Agent
Compresses top retrieval chunks into citation-rich summary packets that preserve intent while cutting token usage.
44 4mo ago A 22 tokens
original MIT
Agent
Runs hybrid retrieval with strict FTS-first policy, BM25 lexical ranking, vector merge, and top 3-5 reranking for token-efficient context selection.
44 4mo ago A 38 tokens
original MIT
Agent
Delegates software engineering operations to focused subagents using compressed context packets to keep the main conversation lean.
44 4mo ago A 26 tokens
original MIT