Deterministic context compression for MCP agents, reducing token usage via 11 tools for prompts, history, shell output, file deltas, and code navigation without ML or GPU.
Reduces token consumption for AI coding agents by 50-70% through intelligent code context filtering, Git delta tracking, and local SQLite/Tree-sitter indexing.
Deterministic context selection for AI coding agents. Scores and selects the minimal file set for each task, then records
outcomes into a local ledger that compounds into reusable patterns.