{
  "id": 17583592,
  "title": "I ran ripgrep, Serena, claude-context and my own tool on the same repo",
  "url": "https://urgent.news/2026/11/01/i-ran-ripgrep-serena-claude-context-and-my-own-tool-on-the-same-repo",
  "topic": "ai",
  "section": "AI",
  "published": "2026-11-01T10:49:54.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/aakashpawar1999/i-ran-ripgrep-serena-claude-context-and-my-own-tool-on-the-same-repo-2m5p"
  },
  "original_language": "en",
  "account": "Four methods were tested to find code within the Flask repository: ripgrep, Serena, Claude-Context, and Semlith. The setup was a Flask 3.1.3 project on an M1 MacBook Air with 8GB of memory. Ripgrep, a plain text search tool, returned the correct eight lines in milliseconds. Serena, a language server-based tool, also found the correct lines, albeit after a few seconds of processing. Unlike ripgrep, Serena can edit code. Claude-Context, a tool using Milvus embeddings for vector storage, indexed the files but took over 21 minutes to complete the task, and the index wasn't fully ready during testing. Semlith, the tool built by the reporter, indexed all 211 files in 84.3 seconds. While Serena was the quickest to set up, its search performance was slower compared to Semlith, which had a faster search time after indexing.",
  "summary": "There are a lot of ways to let a coding agent find code now. Plain grep, a language server behind MCP, a vector database, a local index. Every README says its way is the right one, so I wanted to see them do the same job on the same code. I build one of these tools, Semlith, so treat my bias accordingly. That's also why I'm showing the questions it got wrong. The setup is Flask 3.1.3 on an M1…",
  "key_points": [
    "Ripgrep found correct code lines in milliseconds",
    "Serena found correct lines but took seconds to process",
    "Semlith indexed all files in 84.3 seconds"
  ],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}