable across Roam/Readwise boundaries :-)

the fastest API call is the one you do not need to make

A good way is to go Go #WebNative with https://fission.codes/

https://twitter.com/TrailMarks/status/1349785654939496450

what if all you need is a browser and keep your data local first All Fission Powered up can share the data their create with any other app. Decoupling App from Data Storage making to user in control even authentication

turn a single player app to multi-player app with https://social.coop/@indiehub https://github.com/IndyVerse/indiehub

Local-First Software

• about : local first

CRDT fundational

Test

CRDT see OrbitDB

this is something I hadn't thought to explore before

I feel like this explanation is unnecessarily blurry -- there are good "not just the feels" reasons for wanting ownership of the data...

Local first is different to offline-first

local first webnative apps

trustless method suitable for

centralized, decentralized, peer-to-peer local first apps

gone native with fission

re-encrypted

very much, hence local first, lan first, Heirloom computing https://hyp.is/IzjKBGxKEeuz4dPtUumwUQ/thedorkweb.substack.com/p/the-100-year-computer

achieved through emergent spontaneous order arising from trust local first cooperation designed from trust using tech we can trust

Local First Development Data Agency

build WebNative People-centered decentralized born interoperable collaborative multiplayer Apps from local-first single player ones with TrailHub1

local first longevity

no bottleneck

writing to local first

eventual consistency

fair data

resistance is not futile

local first software

knowledge base sync with github

local-first software

local-first storecard

I have been considering blogging platforms long time ago. My criteria was different, but I care, as you do, about underlying tech stack, programming language and autonomy.

I have blogged about my blogging and these days I just use Markdeep with Fossil and Hypothesis for comments and annotations (as I'm doing here). I think this combination is working pretty fine for now and maybe I just automate the process here and there as needed.

By the way, I also like the self contained tech (I call them "pocket infrastructures": simple, self-contained, local first and extensible), but my exploration goes into dynamic languages and environments with Pharo (a Squeak fork) and I'm just putting Nim in my radar recently. I may try LittleStore. soon, as I see really aligned to my interests.

web native file system host apps with user controlled data, encryption and local first Software

The browser + JS have both of these covered.

Side note: repl.it and other cloud-based hosted services are an example of how /not/ to do it. Heed the plea for local-first software. There's something about the browser that makes people completely throw away their sense of what makes for reasonable expectations and anything they might know about traditional development workflows. Look at, say Digital Mars's download page or Ken Silverman's homepage, where they make available modest executables that consume plain text, output whatever it is they need, and work offline.

Not to mention, repl.it etc stray further into the land of magical abstractions that this post starts out railing against—more so than Eclipse. (And this is a good example of the amnesia I just described.)

What's more, shooting for the same workflow while having to work within the limitations of the browser sandbox actually ends up emphasizing the "ordinary files" mindset.

See also:

• How to displace JS
• triplescripts.org

I would include "project liveness" here, when I was looking for libs I was also checking Github profiles. Some projects would have evergrowing list of issues that are never closed

I think not requiring manual conflict resolution is very important, but also it doesn't capture that it should also merge data. Last-write-wins is also technically automatic conflict resolution, not very good though

If this is the case, do you actually need "My data must be available" point at all?

IMHO this paragraph is very complex

I think this needs more detail, hard to figure what you mean without context