Ted Nyman Ted Nyman

Build AI DevTools with kit

kit is an open source toolkit from Cased for building AI DevTools
Build AI DevTools with kit

TL;DR

kit gives any LLM-powered app IDE-grade knowledge of a repo. Search, extract symbols, build dependency graphs, or ask for AI summaries in two lines of Python—or expose everything as JSON-schema tools the model can call by itself.

from kit import Repository
repo = Repository("./")
print(repo.search_text("TODO"))
print(repo.get_summarizer().summarize_file("api/app.py"))

Prefer MCP? Run python -m kit.mcp and you’re all set.

Why we built it

We use kit to power Cased’s DevOps agent. We think the building blocks for developer tools should be free and open source.

Quick tour

CapabilityOne-linerUse-case
File treerepo.get_file_tree()tree-view in chat
Text searchrepo.search_text("AuthError")”grep inside ChatGPT”
Symbolsrepo.extract_symbols("services/payments.py")jump-to-definition w/o LSP
Dependenciesrepo.get_dependency_analyzer("python").build_dependency_graph()import spaghetti viz
Summariesrepo.get_code_summary(file_path="api/app.py")PR descriptions

Deep dive – a multi-turn session

  1. Open repo
{
  "name": "open_repository",
  "arguments": { "path_or_url": "/workspace/my-app" }
}
  1. User: “Where is calculate_price defined?”
  2. Model ➜ search_code → finds services/pricing.py:120.
  3. Model âžś get_file_content for that file, responds with snippet.
  4. User: “Why does it return NaN?”
  5. Model ➜ extract_symbols → isolates the function → get_code_summary → explains in plain English.

No if/else orchestration in your backend—just register the schema.

Running in-process vs. server

Get started

pip install cased-kit   # core + FastAPI server
python -m kit.mcp       # starts on localhost:8000

Docs: https://kit.cased.com | GitHub: https://github.com/cased/kit

Happy hacking!