← 트렌딩

Tangerine Index는 ChatGPT 이후 나온 프로덕트와 사람들의 반응을 싣습니다.

jcodemunch-mcp

github.com

Symbol-level code retrieval for AI agents: fetch the function you need, not the whole file. Runs locally. 96.2% fewer tokens per lookup on average than grep-and-read on our 15-lookup benchmark. Works with Claude Code, Cursor, Codex and any MCP client. Free for non-commercial use; commercial use needs a one-time license.

오픈소스

github.com 방문외부 사이트GitHub2,837 스타외부 사이트

설치·연결

공식 MCP Registry, Homebrew, npm, PyPI, crates.io에서 저장소나 도메인으로 맞춰 하루 한 번 가져옵니다.

반응 (1)

비슷한 프로덕트

설명이 비슷한 순

  1. Sourcerer

    MCP for semantic code search that reduces token waste

    Hacker News9점GitHub스타 121github.com오픈소스반응 2개최근 반응

  2. Reference MCP

    let your AI agents search each other's past sessions

    Hacker News5점GitHub스타 22github.com오픈소스반응 2개최근 반응

  3. Context Mode

    315 KB of MCP output becomes 5.4 KB in Claude Code

    Hacker News84점GitHub스타 33,732github.comCLI오픈소스반응 2개최근 반응

  4. token-savior

    MCP server that gets Claude to 97.9% (188/192) on a real coding benchmark at -80% active tokens and -83% wall time, vs 78.3% plain. Structural code navigation + persistent memory engine. Works with every MCP client.

    GitHub스타 1,214github.com오픈소스최근 반응

  5. Graft

    Claude Code hooks that cut grep tokens by 42%

    Hacker News39점GitHub스타 11,158github.comCLI오픈소스반응 3개최근 반응