What is CLDK?

CLDK (CodeLLM-DevKit) is a Python library that loads a codebase and exposes typed models of its classes, methods, fields, and call graph. All queries are issued through a single analysis object, which answers structural questions (such as which methods call a given method, or which methods it invokes) without manual file parsing or ad hoc composition of external tools.

The programming model

Every CLDK program follows the same three steps: select a language, analyze a project, and query the resulting typed models.

1. Call the per-language factory for the target language, for example CLDK.java(...). This selects the analysis backend.

2. Build the analysis object by pointing it at a project: CLDK.java(project_path="commons-cli"). The backend runs at this step and produces the program model.

3. Query the typed models with get_classes(), get_method(...), get_call_graph(), and related methods. The returned objects can be read, traversed, serialized, or passed to other tools.

Java

from cldk import CLDK
from cldk.analysis import AnalysisLevel

# 1. select the language  2. analyze the project  3. query
analysis = CLDK.java(
    project_path="commons-cli",
    analysis_level=AnalysisLevel.call_graph,
)

print(len(analysis.get_classes()), "classes")
print(analysis.get_call_graph())          # -> networkx.DiGraph
# 23 classes
# DiGraph with caller -> callee edges

Python

from cldk import CLDK
from cldk.analysis import AnalysisLevel

# Python requires a project_path (no single-file mode)
analysis = CLDK.python(
    project_path="my_pkg",
    analysis_level=AnalysisLevel.call_graph,
)

print(len(analysis.get_classes()), "classes")
print(analysis.get_call_graph())          # -> networkx.DiGraph

Analysis levels

analysis_level defaults to AnalysisLevel.symbol_table, which resolves classes, methods, and fields. Call graphs, callers, and callees require AnalysisLevel.call_graph; pass it explicitly when call relationships are needed.

A language-specific backend sits behind the same API:

flowchart LR
    A["CLDK.<lang>(project_path)"] --> B["analysis object"]
    B --> C["Typed program model"]
    C --> D["Symbol table"]
    C --> E["Call graph"]
    C --> F["Class structure / CRUD"]

The backend is selected by language: Java uses CodeAnalyzer over WALA, and Python uses its own static-analysis engine. The query code is largely identical across languages; only the backend differs.

Language coverage

Every supported language is queried through the same analysis API, backed by a language-specific engine. Java and Python are supported today, with Java offering the deepest analysis, including class-hierarchy and CRUD extraction. TypeScript is available in beta: its symbol table and call graph are solid and queryable through CLDK.typescript(...), while framework entrypoint detection is still in progress. Go and Rust are under active development.

Language	Status	Symbol table	Call graph / callers / callees
Java	Supported	Yes	Yes
Python	Supported	Yes	Yes
TypeScript	Beta	Yes	Yes
Go	In development	Planned	Planned
Rust	In development	Planned	Planned

Next steps

Quickstart Install CLDK and run your first analysis in a couple of minutes.

Core concepts Symbol tables, call graphs, and analysis levels.

Common tasks Task-oriented snippets: get methods, build a call graph, find callers.

API reference Per-language analysis APIs and the typed data models.