About leann-search
leann-search is a skill for searching code by meaning with LEANN, suited to finding concepts, implementation patterns, and related code. It uses sentence embeddings and ranks results by semantic similarity; exact identifiers, regex patterns, and file paths are better handled with Grep or Glob.
Key features
- 01Search code by meaning
- 02Rank results by semantic similarity
- 03List available indexes
- 04Rebuild project indexes
- 05Provide a Claude Code MCP tool
Use cases
- 01Find authentication or error-handling logic
- 02Explore streaming or provider architecture
- 03Locate similar implementations using different terms
MCP support
In Claude Code, it provides the `leann_search` MCP tool for semantic queries against a named index.
Install
Copy the command and run it in a terminal.
$
npx skills add https:/After installing, type/leann-searchin Claude Code to confirm it loaded.
Details
From the project READMELEANN Semantic Search
Use LEANN for meaning-based code search instead of grep.
When to Use
- Conceptual queries: "how does authentication work", "where are errors handled"
- Understanding patterns: "streaming implementation", "provider architecture"
- Finding related code: code that's semantically similar but uses different terms
When NOT to Use
- Exact matches: Use Grep for
class Foo,def bar, specific identifiers - Regex patterns: Use Grep for
error.*handling,import.*from - File paths: Use Glob for
*.test.ts,src/**/*.py
Commands
# Search the current project's index
leann search <index-name> "<query>" --top-k 5
# List available indexes
leann list
# Example
leann search rigg "how do providers handle streaming" --top-k 5
MCP Tool (in Claude Code)
leann_search(index_name="rigg", query="your semantic query", top_k=5)
Rebuilding the Index
When codebase changes significantly:
cd /path/to/project
leann build <project-name> --docs src tests scripts \
--file-types '.ts,.py,.md,.json' \
--no-recompute --no-compact \
--embedding-mode sentence-transformers \
--embedding-model all-MiniLM-L6-v2
How It Works
- LEANN uses sentence embeddings to understand meaning
- Searches find conceptually similar code, not just text matches
- Results ranked by semantic similarity score (0-1)
Grep vs LEANN Decision
| Query Type | Tool | Example |
|---|---|---|
| Natural language | LEANN | "how does caching work" |
| Class/function name | Grep | "class CacheManager" |
| Pattern matching | Grep | error|warning |
| Find implementations | LEANN | "rate limiting logic" |
Comments
Markdown supported