# cased/kit

The toolkit for AI devtools context engineering. Build with codebase mapping, symbol extraction, and many kinds of code search.

Repository: https://github.com/cased/kit
Canonical: https://ross.abutalabs.com/products/cased-kit
Homepage: https://kit.cased.com
Language: Python
License: MIT
License Family: permissive
Last push: 2026-03-03T07:22:13+00:00

## Health v2 (maintenance only)
Score: 57/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 70, release rhythm 54, longevity 35
- inputs: {"age_days": 499, "days_push": 183, "days_rel": 227, "gap_med": 1.0, "n_releases_24m": 63}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1311, forks 84 (observed 2026-08-28T04:04:20.022038+00:00)

## What it is
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
- artifact type: library
- maturity: active
- function: search-engine, parser, rag, mcp, llm-inference, developer-tools, cli, sdk
- domain: developer-tools, large-language-models, apis
- platform: python, cli, cross-platform, self-hosted
- tags: 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
- cased/kit (main) score 57

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:20.022038+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:49:49.443046+00:00, confidence not recorded.
  - readme: https://github.com/cased/kit (fetched 2026-08-28T04:04:20.022038+00:00, sha 7710f0e41f30)
  - homepage: https://kit.cased.com (fetched 2026-08-29T12:07:49.182712+00:00, sha 4142d5865c0e)
  - site_page: https://kit.cased.com/introduction/quickstart (fetched 2026-08-29T12:07:49.192877+00:00, sha 70c8958f8c0c)
  - site_page: https://kit.cased.com/core-concepts/docstring-indexing (fetched 2026-08-29T12:07:49.230315+00:00, sha 8318bd417fba)
  - site_page: https://kit.cased.com/tutorials/docstring_search (fetched 2026-08-29T12:07:49.234946+00:00, sha 371fcc9858cc)
  - site_page: https://kit.cased.com/api/docstring-indexer (fetched 2026-08-29T12:07:49.237903+00:00, sha 182ab81a9cec)
  - site_page: https://kit.cased.com/changelog (fetched 2026-08-29T12:07:49.220491+00:00, sha a76effaeea53)
  - site_page: https://kit.cased.com/mcp/kit-dev-mcp (fetched 2026-08-29T12:07:49.240944+00:00, sha 3b5fbcada1f6)
  - site_page: https://kit.cased.com/api/repository (fetched 2026-08-29T12:07:49.243386+00:00, sha f650c1a34ed5)
- Data as of 2026-08-30T08:39:29.467469+00:00.