pip install embgrep              # core (fastembed + numpy)
pip install embgrep[cli]         # + click/rich CLI
pip install embgrep[mcp]         # + FastMCP server
pip install embgrep[all]         # everything

from embgrep import EmbGrep

eg = EmbGrep()

# Index a directory
eg.index("./my-project", patterns=["*.py", "*.md"])

# Semantic search
results = eg.search("database connection pooling", top_k=5)
for r in results:
    print(f"{r.file_path}:{r.line_start}-{r.line_end} (score: {r.score:.4f})")
    print(f"  {r.chunk_text[:80]}...")

# Incremental update (only changed files)
eg.update()

# Index statistics
status = eg.status()
print(f"{status.total_files} files, {status.total_chunks} chunks, {status.index_size_mb} MB")

eg.close()

# Index a project
embgrep index ./my-project --patterns "*.py,*.md"

# Search
embgrep search "error handling patterns"

# Filter by file type
embgrep search "async database query" --path-filter "%.py"

# Check status
embgrep status

# Update changed files
embgrep update

import embgrep

embgrep.index("./src")
results = embgrep.search("authentication middleware")
status = embgrep.status()
embgrep.update()

{
  "mcpServers": {
    "embgrep": {
      "command": "embgrep-mcp"
    }
  }
}

{
  "mcpServers": {
    "embgrep": {
      "command": "uvx",
      "args": ["--from", "embgrep[mcp]", "embgrep-mcp"]
    }
  }
}

flowchart TD
    A["📁 Files"] --> B["Smart Chunking\ncode: function-level\ndocs: heading-level"]
    B --> C["fastembed\nlocal embeddings"]
    C --> D["SQLite\nvector index"]
    D --> E["🔍 Query"]
    E --> F["Cosine Similarity\nranked results"]
    F --> G["✅ Matches\nwith context"]