Opportunities › Local AI investment research terminals for traders › Proposed app
Ledgerlocal
Private AI research desk for A-share, HK and US stocks that keeps your book on your device
- Score
- 33
- confidence 42
- Evidence
- 4
- items on the page
- Rivals
- 1
- named in sources
- First version
- 40 d
- estimate
- Type
- Desktop app
- PWA: runs in the browser, installs on Mac and Windows
- Market since
- 2025
- New market · AI estimate
ScreensConcept
Desktop app: Traders and analysts maintain books, run research agents and check theses on three markets—serious analytical work with strategy notebooks and detailed note-taking. Sample screens on a computer, in the proposed brand. Their numbers are sample data.
Portfolio
Offline-ready+1.8%
About this appAI proposal
Ledgerlocal is a research terminal for traders and analysts who do not want positions or strategies stored on someone else's servers. Your watchlists, holdings, notes and agent runs are kept on your own machine. You bring your own market data and your own model key.
AI agents read filings, news and price history for A-shares, Hong Kong and US stocks, then write a research note you can check. Each note links to the sources it used, so you can verify it before acting.
It is built for individual traders, small funds and quant analysts. Unlike cloud terminals, it works from a self-hosted install, and only the text you choose to send for analysis leaves your machine.
- Tagline
- Research the market. Keep the book to yourself.
- Voice
- PreciseCalmPrivatePlain
- Why this name
- A ledger is the record traders keep; local says where it lives. Two plain words joined, easy to say and spell.
In the first version
Members say which features they would use. It tells PWAS what people want; it changes no score.
Local-first book
Positions, watchlists, notes and strategies are stored in a database on your own hardware, not in a vendor account.
No member yet
Three markets, one desk
Research A-shares, Hong Kong and US stocks in one view, with currency and trading-calendar differences handled for you.
No member yet
Research agents with sources
Agents draft notes from filings, news and prices. Every claim links to its source passage for checking.
No member yet
Outbound preview
See exactly what text would be sent to the model before each run. Mask tickers or position sizes if you wish.
No member yet
Brand identityAI proposal
Check the name against trademark registers before using it.
Palette
#0F3B34Ink Green · primary#F6F3ECPaper · surface#1B1F1ECharcoal · text#C48A2CBrass · accent#B3392FSignal Red · data, losses#6F9C86Sage · data, gains
Typography
Aa
Ledgerlocal
PricingAI proposal
The material gives no competitor prices. These tiers are a starting point to test, based on the opportunity's freemium and subscription suggestion.
Personal
Free
- Local workspace
- One market at a time
- Bring your own model key
- Manual research runs
Trader
$29 a month
- All three markets
- Daily trigger checks
- Outbound preview and masking
- Encrypted export
Desk
$99 a month
- Up to 5 seats on one install
- Shared strategy notebooks
- Audit log of agent runs
- Priority support
What it could be worthEstimate
What a software business making this much sells for today, from real deals. Pick a monthly revenue.
If it makes
Worth about
$194,000
Sale range $132,000 to $263,000
$120,000 a year in revenue
From 87 software businesses listed and sold on Empire Flippers in the last year, revenue vetted by the broker: they sell for about 19× their monthly revenue, most between 13× and 26×.
Measured on profit, the middle deal is 32× monthly net profit: about 2.7 years of profit.
An estimate, not an offer or financial advice. A real price depends on profit, growth, churn, how much of the work is the owner's, and the buyer.
How it would growAI proposal
How the product would reach new customers through its own use, and how the first ones would be found. A plan to test, not a result.
- Built-in loop
- No loop in the product. Ledgerlocal is private by design, so users do not share their book or invite others by default. It reaches customers through content, open-source communities and word of mouth among traders.
- Do they become customers?
- Test whether privacy-focused traders will pay for a managed, polished version of a tool they could self-assemble. Test whether small funds buy the Desk tier.
- First customers
- Independent quant traders and small funds of one to five people who trade A-shares, Hong Kong and US stocks, and already use their own API keys.
- Where to reach them
- GitHub and open-source forums: Engage users of local-first research projects and offer a managed, supported version with migration help.
- Quant trading communities: Post worked research notes with visible sources and a short guide to keeping a book private.
- Direct outreach to small funds: Offer a two-week pilot of the Desk tier to funds with a stated data-privacy requirement.
- First milestone
- Ten paying Trader or Desk customers within 90 days, from at least two of the three markets.
Why people already pay for this
- VerifiedGitHub repository gained 574 stars in 61 days
- Public claimOpen-source alternative to Tencent WorkBuddy Finance Edition exists, indicating demand for local, self-hosted trading and research tools
- AI inferenceUsers want trading platforms where investment positions and data remain on their own hardware rather than external servers
- AI inferenceMarket opportunity spans multiple stock markets including A-shares, Hong Kong and US stocks
Tech stack
Every proposal builds on the same PWA base, installable from the browser on any phone or computer. Dashed boxes are what this app adds.
- AppNext.js and TypeScript
- PWAManifest and service worker
- UITailwind CSS
- Data and authSupabase Postgres
- PaymentsStripe
- EmailResend
- HostingVercel
- This app · Local data storeBrowser SQLite (OPFS) with optional self-hosted PostgresPositions must stay on the user's device, so data is kept in the browser or a self-hosted database.
- This app · Model accessProvider-neutral LLM client with local endpoint supportUsers bring their own key or a local model, so no prompts pass through our servers.
RisksAI inference
- DataLicensed market data for A-shares, HK and US is costly and restricted. Redistribution terms may force users to bring their own feeds, which narrows the audience.
- AIAgents may misread filings or invent claims. Wrong research notes could lead to losses, so source citation and clear disclaimers are essential.
- RegulatoryResearch tools that look like investment advice may face rules that differ in mainland China, Hong Kong and the US.
- CommercialAn open-source alternative already exists and is free. Paying users must see value in polish, support and data connectors.
- TechnicalA PWA that stores the whole book locally can lose data if the browser clears storage. Backups and a self-hosted option are needed.
Everything marked AI proposal or AI inference was written by a model from the evidence on the opportunity page. The proposed name must be checked against trademark registers before it is used.