{"slug": "slowth-money-a-local-ai-agent-for-your-financial-goals", "title": "Slowth Money: a local AI agent for your financial goals", "summary": "A developer built Slowth Money, a local-first savings and financial goal-planning desktop app that pairs an Electron/React/TypeScript front end with a locally run Gemma 3 12B model via Ollama. The app keeps an encrypted private financial profile on-device, performs interest, fee and savings projections in deterministic TypeScript, and only invokes the LLM when language reasoning is needed, using a tiered source-trust score to weight public web results fetched through SerpApi. The Canada-only MVP is a proof of concept with no cloud backend, and the developer says country packs could extend it to other markets.", "body_md": "*This is a submission for the [Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady](https://dev.to/challenges/hacktoberfest-week3-2026-10-19)*\n\nPersonal finances can often be a source of stress.\n\nMoney management can have a big psychological impact. It consumes a lot of our attention.\n\nThis is why I built Slowth Money, a calm, **local-first savings and financial goal-planning desktop app that leverages open-source AI** to define strong boundaries between public resource sharing and private data kept on your local machine.  \n\nSlowth Money tries to minimize the stress of financial planning by embracing laziness through various forms:\n\nCheck out the code on Github!\n\nFeel free to fork it, experiment with it, and share feedback.\n\nYou could try adding your own country pack to run it from your own home for example.\n\nDisclaimer: This is a proof of concept. It may contain bugs and incomplete features. Do not rely on it as financial advice.\n\nNo web deployment or cloud backend is required. The projects runs locally as an Electron desktop app.\n\nSlowth Money is a calm, local-first savings and goal-planning desktop app. Canada is the proof-of-concept market for the current MVP: its registered-account wrappers, public institutions, and deposit products provide a concrete way to validate the privacy and planning architecture. The longer-term design can support other markets through country-specific packs, provider adapters, schemas, and UI, but only Canada is implemented today.\n\nSlowth Money helps answer four questions without turning personal finance into another feed to monitor:\n\nThe hackathon MVP runs as an Electron app on macOS, keeps the private financial profile encrypted locally, performs financial math in deterministic TypeScript, and uses an open-weight model through local Ollama only when language reasoning adds value.\n\nThe internet knows what financial products exist.\n\nThe local model knows your financial situation.\n\nNeither…\n\nSlowth Money runds as a local desktop application.\n\n```\n- Electron for the desktop application\n- React + TypeScript for the interface\n- SQLite for local persistence\n- Ollama for local model inference\n- Gemma 3 12B as the open-weight model\n- SerpApi for public web discovery\n- deterministic TypeScript code for financial calculations\n- native desktop notifications\n```\n\nI am running the application on an Apple M4 with 24 GB of RAM.\n\nI built this project around an **intentional privacy boundary**:\n\nThe internet knows what the latest financial products are whereas the local model knows my financial situation. External services don't need to know about the latter by default.\n\nTo give you some examples of what is fed to my **private context**:\n\nIn the **public context** we can find:\n\nThe core technical design decisions I took when building this project include:\n\nRecommendations use this trust score for the RAG context.\n\n```\nSOURCE TRUST\n\nGovernment             1.00\nRegulator              1.00\nFinancial institution  0.95\nEstablished aggregator 0.75\nFinancial publication  0.70\nGeneral website        0.40\nForum / social media   0.20\n```\n\nHow often should the agent check things?\n\n```\nApp launches\n\n        ↓\n\nMarket data older than 7 days?\n        │\n     YES│\n        ▼\n     Refresh\n\nCountry rules older than 30 days?\n        │\n     YES│\n        ▼\n     Refresh\n\nAnything changed?\n        │\n     YES│\n        ▼\n     Load Gemma\n```\n\nMost of the financial calculations don't require an LLM so I use normal code for them.\n\nThings such as calculations over interest, fees, projected savings rely on application code.\n\nThe local model is only pulled in when language understanding or reasoning is needed.\n\nThe adapters support multiple providers and normalize their results.\n\nWithout this scraping would be unreliable as bank sites can change HTML, restructure pages, therefore making it hard to build a universal financial website scraper.\n\nThe application can be configured to only notify about an opportunity that exceeds the user's financial opportunity laziness threshold. ie. how much financial benefit should this promotional rate offer to bother me with a notification.\n\nThis project got me thinking more about leveraging open-weight models to set boundaries on what sensitive information I want to keep private, my personal finances in this case.\n\nI also have more abilities to inspect the processes surrounding the model reasoning.\n\nIt also got me thinking about being less wasteful about AI consumption and only run inference periodically to stay on track with goals. Even your AI model should be allowed to be lazy at times!\n\nI can run the model offline and ore transparent planning and insepction of the process.\n\nUsing open-weight model forces a better and more mindful usage of resources to make the setup work properly, which I consider a healthy source of friction.\n\nThis project is essentially free to run in my case with my current setup.\n\nThere is no per-request AI API fee to pay.\n\nThere is no lock-in to a company or model. If I want to switch model, I can do so very easily.\n\nI used Slowth Money the past week to set some financial goals and keep track of financial provider's latest offers in my area.\n\nWhen using this application I found myself not having to think so often about where my money should sit as I knew that Slowth Money was checking for me and helping me reach my financial goals in the background.\n\nI also wanted more control on when I am bothered with notifications. In the context of my app, I can set the financial benefit control to only bother me if it exceeds a certain amount. I value my time and the notification should be worth opening.\n\nOther than the benefits of the product itself, working on this project made me think about AI consumption itself.\n\nThat is also a different kind of lazy payoff:\n\nGemma is a good fit for Slowth Money because it provides me with a robust open-weight reasoning layer without requiring my personal financial information to leave the device.\n\nThe model efficiently handles tasks such as understanding financial goals, reasoning over relevant context and providing useful recommendations.\n\nThe model is also resource efficient, allowing me to run the model locally on my local machine while also processing other tasks in parallel such as browsing the internet and coding on other projects.\n\nSerpApi helped me bridge the private reasoning provided by Gemma and with the latest public data from financial products.\n\nI used it as a discovery layer for public information such as new financial offers, current promotions, changes in regulated financial products.\n\nSerpApi helped me keep fresh public knowledge whilst maintaining private local reasoning in parallel.\n\nAfter sharing this project, I would love to know your thoughts.\n\nWhat do you think of the privacy model? Of the architectural setup?\n\nDo you have any feature requests? Optimizations? Design recommendations?\n\nDo you have any useful tool you already use for your personal finances?\n\nTo help me gauge community interest for future development, consider starring the repository on Github if you find the idea interesting.", "url": "https://wpnews.pro/news/slowth-money-a-local-ai-agent-for-your-financial-goals", "canonical_source": "https://dev.to/javz/slowth-money-a-local-ai-agent-for-your-financial-goals-2ki2", "published_at": "2026-10-25 23:38:36+00:00", "updated_at": "2026-10-25 23:42:35.976980+00:00", "lang": "en", "topics": ["ai-agents", "ai-tools", "large-language-models", "ai-products"], "entities": ["Slowth Money", "Ollama", "Gemma 3 12B", "Electron", "SerpApi", "SQLite", "Hacktoberfest"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/slowth-money-a-local-ai-agent-for-your-financial-goals", "markdown": "https://wpnews.pro/news/slowth-money-a-local-ai-agent-for-your-financial-goals.md", "text": "https://wpnews.pro/news/slowth-money-a-local-ai-agent-for-your-financial-goals.txt", "jsonld": "https://wpnews.pro/news/slowth-money-a-local-ai-agent-for-your-financial-goals.jsonld"}}