PortfoliQa
Honest valuation tools for self-directed investors, US + BR
What it does
PortfoliQa brings global investing into one workspace — US stocks, ETFs, crypto, metals, plus Brazilian fixed income (CDB, Tesouro) with real after-tax yields. Transparent valuation factors (no black-box scores), bilingual EN/PT. Free: charts, fundamentals, valuation, news, rankings, portfolio, BR fixed-income comparison, 5-symbol watchlist, 10 AI chats/day. Premium ($14.99/mo or $9.99 yearly • R$39.99 / R$29.99 yearly): unlimited AI + watchlist. Solo-built. Honest feedback welcome.
Does the same job
all alternatives →- IBI built an AI that knows my net worth: 3 countries, 6 currenciesJul 2026 · demo.joinbrisa.com · ▲6
I'm Canadian, live abroad, and my money is scattered across two countries, multiple currencies, banks, brokerages, real estate, and some private equity. No app could hold all of it, and none could answer a simple question like "what's my actual USD exposure?" Brisa pulls everything together (Plaid + manual accounts + real estate + PE, all multi-currency) and puts an AI on top that has my full financial picture in context. Instead of clicking through charts, I can just ask. Would appreciate any feedback!
- FFFinagg – free and nearly unlimited financial data2024 · github.com · ▲11
finagg is a Python package and CLI that enables you to aggregate and update free financial data from a handful of high quality data sources all within your own SQL database. Here're some quick facts about it: - Implements nearly all of the BEA API, FRED API, and SEC EDGAR APIs (all of which have free and nearly unlimited data access) - Only focused on macrodata (no intraday data support) - Provides methods for transforming data from these APIs into normalized features that're readily useable for analysis, strategy development, and AI/ML - The most popular methods include getting…
- NCNo-code tool for creating stunning portfolios and resumes2024 · ▲6
Hey Hacker News community, I’m excited to share something I’ve been working on that you’ll find really useful! I created a no-code tool called Portfoliia that simplifies the process of building stunning portfolios and resumes. Creating and updating portfolios and resumes can be a time-consuming and tedious task. Not everyone has the design skills or the time to keep their professional profiles polished and up-to-date. This can be a significant hurdle when you're focused on learning new skills, growing your career, and landing that dream job. With Portfoliia, you can quickly generate and…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
- NW
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com
- FM
Dev tools · May 2026 · github.com