Context engine for large codebases, exposed through MCP. Gives AI coding agents precise repository context; benchmarked at frontier-agent quality with ~25x lower model cost and 45% fewer tokens with semantic search.

Your agent pays twice for output it has already seen. OMNI returns a handle instead: 97.2% off a file read twice. Nothing deleted, nothing invented.

Persistent session memory for AI coding agents — local-first, with on-device inference, associative recall, and drift detection. Works with Claude Code, Cursor, and Codex.