cased/kit

Health v2 · maintenance only

Adoption not part of the score

1311 stars · 84 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

kit is a Python toolkit for code intelligence and context engineering, providing codebase mapping, tree-sitter-based symbol extraction, grep/AST/semantic search, and docstring-based vector indexing. It can be used as a Python library, CLI, REST service, or MCP server to build LLM-powered developer tools like code reviewers and coding assistants.

Use cases

• build an AI code reviewer with repository context
• extract functions and classes from a codebase for LLM prompts
• semantic search over code using docstring embeddings
• give Claude or Cursor codebase analysis tools via MCP
• map file structure and dependencies of a large repo
• find all usages of a class or function across a repository
• generate PR summaries and commit messages with LLMs

When to choose

• you're building LLM-powered devtools, agents, or coding assistants that need precise code context
• you need multi-language symbol extraction and code search from Python
• you want a local, private MCP server for codebase analysis in AI editors
• you need semantic code search without shipping code to external services

When to avoid

• you only need a simple one-off grep or ripgrep search
• you need a full IDE or hosted code intelligence platform out of the box
• your project is not Python-based and you need a native library in another language

Facets

library · maturity active

search-engine parser rag mcp llm-inference developer-tools cli sdk developer-tools large-language-models apis python cli cross-platform self-hosted code-intelligence codebase-mapping symbol-extraction tree-sitter vector-search context-engineering code-search mcp-server claude-code code-review ai-agents retrieval-augmented-generation automation

Member repositories

For agents

markdown · JSON · MCP: product_card(name="cased/kit")