Semantic vector search over the codebase — find code by meaning, not exact names. Use when you need to locate implementations without knowing exact function/class names. Triggers on: "find code", "search codebase", "locate implementation", "what does X do"
中文简介正在准备中。当前显示原文说明。
实测评分 未实测
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Finds code by meaning using local vector embeddings (no API key, works offline). Complement to codebase-memory-mcp (structural) — use both for complete discovery.
| Use cocoindex-code | Use codebase-memory-mcp instead |
|---|---|
| "find code that handles rate limiting" | "who calls rateLimit()?" |
| "locate authentication middleware" | "what does AuthService import?" |
| "find all error handling patterns" | "trace path from HTTP handler to DB" |
| Exploring unfamiliar codebase | Tracing known functions |
| Fuzzy conceptual search | Exact structural traversal |
search{
"query": "string — natural language or code snippet",
"limit": 5,
"offset": 0,
"refresh_index": true,
"languages": ["python", "typescript"],
"paths": ["src/auth/*"]
}
Result: Array of {file_path, language, content, start_line, end_line, score}.
After getting results: Use the Read tool on file_path at start_line–end_line for full context.
refresh_index: false for consecutive searches in the same session (no code changes)languages filter to scope search (faster for single-language queries)paths filter to limit to a directory (triggers full scan — slower than language filter)Index not built yet: ccc index — or handled automatically on first MCP search.
After major changes: Index auto-refreshes on each MCP search call (refresh_index=True default).
Check status: ccc status shows chunks and file counts.
Switch embedding model: Edit ~/.cocoindex_code/global_settings.yml, then ccc reset && ccc index.
Warning: model switch requires full re-index — different vector dimensions are incompatible.
Python, JavaScript, TypeScript/TSX/JSX, Rust, Go, Java, C, C++, C#, SQL, Shell/Bash, Markdown, PHP, Lua, Ruby, Swift, Kotlin, Scala, R, HTML, CSS/SCSS, JSON, YAML/TOML, XML, Solidity, Pascal, Fortran, plain text.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Route a codebase question to the right tool — structural graph, semantic search, or risk analysis. Use when you need to find or understand code without knowing exact file names.
中文简介正在准备中。当前显示原文说明。
Auto-configure CLAUDE.md and claude/ knowledge docs for a new project. Use when setting up Brain Bootstrap in a new repository. Discovers the codebase, fills in templates, and writes project-specific configuration.
中文简介正在准备中。当前显示原文说明。
Use before any new feature, component, or behavioral change — when you need to explore requirements and design before writing code
中文简介正在准备中。当前显示原文说明。
Activate safety guards for the session. Use /careful before critical operations — blocks rm -rf, DROP TABLE, git push --force, kubectl delete namespace, docker system prune via PreToolUse hook.
中文简介正在准备中。当前显示原文说明。
Generate a user-facing changelog from git commits — categorize, filter noise, translate to user language. Runs in isolated fork context.
中文简介正在准备中。当前显示原文说明。
Save session state before context gets full or before ending. Writes current task state, branch, and loaded docs to claude/tasks/todo.md so the next session can resume cleanly.
中文简介正在准备中。当前显示原文说明。