Capturing is easy
A voice note, some text, a photo — saved in seconds. This step never failed you.
AI personal knowledge management
Give every thoughtthe shape of knowledge
Capturing is easy — the hard part is still finding it three months later. Sorp grows the voice notes, text and photos you drop in into a chaptered body of knowledge. You never build a folder tree, and you never maintain one.
- 4 ways
- in: voice · text · photo · scan
- 0
- folders you have to maintain
- 21
- viewpoints, each with its blind spots
Screenshot pendingpublic/shots/home-capture.webpThe problem
Every note app you abandoned died of the same thing
It is not a discipline problem. Maintaining structure is simply not work a person should be doing.
Finding is hard
Three months later you want that judgement you made. You search everything and only remember that you "said something about it".
Maintaining is impossible
Filing, naming, splitting pages, tagging, linking. Skip it for one day and the backlog never clears again.
Sorp's answer is to take that work away entirely. The AI maintains the knowledge base; you just capture.
How it works
A knowledge base you never maintain, but fully control
"Fully automatic" and "under my control" normally contradict each other. Sorp holds both through four things.
Read-only: structure is not your job
The AI maintains the knowledge base exclusively. Chapters, sections, links and summaries are all generated — you never face an empty folder.
Block-level provenance: every line goes back
Every conclusion links to the fragment it came from and the write that created it. Not "the AI said so", but "this is what you said".
One-tap revert: mistakes roll back
Every Agent write leaves a before-and-after snapshot. Read the card, and if you disagree, undo it — the knowledge base returns to the previous state.
Four gates: rather nothing than something wrong
Any automatic write must clear four gates: source allowlist, module allowlist, verbatim quote check, and an independent entailment check. If the last one fails, the write is discarded.
Authorship discipline
Third-party material never masquerades as your knowledge
Content from news, WeChat articles, insight pieces and viewpoint sessions is never silently written into your knowledge base. It persists only if you approve it yourself.
Because a verbatim-accurate quotation can pass every factual check and still read, to you, like your own belief. That is a misattribution of authorship — harder to spot than a factual error, and harder to undo.
The one write channel
Want it changed? Tell the Agent
The Agent is your only write channel into the knowledge base. Say "add that pricing judgement from last time" and it does — returning a card you can undo.
- Update a knowledge entry
- Rewrite a whole domain for consistency
- Record a cognition, decision rule or factual claim
- Add a term
- Write domain memory
- Search across the base before answering
Every write comes back as a card, revertible one by one.
Screenshot pendingpublic/shots/agent-chat.webpFive modules
Only five things to keep track of
Notes, Domains, Insights, Viewpoints, News — everything else is what they produce in the background.
Notes
Hold to talk, type, shoot, or scan. Four ways in — and no demand that you organize anything on the spot.
Domains
Create a domain for something you care about long-term. The AI interviews you first, then grows scattered notes into a chaptered body of knowledge.
Insights
Pick a thinking method; the AI writes an 800–2000 word illustrated piece grounded in your own notes.
Viewpoints
Hand a question to one thinker, or seat 2–5 of them at a table to debate, with a neutral host summing up agreement and disagreement.
News
Long-form reading recommended by your domains — with an AI close-reading before you commit the time.
The Agent floats above all five, available at any time.
Domains · the most unusual part
It interviews you first, then grows the structure
A domain is a container for something you care about long-term — a job, a hobby, a relationship. It is not a folder; it is a structure that grows.
- 01
The AI interviews you
One round of questions establishes what you want to study, what you already know, and where the edges are.
- 02
A chapter structure grows
From those answers the AI builds a chaptered skeleton — not an empty directory handed to you.
- 03
Records file themselves
What you capture afterwards gets judged for relevance and integrated into the right chapter.
- 04
Inspiration cards, daily
Up to 5 cards per domain per day, each asking whether a record belongs in the knowledge base.
Cognition ≠ knowledge
Two axes, because their standards of truth differ
"Cognition" records how you think — it has no right answer, only whether it is true to you. "Knowledge" records what you know — it has right answers and needs evidence.
Cognition system
Values, worldview, decision patterns, emotional patterns. No right answer.
Knowledge system
Entries, terms, factual claims. Right answers, fully traceable.
Growth
14 achievement groups, named after the classics
Breaking Ground, Unrolling, Six Harmonies, Word Hoard, Ploughing, Discernment, Prism, Thesis, Strategy, Growth Rings, Persistence, Spark, Hearing the Way, Inquiry.
Screenshot pendingpublic/shots/domain-interview.webpScreenshot pendingpublic/shots/domain-knowledge.webpInsights
12 thinking methods, run on your own notes
Pick a method. The AI reads your notes and writes an 800–2000 word illustrated piece. Not generic advice — every input is something you recorded yourself.
Thinking Methods
5 methods
First Principles
10 creditsBreak it down, then rebuild
Inversion
10 creditsThink backwards from failure
Pre-mortem
10 creditsAssume failure, work backwards
Second-Order Thinking
10 creditsAsk "and then what?" twice
Values Clarification
10 creditsClarify what you truly value
Mind & Cognition
4 methods
CBT Reframing
10 creditsSpot automatic thoughts and biases
Emotion Review
10 creditsReview an emotion you felt
MBTI Analysis
10 creditsCompare against your own patterns
Self-Compassion
10 creditsTreat yourself like a friend
- CBT Reframing — This is a self-help CBT exercise, not medical advice. If you are in serious emotional distress, please seek professional help.
- Emotion Review — This is a self-help emotion review exercise, not medical advice. If you are in serious emotional distress, please seek professional help.
- MBTI Analysis — MBTI is a self-reflection tool, not a scientific personality diagnosis.
- Self-Compassion — This is a self-help self-compassion exercise, not medical advice. If you are in serious emotional distress, please seek professional help.
Life Records
3 methods
Travel Journal
15 creditsTurn one trip into an illustrated journal
Spot Notes
15 creditsTurn a meal out into a written note
Monthly Review
15 creditsSettle a month into a review
Here is what it produces
800–2000 words, 3–5 sections, 2–4 illustrations, and a short list of actions for the coming week. Built only from your own notes.
Screenshot pendingpublic/shots/insight-article.webpViewpoints
21 thinkers, each with a written blind-spot notice
Hand your question to one thinker, or seat 2–5 at a table to debate. Every viewpoint states its own limits — knowing where you will be wrong beats pretending you will not be.
Let us be clear about what this is
These are AI simulations of how historical figures thought, built from public sources. They are for provoking thought. They are not the figures' own words, and no quotations are fabricated. Each figure ships with a blind-spot list defined in our source code — what they would object to, and what they overlook.
Single analysis · 10 creditsRoundtable · 5 credits per speaker · 2–5 people
Business & Investing
5 thinkers
Charlie Munger
Master of mental models
Blind spots of this viewpoint
Underrates fast-iteration internet playbooks and the non-linear breakout of young industries; his conservative temperament can suppress decisions that require risk; limited value on macro and short-term opportunities.
Steve Jobs
Tyrant of minimalism and taste
Blind spots of this viewpoint
His forceful, unilateral style can ignore team consensus; low price sensitivity means advice may exceed an ordinary budget; an elitist lens underrates mass-market differences; his aggressive approach to health is not worth imitating.
Kazuo Inamori
Philosopher of management
Blind spots of this viewpoint
A Japanese collectivist context sits at a distance from individual-centric internet culture; mechanically applied altruism can blunt competitive aggression; limited experience with rapid scaling playbooks.
Peter Drucker
Father of modern management
Blind spots of this viewpoint
Drawn from large organizations, so it fits very early startups and solo operators poorly; a gradualist temperament is in tension with disruptive innovation; highly abstract, so it assumes some management background.
Benjamin Franklin
Archetype of self-made success
Blind spots of this viewpoint
A pre-industrial virtue checklist needs reworking for modern work rhythms; heavy self-discipline suits divergent creative work poorly; pays little attention to emotional and psychological complexity.
Science & Engineering
7 thinkers
Richard Feynman
The physicist who could teach
Blind spots of this viewpoint
An anti-authority stance can underrate the value of organization and process at scale; limited patience for business and politics; "say so when you don't understand" can look hesitant when a decisive call is needed.
Albert Einstein
Imagination over knowledge
Blind spots of this viewpoint
His long resistance to quantum mechanics shows even geniuses get trapped by an old paradigm; an idealist stance has limited applicability in commercial competition; heavy on theory, light on execution.
Marie Curie
Twice a Nobel laureate, alone
Blind spots of this viewpoint
A working style that sacrifices family and health should not be promoted; the lone-hero path needs rework in modern collaborative R&D; no interest in commercialization or reputation management.
Claude Shannon
Father of the information age
Blind spots of this viewpoint
Models irrational human and organizational factors poorly; an engineering-optimization mindset can miss unquantifiable value such as brand and emotion; market and user understanding is not his strength.
Charles Darwin
Author of evolutionary thinking
Blind spots of this viewpoint
Gradualism explains leapfrog technological revolutions poorly; a modest style can lose focus when a forceful decision is needed; social Darwinism is a misuse of his theory — beware mechanical application.
Alan Turing
Father of computing and AI
Blind spots of this viewpoint
A purely logical framework covers emotion and aesthetics poorly; the injustice he suffered is a reminder that talent needs a tolerant environment; too technical to be understood without translation.
Leonardo da Vinci
The ultimate curious generalist
Blind spots of this viewpoint
Interests scattered so widely that much was left unfinished — focus and closure are his weak points; genius-level omnicompetence is not reproducible for ordinary people; little interest in systematic, scaled engineering.
Letters & Thought
6 thinkers
Lu Xun
Dissector of the national character
Blind spots of this viewpoint
An excess of critique can make conclusions sound bleak; his era (national crisis) needs translation for modern personal-growth questions; his edge aims straight at human darkness and may unsettle thin-skinned readers.
Socrates
The gadfly of Athens
Blind spots of this viewpoint
Asking without answering is inefficient when a quick decision is needed; the midwife stance is easily read as arguing for its own sake; underrates intuitive and experiential knowledge.
Laozi
Sage of the natural way
Blind spots of this viewpoint
Highly condensed wisdom must be translated into action by the reader; "not contending" can be misread as passivity in zero-sum settings; mystical phrasing is unfriendly to modern readers seeking certainty.
Wang Yangming
Master of unity of knowing and acting
Blind spots of this viewpoint
Emphasis on inner conscience can turn into self-righteousness for the untrained; success depends heavily on personal cultivation and does not scale; comparatively thin on institutions and systems.
Sima Qian
Historian who judged by history
Blind spots of this viewpoint
Historical analogy can mask fundamental differences in present variables such as technology and institutions; deferred judgment does not suit situations needing immediate feedback; a tragic temperament yields overly heavy advice.
Aristotle
Founder of the Western tradition
Blind spots of this viewpoint
A static taxonomic framework dates quickly in fast-evolving fields; era-bound views such as those on slavery must be inherited critically; academic rigor can look short on frontline sharpness.
Strategy & Beyond
3 thinkers
Sun Tzu
Strategist of winning without fighting
Blind spots of this viewpoint
A military-confrontation frame can over-competitivize win-win settings; the stratagem flavor needs reconciling with modern business ethics; says less about long-term trust and cooperation than about confrontation.
Bruce Lee
Cross-domain martial artist, like water
Blind spots of this viewpoint
Intensely individualist expression fits team collaboration poorly; "no form as form" can leave beginners with no structure at all; a short life left his system of thought incomplete.
Zeng Guofan
Exemplar of patient self-cultivation
Blind spots of this viewpoint
Extreme self-discipline has a high bar for ordinary people; a hierarchical, obedience-heavy view of organization is distant from flat modern teams; the patient approach can miss windows in fast-iterating industries.
Roundtable
Should I quit and start a company?
- Charlie Munger
First work out whether you can survive the worst outcome. Do not stare only at the probability of success.
- Steve Jobs
If the product does not excite you, do not start.
- Sun Tzu
First make yourself invincible, then wait for the enemy's opening. Consider defeat before victory.
Host summary
- Agreement
- Sort out the risk and your floor before you move.
- Disagreement
- Wait for the moment to ripen, or break through on passion.
- Suggested action
- Run a three-month minimum-cost validation before deciding to commit fully.
Screenshot pendingpublic/shots/viewpoint-roundtable.webpPricing
No feature tiers — only intensity tiers
Free, Lite and Pro have exactly the same features. They differ only in how many credits arrive each period. Capturing a note is free and costs nothing.
Free
¥0
free forever
500 credits on signup
one-time · never expires · no refill
- Every feature available
- Capturing costs nothing
- Read-only knowledge base
- Block-level provenance and revert
Lite
¥8
per month · or ¥98 / year
1,000 credits per period
auto-granted monthly · valid that month
- Every feature available
- A steady monthly allowance
- Yearly plan grants 12 periods
- Top up separately when you run out
Pro
¥18
per month · or ¥198 / year
2,500 credits per period
auto-granted monthly · valid that month
- Every feature available
- A larger monthly allowance
- Yearly plan grants 12 periods
- Top up separately when you run out
Credit packs
¥8–¥168
7 tiers
800–16,800 credits
one purchase · never expires
- Top up after membership credits run out
- Buyable without a subscription
- Valid long-term
- Failed AI tasks refunded automatically
What a credit actually buys
¥1 = 100 credits. These are the real costs, all visible inside the app.
- Capture a note (voice / text / image)
- Free
- An insight article (thinking / cognition)
- 10 credits
- An insight article (life-record types)
- 15 credits
- Single-viewpoint analysis
- 10 credits
- Roundtable discussion
- 5 credits per speaker
- Live voice call
- 6 credits / min (capped at 10 min)
- Save an inspiration card to the base
- 5 credits
- A quote card
- 5 credits
- A failed AI task
- Refunded
Only AI generation spends credits. Capturing is always free.
FAQ
What you might be wondering
How is this different from flomo, Notion or Obsidian?
All three expect you to build the structure and maintain the taxonomy. Sorp's knowledge base is maintained solely by the AI and is read-only: you only record, while structure, filing, linking and summaries are done for you. If you enjoy hand-building a second brain, Sorp is not for you. If you are tired of maintaining it, Sorp is.
What if the AI files something wrong? Can I fix it?
Yes. The knowledge base is not sealed: the Agent is your one write channel, and every write produces a card with a before-and-after snapshot that you can revert individually. You can also just tell the AI what to change and have it rewrite.
Could third-party content end up presented as my own knowledge?
No — this rule is hard-coded. Content from news, WeChat articles, insight pieces and viewpoint sessions is never silently written into your knowledge base; it only persists if you explicitly confirm it. The reason: a verbatim-accurate quotation can pass every factual check yet read as your own belief — that is a misattribution of authorship.
Where is my data stored?
On Alibaba Cloud (object storage and database). Speech-to-text and image understanding are provided by Alibaba Cloud Bailian, the large model by DeepSeek, and one-tap phone login by Alibaba Cloud PNVS. In settings you can inspect and clear the knowledge base, clear local cache, sign out, or unbind WeChat.
Can I record something without filing it?
Yes — recording and settling are separate. Creating a note costs no credits and triggers no organizing task. Each day the AI places a few inspiration cards in your domain (at most 5 per domain per day), and you decide what is worth keeping.
How are credits spent? Will I run out?
Recording is free. Credits are spent on AI generation: 10 for an insight article (15 for life-record types), 10 for a single-viewpoint analysis, 5 per speaker for a roundtable, and 6 per minute for live voice calls (capped at 10 minutes, with the difference refunded on hang-up). Every tier has identical features — only the credit allowance differs. Failed AI tasks are automatically refunded.
Get started
Put Sorp in your pocket
The iOS release is working its way through App Store review. Until it lands, scan to register for the beta.
Coming soon to the App Store
Scan to join the beta · iOS