Semantic Designs Source Code Search Engine vs Shebe

Semantic Designs Source Code Search Engine searches and inspects indexed code using language structure, so queries can target constructs and complex statements as well as text patterns. It supports regular expressions and numeric values or ranges, and searches can disregard whitespace, line breaks, and comments. The maker says it can search millions of lines across tens of thousands of source files. Results include surrounding code and highlighted matches; users can open source text or launch an editor on the matching file. The engine also calculates Cyclomatic and Halstead complexity metrics and counts source, code, comment, and blank lines. Listed scanners include ABAP, C, C++, COBOL, Java, JavaScript, Python, PHP, SQL dialects, and XML, with beta scanners and custom options. Files are collected, scanned, and indexed on a recurring schedule. Results can be produced in XML for other graphical interfaces. The free evaluation covers 10,000 lines and requires registration; its license ends 90 days after download. Pricing for a production license is available on request.

Shebe is a local code-search tool that uses BM25 full-text search across code repositories. It ranks results and supports phrase searches, Boolean queries, and literal matching. Fourteen MCP tools serve coding agents with functions including search, repository indexing, file reading, and reference finding. Shebe runs without embeddings, a GPU, or a cloud service, but repositories must be cloned locally before indexing; remote repository URLs are not supported. Its text-based search does not provide semantic similarity, so related words such as “login” and “authenticate” may not match. Prebuilt binaries are listed for Linux x86_64 and macOS on Apple Silicon and Intel; Linux ARM64 is planned. Windows users need to build it from source. The installation guide covers MCP setup and Zed configuration and points to the organization for VS Code and other editor extensions. Shebe is free and licensed under Apache-2.0. The README reports 2 ms query latency and indexing rates from 1,928 to 11,210 files per second in its listed benchmarks.