Перейти к содержимому
TakoAPI
Назад к навыкам

index1

от gladego

Coding Agents & IDEs
547Число загрузок по данным clawskills.sh
0Просмотры
0 лайковВойдите, чтобы поставить лайк навыку
—Ещё нет оценок
Ваша оценка

Кратко

AI memory system for coding agents — code index + cognitive facts, persistent across sessions.

Описание

Что делает этот навык

Persistent memory system for coding agents that combines BM25 full-text and vector semantic search over indexed code and documents. Stores cognitive facts like decisions and lessons learned across sessions via 6 MCP tools. Works out of the box with built-in ONNX embeddings, no external embedding service required.

Hybrid BM25 + vector search with RRF fusion finds relevant code for exploratory questions where grep requires knowing the exact identifier, and can cross language boundaries that grep cannot.

Когда его использовать

  • Finding how a feature works by concept rather than exact symbol name
  • Searching an English codebase using a Chinese or Japanese query
  • Recording architectural decisions so future agent sessions retain context
  • Reducing context window consumption when a keyword appears hundreds of times
  • Rebuilding the search index after adding new source files or docs

Пример сценария

ВВОД

User asks: how does the authentication flow work in this project?

АГЕНТ
  1. 1

    Agent calls recall with query 'authentication flow'

  2. 2

    index1 runs BM25 + vector hybrid search across indexed code and cognitive facts

  3. 3

    Returns ranked summaries of relevant files and any recorded decisions about auth

  4. 4

    Agent uses Grep for specific identifiers found in the summaries

  5. 5

    Agent composes answer from summaries and targeted grep results

ВЫВОД

Explanation of the auth flow with file locations, using ~460 tokens instead of thousands from raw grep output

Установка

clawhub install gladego/index1

Выполните команду CLI или вставьте промпт в Claude Code, Cursor, Codex — любой кодинг-агент, которым пользуетесь.

Ссылки