index1
gladego 제작
Coding Agents & IDEs요약
AI memory system for coding agents — code index + cognitive facts, persistent across sessions.
설명
이 스킬이 하는 일
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.
사용 시점
- 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
예시 워크플로
User asks: how does the authentication flow work in this project?
- 1
Agent calls recall with query 'authentication flow'
- 2
index1 runs BM25 + vector hybrid search across indexed code and cognitive facts
- 3
Returns ranked summaries of relevant files and any recorded decisions about auth
- 4
Agent uses Grep for specific identifiers found in the summaries
- 5
Agent composes answer from summaries and targeted grep results
Explanation of the auth flow with file locations, using ~460 tokens instead of thousands from raw grep output
설치
clawhub install gladego/index1CLI 명령을 실행하거나, 프롬프트를 Claude Code, Cursor, Codex 등 사용하는 코딩 에이전트에 붙여넣으세요.