Over/Under Market Intelligence
AI-leveraged analysis of prediction markets finds the edge
What it does
O/U is a prediction market analysis tool that finds edge pricing on thousands of Kalshi and Polymarket contracts. Independently calculated probabilities help you identify great buys and avoid bad ones. Go deeper with on-demand analyses that equip you with reasoning, sources, confidence levels, and information about potential price pivots. O/U has a fully graphic interface and is easy to use. Best of all, the core analysis is totally free and updates every two hours.
Does the same job
all alternatives →
- MAMulti-agent AI stock analyzer – 408% return trading Korean marketNov 2025 · ▲5
Hey HN! I built PRISM-INSIGHT, a multi-agent system where 13 specialized AI agents collaborate to analyze Korean stocks (KOSPI/KOSDAQ). It's completely open source and has been running live since March 2025. [What it does] The system automatically detects surging stocks twice daily, generates analyst-level reports, and executes trading strategies. Each agent specializes in something different – technical analysis, trading flows, financials, news, market conditions, etc. They work together like a real research team. [Why I built this] I wanted to see if GPT-4 and GPT-5 could genuinely…
- AFA financial analysis and research tool powered by agents2024 · github.com · ▲6
Hey HN! I've always been fascinated by financial markets. This month, I decided to build a tool to help with the research of stocks and cryptocurrencies. I'm using YFinance as a data source because it's free and provides a wide range of reliable market data. For sentiment analysis, I'm leveraging Google Trends to gauge public interest and sentiment over time. The tool, named Zenith, is a command-line utility with four main features: Market Analysis: Provides insights like moving averages, RSI, and volatility for selected stocks or cryptocurrencies. Sentiment Analysis: Uses Google Trends to…
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