Intel / article

Relace Repos

Terms in this piece · Glossary

token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.

Why it matters

Search consumed over half the in Relace's 1,200-task traces; Repos pairs agent-oriented git hosting with auto-indexed vector-then-reranker retrieval so agents stop burning locating files.