Cased Kit

Stale
GitHub Python MIT

Description

The toolkit for AI devtools context engineering. Build with codebase mapping, symbol extraction, and many kinds of code search to help AI agents better understand and operate on codebases.

Key Features

  • Codebase mapping and symbol extraction for functions, classes, and constructs
  • Multiple code search modes: regex (ripgrep), AST pattern matching, and symbol usage tracking
  • LLM context preparation with intelligent file chunking for context windows
  • AI-powered code summarization and docstring indexing for semantic search
  • Dependency analysis with import mapping and LLM-friendly context generation
  • Multi-repo support for monorepos, microservices, and cross-repo searches

Use Cases

💡 Building AI-powered code review tools with full codebase understanding
💡 Creating intelligent IDE assistants that understand project structure
💡 Generating code documentation and dependency reports automatically
💡 Searching across multiple repositories for shared patterns and usages
💡 Preparing code context for LLM-based code generation workflows

Tags

coding agent tools python

Categories

💻 Coding Agent

Quick Start

Install: uv pip install cased-kit. Or globally: uv tool install cased-kit. Python: from kit import Repository; repo = Repository('/path/to/repo'). CLI: kit file-tree /path/to/repo. Claude Code plugin: /plugin marketplace add cased/claude-code-plugins.
Visit GitHub

Related Projects