Layer vs. Singularity

One API for prediction markets. Find markets, stream normalized data, place orders, and track positions across Kalshi and Polymarket. Hi HN, I'm David. I built Layer, an API + SDK or building trading bots/ai agents across prediction markets.The idea came from something i kept running into while playing with trading bots. Once your bot needs access to more than 1 venue, you suddenly have to deal with different market schemas, contract definitions, prices, fees and APIs before you can reason about where to trade. That gets messy real fast, especially with prediction markets. The same real-world event can exist on Kalshi & Polymarket, but the contracts can be represented differently.Here's my broader thesis:...

Contribute to pandacover/singularity development by creating an account on GitHub. Coding agents start every session from zero. Ask Claude Code for a change like one it made last week and it reads the same files again, falls into the same test traps again, and you pay for all of it again.Singularity learns from your finished sessions (change committed, tests passing): where each kind of change goes in this repo, how it gets checked, and the mistakes made along the way. When the next task starts, a hook hands the agent the workflows that fit, pointed at the code as it is today. Picking them is plain text matching with no model call. It stores where to edit, never the code its...