I ran ripgrep, Serena, claude-context and my own tool on the same repo

Описание и применение

Сравнение производительности ripgrep, Serena, claude‑context и Semlith на репозитории Flask 3.1.3: ripgrep быстрее при точном поиске, Serena удобна для редактирования кода, claude‑context требует длительной настройки и иногда индекс incomplete, Semlith балансирует скорость и семантическую релевантность.

Задача

Compare how different code‑search tools perform on the same repository when answering the same query.

Результат

ripgrep was fastest for exact identifier queries; Serena excelled at symbol‑level edits; claude‑context required the longest setup and had incomplete indexing; Semlith balanced speed and semantic relevance, returning relevant code and documentation.

Рабочий процесс

• Clone Flask 3.1.3 repo
• Run ripgrep search with and without identifier
• Set up Serena environment and index repository
• Query Serena with identifier and regex
• Set up claude‑context with local Milvus and Ollama
• Run claude‑context indexing and search
• Run Semlith index and search
• Compare results for specific queries
• Measure setup times and search accuracy

Доказательства

ripgrep 15.2.0, Serena 2.1.0, claude-context 0.1.15 (with Milvus 3.0.3 and Ollama running nomic-embed-text) and semlith 0.50.0.

Источник

Setup on Flask 3.1.3 on an M1 MacBook Air with 8 GB.

Источник

Serena gives the agent symbol tools backed by real language servers, over 40 languages.

Источник

claude-context is Zilliz's MCP server. It chunks code, embeds it and stores the vectors in Milvus, with hybrid search on top.

Источник

Semlith index .
indexed 211 files (2778 chunks, 5 images) in 84.3s

Источник