SDKs

A CLDK SDK (a frontend) is an analysis API over the canonical JSON that the codeanalyzer backends produce. Because the backends perform the language analysis, each SDK exposes the same call graphs, symbol tables, and reachability data in its host language.

This is the frontend layer. For the analyzers behind it, see the backends overview.

Maturity tiers

Mature production-ready  ·  Alpha experimental  ·  Help wanted contributors wanted  ·  Stub not started

Frontends (SDKs)

The SDK you write against. Each is an analysis API over the canonical JSON.

SDK	Repository	Maturity
Python	codellm-devkit/python-sdk	Mature
TypeScript	codellm-devkit/typescript-sdk	Alpha
Java	Not started	Help wanted Stub
Rust	Not started	Help wanted Stub
Go	Not started	Help wanted Stub

Pick an SDK

Python SDK The reference implementation. Install cldk from PyPI and query Java, Python, and TypeScript projects through one analysis API.

TypeScript SDK Experimental (alpha). A TypeScript/Node frontend over the same canonical analysis JSON. Track progress on GitHub.

Add a frontend Help wanted. A new frontend can consume every existing backend; see the roadmap and starting points for a native SDK.

Adding a language pack

A CLDK skill scaffolds a whole new language (a codeanalyzer-<lang> backend plus the SDK bindings) end to end. See codellm-devkit/developer-skillset.

Same contract, every language

Each SDK exposes the same analysis vocabulary because they all read the single schema the backends serialize:

• A per-language factory, e.g. CLDK.java(project_path=...), constructs the analysis object.
• The core methods (get_symbol_table, get_call_graph, get_callers, get_callees, and related calls) return the same typed models.
• Adding a backend makes the new language available to every SDK that consumes the shared schema.

The Python SDK is stable and the recommended starting point. The TypeScript SDK is experimental and evolving. The Java, Rust, and Go frontends are not yet built; see Add a Rust frontend for the form a native SDK takes.