Mantic
A structural code search engine for AI agents. Provides sub-500ms file ranking across massive codebases without embeddings, vector databases, or external dependencies.
What's New in v1.0.12
Critical Fix : Implemented missing high-confidence scoring path in scanProjectLegacy that was causing "Scanner failed to produce scored files" error
: Implemented missing high-confidence scoring path in scanProjectLegacy that was causing "Scanner failed to produce scored files" error Proper Scoring : All queries now receive proper scores from BrainInspiredScorer regardless of intent confidence level
: All queries now receive proper scores from BrainInspiredScorer regardless of intent confidence level Reliability: Fixed the root cause of undefined scoredFiles that was triggering the broken fallback in v1.0.10
Table of Contents
About the Project
Mantic is an infrastructure layer designed to remove unnecessary context retrieval overhead for AI agents. It infers intent from file structure and metadata rather than brute-force reading content, enabling retrieval speeds faster than human reaction time.
Key Benefits
... continue reading