A workspace for agent context

Context Designer

Give every part of your agent's context a place.

Map instructions, tools, memory, and conversation into editable slots. Set token budgets, add real content, and see exactly how it fits your context window.

Your context map

Define the window, then select a slot to shape its content.

Loading tokenizer…
0 tokens
Filled = content · pale = unused slot budget · red = slot overrun. Footprint uses the larger of budget or content for each slot.

Edit slot

Counts sum each slot’s literal text with the selected encoding. Message framing, images and provider-specific overhead are excluded. Text is never truncated to fit a budget.
Empty starter template · illustrative budgets · no prompt content yet
Export / import design
gpt-tokenizer 3.4.0 · local BPE counting after the tokenizer loads