contextual-engine 0.9.1

Temporal-first local code memory for AI tools via MCP

Contextual

Local-first temporal semantic code memory engine for AI tools

What is Contextual?

Contextual transforms code repositories into queryable, time-aware knowledge structures. Unlike traditional RAG systems that treat code as static documents, Contextual maintains full temporal awareness, structural understanding, and semantic relationships across your entire codebase.

The Four-Way Wedge:

• Local-first - Embedded storage, no cloud dependency
• Bitemporal - Tracks when facts were true AND when you learned them
• Code-aware - AST parsing, not just text chunking
• Tool-agnostic - MCP integration works with any AI IDE/chat client

Features

• Hybrid Search - BM25 + vector embeddings with RRF fusion
• Temporal Queries - Time-travel through your codebase history
• Knowledge Graph - Entity-relationship triples with recursive traversal
• GNN Enhancement - Graph neural networks propagate semantic context
• Docs Write - AI-powered documentation updates with two-phase commit
• Incremental Indexing - Git-aware change detection, BLAKE3 content hashing

Installation

pip install contextual-engine

Quick Start

# Initialize project
contextual init /path/to/repo

# Index codebase
contextual index .

# Search
contextual search "authentication middleware"

# Start MCP server (for Claude Desktop, Cursor, etc.)
contextual serve

MCP Integration

Add to your AI tool's MCP config:

{
  "mcpServers": {
    "contextual": {
      "command": "contextual",
      "args": ["serve", "--project", "/path/to/repo"]
    }
  }
}

Documentation

• Architecture - System design across all layers
• Technical Spec - Implementation details
• Project Phases - Development roadmap
• MCP Tools - Tool contracts and API

License

Business Source License 1.1 (BUSL-1.1) — see LICENSE for the full terms, including the Additional Use Grant and the Change Date / Change License.