Skip to content

Conversation

@nan-bit
Copy link

@nan-bit nan-bit commented Jan 28, 2026

Overview

This PR integrates AIC (AI Compiler) into the Conductor workflow to address performance and scalability issues when working with large "brownfield" projects. It introduces semantic indexing and rich skeletons to optimize token usage and context depth.

Key Features

  • Semantic Dependency Graph: A local SQLite-based index that maps file relationships, enabling intelligent context retrieval.
  • Rich Skeletons: Compressed representations of source code that preserve API contracts (signatures, docstrings, etc.) while discarding implementation logic, reducing context size by ~90%.
  • MCP Server Integration: AIC is integrated as a local Model Context Protocol (MCP) server for seamless tool access.

Implementation Details

  • Added the core module (Skeletonizer, DB layer, and CLI).
  • Updated the /conductor:setup command to perform initial semantic indexing.
  • Enhanced /conductor:newTrack and /conductor:implement to utilize skeletons instead of raw source files.
  • Added tests for multi-language support (TypeScript, Go, Python) and dependency resolution.

Fixes

Closes #64

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

feat: Integrate Semantic Graphing & Rich Skeletons for Context Efficiency

1 participant