When we hit, ~91% less context than a full doc read.
Compact is a versioned knowledge cache for AI coding agents. When the cache has the right procedure, one query returns ~800 tokens instead of 8k–14k. Less context, better code.
How it works
Agent queries Compact
Instead of fetching raw docs, your agent sends a natural-language query to Compact.
Cache returns a structured procedure
~800 tokens. Steps, code snippets, prerequisites, and common errors—versioned and ready to use.
~91% fewer tokens when we hit
Compared to a single full doc read (8k–14k). Agents often open multiple docs before finding the right use case—savings can be higher. 5–10% of the cost. Less context, better code.
1,000+ procedures. Ready when your agent asks.
Join the beta
Request access — we'll send your API key via email.
Every developer has debugged something that took hours and wasn't in any docs. That knowledge belongs in Compact so the next person doesn't lose the same time.
Submit a field trial — describe what you hit, what the fix was, and any relevant code. If it's a real sharp edge we'll add it to the cache within 48 hours.