Show HN: Stoke Money – Personal finance app built around a cash flow forecast (stoke.money)
I've been through many finance tracking apps, starting with Personal Capital, then Monarch, and most recently Copilot. None of them have worked perfectly for my needs.
All of these apps tend to model “cash flow” as the net sum of your transactions during a month, yet while credit card charges are reported immediately, they are typically deducted from checking (cash) accounts the following month when the bill is due. As a result, I've always had to maintain a separate spreadsheet to track my actual cash flow.
These apps also have a huge focus on managing budgets, which has never been for me. My spending is rarely consistent month-to-month, so every month I'm comparing my fully justified spending against my budget, and tweaking my budget until I “pass”.
So I built yet another finance tracking app. It has the usual components - accounts, transactions, categories - but the core is a cash flow projection engine, and everything else is built around it.
Budgets are gone. Instead, each income/spending category is projected forward from your historical activity, but not as a flat monthly number. They land in whatever account you historically use (e.g. checking account for paychecks/rent/bills, credit/debit cards for daily spending). Credit card payments are modeled automatically based on your projected credit card balance. You can set up your own recurring transfers between accounts as well, to model savings, for example.
The end result is that the app can forecast how your cash moves, and you can see in advance when any account might run low. If all of your accounts look good for the next 12 months, maybe you don't have a budgeting problem.
What’s made the biggest difference for me has been the MCP integration, which I have connected to Claude (but can be connected to any AI agent of your choice). I have asked it to import historical transactions by uploading PDF account statements, categorize/tag all transactions that took place while I was on vacation, and plan transfers across my accounts to cover expected payments.
I hope some people that share my frustrations will find this app useful.
25 comments
[ 2.8 ms ] story [ 76.6 ms ] threadEven a SOC type 1 would show you're on the journey.
You need to spam growth and marketing. Your landing page is horrible. Redo it. Run ads and pay Tiktok influencers and YouTubers.
Standard consumer SaaS security is more than enough for this sort of product. Your users won't know the difference between end to end encryption and encryption at rest and while you are nitpicking based on hacker news power user feedback others would eat your lunch already.
The governing terms are California's. I checked CA business registry and found no 'VoidHQ' or 'Void HQ'. Not sure who I would be trusting with my data.
in my world, there is no such things as "registering", just processing and I say that because I've seen many people get caught up on this process for actual years. Picking the wrong state, or getting hung up on name, and things like that. Can you shift liability and process payments or not. there is a blueprint that works for this country and international access, but nearly infinite permutations that may take you a lifetime to figure out, or cost you more than it should by copy pasting Delaware for everything.
[1]: https://openai.com/index/personal-finance-chatgpt/
- Privacy. Stoke is a paid subscription. I’m not selling your data. Caveat: if you connect an agent over MCP, what that agent does with your data is up to you. I can't control that.
- Control. The core product is the projection, and it’s only as good as the data underneath it. Plaid data is imperfect, so there’s always some cleanup to do. ChatGPT and Muse may do a decent job of recategorizing transactions and even remembering those fixes for future ones, but I think direct access to those controls (categories, rules, overrides) is a better experience than asking a chatbot.
- Portability. Everything you’ve modeled lives in Stoke, not in one product's memory. You can freely switch from ChatGPT to Claude or anything else without losing anything.
- Not mutually exclusive. All the questions you would ask your LLM about your finances, you can still do via the Stoke MCP, so I see it as the best of both worlds.
This is more or less how I already set up GNUCash. Couple dozen scheduled transactions created 90 days into the future, with the "Future Minimum Balance" field enabled on the homescreen.
For me, the time sinks are interrelated:
1. Monthly reconciliation. Every month I sit down and compare the scheduled transactions with what actually happened in statements, for approximately thirty different accounts. Many don't have APIs, certainly none GNUCash would speak. This takes a lot of time and I wish I could just have this automated. Just give me exception handling on the edge cases like a new transaction category, or a forecasted negative checking balance.
2. CC transaction import. This is a structural failing of banking closing down formerly open APIs. Only thing left on my BofA accounts is CSV exports. Which thankfully works with a bit of setup but the writing is on the wall and even that may soon vanish in the name of banks defending their core business.
3. Stock transactions, equity grants & price tracking. This one is even harder since CSV feels structurally not up to the task of representing the "sell to cover taxes" split of RSU grants, and I never really got it working in OFX anyways. Plus I have a pretty weird collection of accounts including a pension IAP that updates once a year (and that update is retroactive to 6 months ago) and a 457b invested in restricted custom funds with no ticker symbols.
These products are deeply needed, but they are gated behind Saas payments. And this requires significant trust of the provider, as they have visibility of all the financial records of the user.
My understanding is the need for recurring payments is the cost of data integration providers. This cost can be passed entirely to the user if run locally. I would suggest that the integration providers might want to fund such projects if they were Free and Open Source.
Build a stand alone binary that lets users import their own api keys and this product will survive a long time
1. Exclusions. You can exclude any single transaction from the forecast. It stays in your history but no longer counts toward the projection.
2. Streams. You can group a set of transactions into a stream (e.g. your YouTube subscription inside Entertainment), and it gets its own projection on its own schedule instead of being averaged into the category.
3. Plans. If you know a big expense is coming, you can set up a Plan. Plans can add one-off events (like an expensive car repair) or apply a percentage increase/decrease to a category (like Shopping during the holidays).
Finally, once there’s enough history, the forecast also picks up seasonal patterns, like higher spending in Shopping or Travel in December, and will project higher amounts for just that month. Your first December may be underestimated, but it gets more accurate as history builds up.