The toolkit for AI devtools context engineering. Build with codebase mapping, symbol extraction, and many kinds of code search.
See the codekit is a production-ready 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. Work with kit directly from Python, or with MCP + function calling, REST, or CLI.
Explore the full documentation for detailed usage, advanced features, and practical examples. Check out docs for kit's local dev MCP server, too.
uv pip install cased-kit
# With ML features for advanced analysis and vector search
uv pip install 'cased-kit[all]'
If you want to use the kit CLI globally without affecting your system Python, use uv tool install. This creates an isolated environment for kit while making the CLI available from anywhere:
# Install the base kit CLI globally
uv tool install cased-kit
# Everything (including MCP server and all features)
uv tool install cased-kit[all]
After installation, the kit and kit-dev-mcp commands will be available globally. To manage your uv tool installations:
# List installed tools
uv tool list
# Uninstall if needed
uv tool uninstall cased-kit
Use kit directly in Claude Code with the official plugin:
/plugin marketplace add cased/claude-code-plugins
/plugin install kit-cli
The plugin gives Claude autonomous access to kit's codebase analysis tools. Claude will automatically use kit when you ask questions like:
See the Claude Code Integration Guide for details.
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")
# Load a private GitHub repo (automatically uses KIT_GITHUB_TOKEN if set)
repo = Repository("https://github.com/owner/private-repo")
# Or explicitly
repo = Repository("https://github.com/owner/private-repo", github_token="ghp_...")
# At a specific commit, tag, or branch
# repo = Repository("https://github.com/owner/repo", ref="v1.2.3")
# For multiple repos (microservices, monorepos, team projects)
from kit import MultiRepo
repos = MultiRepo(["~/code/frontend", "~/code/backend", "~/code/shared"])
repos.search("handleAuth") # Search across all repos
# Explore a 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", ...}, ...]
# Access git metadata
print(f"Current SHA: {repo.current_sha}")
print(f"Branch: {repo.current_branch}")
# Read one file
main_py = repo.get_file_content("src/main.py")
# Read many files in one round-trip
contents = repo.get_file_content([
"src/main.py",
"src/utils/helper.py",
"tests/test_main.py",
])
print(contents["src/utils/helper.py"])
kit provides a comprehensive CLI for repository analysis and code exploration.
Repository Analysis:
# Get repository file structure
kit file-tree /path/to/repo
# Extract symbols (functions, classes, etc.)
kit symbols /path/to/repo --format table
# Search for code patterns
kit search /path/to/repo "def main" --pattern "*.py"
# Find symbol usages
kit usages /path/to/repo "MyClass"
# Export data for external tools
kit export /path/to/repo symbols symbols.json
PR Reviews:
# Initialize configuration
kit review --init-config
# Review GitHub PRs
kit review --dry-run https://github.com/owner/repo/pull/123
kit review https://github.com/owner/repo/pull/123
# Review local git diffs (no PR required!)
kit review main..feature # Compare branches
kit review HEAD~3..HEAD # Review last 3 commits
kit review --staged # Review staged changes
PR Summaries:
# Generate PR summaries for quick triage
kit summarize https://github.com/owner/repo/pull/123
kit summarize --update-pr-body https://github.com/owner/repo/pull/123
Commit Messages:
# Generate intelligent commit messages from staged changes
git add . # Stage your changes first
kit commit # Analyze and commit with AI-generated message
Package Search (requires Chroma API key):
kit package-search-grep numpy "def.*fft" --max-results 10 # Plain grep-style output
kit package-search-grep numpy "def.*fft" --json # Structured JSON output
kit package-search-hybrid django "authentication middleware"
kit package-search-read requests "requests/models.py"
See the CLI Documentation for comprehensive usage examples.
kit helps your apps and agents understand and interact with codebases, with components to build your own AI-powered developer tools.
Explore Code Structure:
repo.get_file_tree() to list all files and directories. You can also pass a subdirectory for a more limited scan.repo.extract_symbols() to identify functions, classes, and other code constructs, either across the entire repository or within a single file.repo.extract_symbols_incremental() to get fast, cache-aware symbol extraction—best when dealing with small changes to repositories.Pinpoint Information:
repo.search_text() (automatically uses ripgrep when available for 10x speedup).repo.find_symbol_usages().Prepare Code for LLMs & Analysis:
repo.chunk_file_by_lines() or repo.chunk_file_by_symbols().repo.extract_context_around_line().Generate Code Summaries:
Summarizer (e.g., summarizer.summarize_file(), summarizer.summarize_function()).DocstringIndexer and query it with SummarySearcher for intelligent code discovery.Analyze Code Dependencies:
repo.get_dependency_analyzer() to understand your codebase structure.analyzer.generate_dependency_report() and analyzer.generate_llm_context().Search Package Source Code (via Chroma):
ChromaPackageSearch for regex patterns and semantic queries.Repository Versioning & Historical Analysis:
ref parameter.repo.current_sha, repo.current_branch, etc.Multi-Repository Analysis:
MultiRepo for microservices, monorepos, or team projects.kit multi search, kit multi deps, kit multi summary.kit includes an enhanced MCP (Model Context Protocol), kit-dev, designed especially for individual local dev work. It includes kit's production-grade code intelligence and context building, and adds in multi-source documentation research and package searching.
Environment Variables: OPENAI_API_KEY, OPENAI_BASE_URL (for proxies/custom endpoints), ANTHROPIC_API_KEY
→ Full kit-dev MCP Documentation
As both demonstrations of this library, and as standalone products,
kit ships with MIT-licensed, CLI-based pull request review and summarization features.
The pull request reviewer ranks with the better closed-source paid options, but at
a fraction of the cost with cloud models. At Cased we use kit extensively
with models like Sonnet 4 and gpt4.1, paying just for the price of tokens.
kit review --init-config
kit review https://github.com/owner/repo/pull/123
→ Complete PR Reviewer Documentation
For quick PR triage and understanding, kit includes a fast, cost-effective PR summarization feature.
Perfect for teams that need to quickly understand what PRs do before deciding on detailed review.
kit summarize https://github.com/owner/repo/pull/123
kit summarize --update-pr-body https://github.com/owner/repo/pull/123
Key Features:
Generate intelligent commit messages from staged changes using the same repository intelligence:
git add . # Stage your changes
kit commit # Analyze and commit with AI-generated message
Full Documentation - Detailed usage, advanced features, and practical examples. Full REST documentation is also available.
kit-dev MCP Documentation - Complete guide for the enhanced MCP server
Changelog - Track all changes and improvements across kit releases
MIT License
To contribute, fork the repository, make your changes, and submit a pull request.
(top 24 of 42)
600 followers · starred May 2025
1,303 followers · starred Nov 2025
115 followers · starred Nov 2025
1,679 followers · starred May 2025
The toolkit for AI devtools context engineering. Build with codebase mapping, symbol extraction, and many kinds of code search.
See the codekit is a production-ready 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. Work with kit directly from Python, or with MCP + function calling, REST, or CLI.
Explore the full documentation for detailed usage, advanced features, and practical examples. Check out docs for kit's local dev MCP server, too.
uv pip install cased-kit
# With ML features for advanced analysis and vector search
uv pip install 'cased-kit[all]'
If you want to use the kit CLI globally without affecting your system Python, use uv tool install. This creates an isolated environment for kit while making the CLI available from anywhere:
# Install the base kit CLI globally
uv tool install cased-kit
# Everything (including MCP server and all features)
uv tool install cased-kit[all]
After installation, the kit and kit-dev-mcp commands will be available globally. To manage your uv tool installations:
# List installed tools
uv tool list
# Uninstall if needed
uv tool uninstall cased-kit
Use kit directly in Claude Code with the official plugin:
/plugin marketplace add cased/claude-code-plugins
/plugin install kit-cli
The plugin gives Claude autonomous access to kit's codebase analysis tools. Claude will automatically use kit when you ask questions like:
See the Claude Code Integration Guide for details.
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")
# Load a private GitHub repo (automatically uses KIT_GITHUB_TOKEN if set)
repo = Repository("https://github.com/owner/private-repo")
# Or explicitly
repo = Repository("https://github.com/owner/private-repo", github_token="ghp_...")
# At a specific commit, tag, or branch
# repo = Repository("https://github.com/owner/repo", ref="v1.2.3")
# For multiple repos (microservices, monorepos, team projects)
from kit import MultiRepo
repos = MultiRepo(["~/code/frontend", "~/code/backend", "~/code/shared"])
repos.search("handleAuth") # Search across all repos
# Explore a 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", ...}, ...]
# Access git metadata
print(f"Current SHA: {repo.current_sha}")
print(f"Branch: {repo.current_branch}")
# Read one file
main_py = repo.get_file_content("src/main.py")
# Read many files in one round-trip
contents = repo.get_file_content([
"src/main.py",
"src/utils/helper.py",
"tests/test_main.py",
])
print(contents["src/utils/helper.py"])
kit provides a comprehensive CLI for repository analysis and code exploration.
Repository Analysis:
# Get repository file structure
kit file-tree /path/to/repo
# Extract symbols (functions, classes, etc.)
kit symbols /path/to/repo --format table
# Search for code patterns
kit search /path/to/repo "def main" --pattern "*.py"
# Find symbol usages
kit usages /path/to/repo "MyClass"
# Export data for external tools
kit export /path/to/repo symbols symbols.json
PR Reviews:
# Initialize configuration
kit review --init-config
# Review GitHub PRs
kit review --dry-run https://github.com/owner/repo/pull/123
kit review https://github.com/owner/repo/pull/123
# Review local git diffs (no PR required!)
kit review main..feature # Compare branches
kit review HEAD~3..HEAD # Review last 3 commits
kit review --staged # Review staged changes
PR Summaries:
# Generate PR summaries for quick triage
kit summarize https://github.com/owner/repo/pull/123
kit summarize --update-pr-body https://github.com/owner/repo/pull/123
Commit Messages:
# Generate intelligent commit messages from staged changes
git add . # Stage your changes first
kit commit # Analyze and commit with AI-generated message
Package Search (requires Chroma API key):
kit package-search-grep numpy "def.*fft" --max-results 10 # Plain grep-style output
kit package-search-grep numpy "def.*fft" --json # Structured JSON output
kit package-search-hybrid django "authentication middleware"
kit package-search-read requests "requests/models.py"
See the CLI Documentation for comprehensive usage examples.
kit helps your apps and agents understand and interact with codebases, with components to build your own AI-powered developer tools.
Explore Code Structure:
repo.get_file_tree() to list all files and directories. You can also pass a subdirectory for a more limited scan.repo.extract_symbols() to identify functions, classes, and other code constructs, either across the entire repository or within a single file.repo.extract_symbols_incremental() to get fast, cache-aware symbol extraction—best when dealing with small changes to repositories.Pinpoint Information:
repo.search_text() (automatically uses ripgrep when available for 10x speedup).repo.find_symbol_usages().Prepare Code for LLMs & Analysis:
repo.chunk_file_by_lines() or repo.chunk_file_by_symbols().repo.extract_context_around_line().Generate Code Summaries:
Summarizer (e.g., summarizer.summarize_file(), summarizer.summarize_function()).DocstringIndexer and query it with SummarySearcher for intelligent code discovery.Analyze Code Dependencies:
repo.get_dependency_analyzer() to understand your codebase structure.analyzer.generate_dependency_report() and analyzer.generate_llm_context().Search Package Source Code (via Chroma):
ChromaPackageSearch for regex patterns and semantic queries.Repository Versioning & Historical Analysis:
ref parameter.repo.current_sha, repo.current_branch, etc.Multi-Repository Analysis:
MultiRepo for microservices, monorepos, or team projects.kit multi search, kit multi deps, kit multi summary.kit includes an enhanced MCP (Model Context Protocol), kit-dev, designed especially for individual local dev work. It includes kit's production-grade code intelligence and context building, and adds in multi-source documentation research and package searching.
Environment Variables: OPENAI_API_KEY, OPENAI_BASE_URL (for proxies/custom endpoints), ANTHROPIC_API_KEY
→ Full kit-dev MCP Documentation
As both demonstrations of this library, and as standalone products,
kit ships with MIT-licensed, CLI-based pull request review and summarization features.
The pull request reviewer ranks with the better closed-source paid options, but at
a fraction of the cost with cloud models. At Cased we use kit extensively
with models like Sonnet 4 and gpt4.1, paying just for the price of tokens.
kit review --init-config
kit review https://github.com/owner/repo/pull/123
→ Complete PR Reviewer Documentation
For quick PR triage and understanding, kit includes a fast, cost-effective PR summarization feature.
Perfect for teams that need to quickly understand what PRs do before deciding on detailed review.
kit summarize https://github.com/owner/repo/pull/123
kit summarize --update-pr-body https://github.com/owner/repo/pull/123
Key Features:
Generate intelligent commit messages from staged changes using the same repository intelligence:
git add . # Stage your changes
kit commit # Analyze and commit with AI-generated message
Full Documentation - Detailed usage, advanced features, and practical examples. Full REST documentation is also available.
kit-dev MCP Documentation - Complete guide for the enhanced MCP server
Changelog - Track all changes and improvements across kit releases
MIT License
To contribute, fork the repository, make your changes, and submit a pull request.
(top 24 of 42)
600 followers · starred May 2025
1,303 followers · starred Nov 2025
115 followers · starred Nov 2025
1,679 followers · starred May 2025