de>scriptor
Features

Everything You Need
for AI-Powered Development

A complete toolkit built in Rust for turning your codebase into an AI-navigable knowledge graph

Built in Rust

Extremely efficient modern Rust implementation delivering 3-5x faster parsing performance with memory safety and zero-cost abstractions.

  • •Memory safety without garbage collection
  • •Zero-cost abstractions for optimal performance
  • •True parallelism without GIL constraints
  • •2-3x lower memory usage via zero-copy parsing

Single SQLite Database

All your codebase knowledge in one portable file. Query with SQL, perform semantic search with vectors, and maintain a persistent knowledge graph.

  • •Portable single-file database
  • •SQL querying capabilities
  • •Vector storage with sqlite-vec
  • •HNSW indexing for fast semantic search

Code Graph Analysis

Comprehensive code analysis with entity extraction, relationship mapping, cross-reference detection, and architectural pattern recognition.

  • •Entity extraction (functions, classes, variables)
  • •Relationship mapping (calls, inheritance, imports)
  • •Cross-reference detection across files
  • •Architectural pattern recognition

LSP Code Intelligence

38 LSP tools providing real-time IDE features through 4-tier auto-detection system supporting 35 language servers.

  • •Go-to-definition navigation
  • •Hover information and type signatures
  • •Code completions
  • •Call and type hierarchy
  • •Diagnostics and error detection

35 Programming Languages

Universal code analysis via individual tree-sitter parsers. Web, systems, JVM, functional, and specialized languages—all with dedicated parser support.

  • •Individual tree-sitter parser per language
  • •Tree-sitter 0.25 based
  • •Consistent AST representation
  • •Language-specific entity extraction

Gitignore Filtering

Automatic respect for .gitignore files using ripgrep's ignore engine for bulletproof file filtering.

  • •All glob patterns (*, **, ?, [abc])
  • •Negation patterns (!)
  • •Directory-only patterns (/)
  • •Nested .gitignore files with proper precedence
  • •.git/info/exclude support

Priority Scanning

Intelligent file prioritization for optimal processing order—entry points first, tests last.

  • •Priority 1: Entry points (main, app, index, server)
  • •Priority 2: Core modules and configuration
  • •Priority 3: Source files (non-test)
  • •Priority 4: Test files
  • •Priority 5: Documentation

Context Graph Memory

AI agents that remember. Store architectural decisions, coding standards, and project knowledge across sessions with 7 structured note types.

  • •7 structured note types (ADR, STANDARD, OPTIMIZATION, FAILURE, REFACTOR, TODO, QUESTION)
  • •File context workflow with modification chains
  • •Code linking with stale context detection
  • •Context-first queries for efficiency

100% Local & Private

Your code never leaves your machine. Completely isolated environment with zero external dependencies.

  • •No code sent to external services
  • •No internet connection required
  • •No telemetry or analytics
  • •Complete data control

MCP Server Built-in

Native integration with Claude Desktop, Cline, and any MCP-compatible AI agent. 70 total tools including 27 Core + 38 LSP + 5 Architecture.

  • •27 Core analysis tools
  • •38 LSP code intelligence tools
  • •5 Architecture management tools
  • •Works with any MCP client

Semantic Search

Find code by meaning, not just keywords. Vector embeddings powered by local Jina embedding model.

  • •Local Jina embeddings (jina-embeddings-v2-base-code)
  • •No API keys required
  • •Sub-100ms search via HNSW vectors
  • •Natural language code discovery

Relationship Mapping

Understand how your code connects. Automatic detection of inheritance, implementation, function calls, imports, and data flow.

  • •Function call relationships
  • •Inheritance and implementation
  • •Import and dependency tracking
  • •Cross-file relationship detection