A provider vs NodePad

A headless, provider-agnostic agentic loop. Every piece, memory, model, tools, stop conditions, sits behind a swappable interface. Streaming by default, one dependency,...

Agent on canvas. NodePad lays your AI conversations out on a canvas, so you try more ideas, keep the answers that hold up, and never lose the thread that mattered.

About A provider

A headless, provider-agnostic agentic loop. Every piece, memory, model, tools, stop conditions, sits behind a swappable interface. Streaming by default, one dependency, runs anywhere. The pieces to build your own agent: your Jarvis, your Cortana, your Samantha. The loop never writes to a screen, it emits one typed AgentEvent stream, so a trace is just data. Scrub the same run and watch three front ends rebuild in lockstep. One pass through the loop, seam by seam, each is just a field on runAgent() .

About NodePad

Agent on canvas. NodePad lays your AI conversations out on a canvas, so you try more ideas, keep the answers that hold up, and never lose the thread that mattered. You can then use the arrow keys to move the node around. You can then press delete to remove it or escape to cancel. Every message on a NodePad canvas is a node you can build on, and the model only ever sees the context you chose.