Deterministic repository context packing for AI coding agents: selects, compresses, and budgets only the files a task needs. Measured 83% fewer input tokens at the same task coverage, fully local, no LLM in the loop.
Token-optimized semantic code search with automatic context expansion for AI coding assistants, enabling efficient discovery of code relationships and reducing token usage.
A memory system for AI coding tools that stores and retrieves codebase context with project isolation. Enables coding assistants to maintain searchable memory of code snippets, comments, and runtime traces with full source traceability.
Gives coding agents a memory of codebases by searching repositories using semantic similarity and structural call/import graphs, enabling reuse of proven patterns and reducing token usage.
