cased-kit 0.2.0

A modular toolkit for LLM-powered codebase understanding.

kit 🛠️ Code Intelligence Toolkit

kit is a production-ready Python toolkit for codebase mapping, symbol extraction, code search, and building LLM-powered developer tools, agents, and workflows.

Use kit to build things like code reviewers, code generators, even IDEs, all enriched with the right code context.

Quick Installation

Install from PyPI

# Standard installation (all features, including the kit-mcp server)
pip install cased-kit

Install from Source

git clone https://github.com/cased/kit.git
cd kit
uv venv .venv
source .venv/bin/activate
uv pip install -e .

Basic Usage

from kit import Repository

# Load a local repository
repo = Repository("/path/to/your/local/codebase")

# Load a remote public GitHub repo
# repo = Repository("https://github.com/owner/repo")

# Explore the repo
print(repo.get_file_tree())
# Output: [{"path": "src/main.py", "is_dir": False, ...}, ...]

print(repo.extract_symbols('src/main.py'))
# Output: [{"name": "main", "type": "function", "file": "src/main.py", ...}, ...]

Key Features & Capabilities

kit helps your apps and agents understand and interact with codebases, with components to build your own AI-powered developer tools.

• Explore Code Structure:

  • High-level view with repo.get_file_tree() to list all files and directories.
  • Dive down with repo.extract_symbols() to identify functions, classes, and other code constructs, either across the entire repository or within a single file.

• Pinpoint Information:

  • Run regular expression searches across your codebase using repo.search_text().
  • Track specific symbols (like a function or class) with repo.find_symbol_usages().

• Prepare Code for LLMs & Analysis:

  • Break down large files into manageable pieces for LLM context windows using repo.chunk_file_by_lines() or repo.chunk_file_by_symbols().
  • Get the full definition of a function or class off a line number within it using repo.extract_context_around_line().

• Generate Code Summaries:

  • Use LLMs to create natural language summaries for files, functions, or classes using the Summarizer (e.g., summarizer.summarize_file(), summarizer.summarize_function()).
  • Build a searchable semantic index of these AI-generated docstrings with DocstringIndexer and query it with SummarySearcher to find code based on intent and meaning.

• Analyze Code Dependencies:

  • Map import relationships between modules using repo.get_dependency_analyzer() to understand your codebase structure.
  • Generate dependency reports and LLM-friendly context with analyzer.generate_dependency_report() and analyzer.generate_llm_context().

• And much more... kit also offers capabilities for semantic search on raw code, building custom context for LLMs, and more.

MCP Server

The kit tool includes an MCP (Model Context Protocol) server that allows AI agents and other development tools to interact with a codebase programmatically.

MCP support is currently in alpha. Add a stanza like this to your MCP tool:

{
  "mcpServers": {
    "kit-mcp": {
      "command": "python",
      "args": ["-m", "kit.mcp"]
    }
  }
}

The python executable invoked must be the one where cased-kit is installed. If you see ModuleNotFoundError: No module named 'kit', ensure the Python interpreter your MCP client is using is the correct one.

Documentation

Explore the Full Documentation for detailed usage, advanced features, and practical examples.

License

MIT License

Contributing

Please see our Roadmap for project directions.