LLM Space
A desktop app for agent builders that lets you prototype agent ideas, trace every model call and tool run, replay failed runs, and measure performance in one place.
LLM Space is a desktop app for agent builders. It lets a developer write and version prompts, system messages, tools and model settings, trace every model call and tool run inside the agent loop as it happens, replay a run from history and step through it to find what went wrong, and measure how an agent performs across runs.
It keeps threads organized as files on the user's own machine, and can generate prompts and tools with AI or turn a thread into a runnable LangGraph agent. It is a sister project of DeerFlow and is used to build and debug every version of DeerFlow.
It is a Bun monorepo written in TypeScript, packaged as a desktop app with the Electrobun shell and a React, Tailwind CSS and shadcn/ui interface, built on the Pi Agent Core agent framework. It collects a small amount of anonymous usage data to improve the app, which can be turned off.