chore: release v0.2.4

Feature/claude code research

README.md

@@ -16,7 +16,7 @@ LEANN is an innovative vector database that democratizes personal AI. Transform
 
 LEANN achieves this through *graph-based selective recomputation* with *high-degree preserving pruning*, computing embeddings on-demand instead of storing them all. [Illustration Fig →](#️-architecture--how-it-works) | [Paper →](https://arxiv.org/abs/2506.08276)
 
-**Ready to RAG Everything?** Transform your laptop into a personal AI assistant that can search your **[file system](#-personal-data-manager-process-any-documents-pdf-txt-md)**, **[emails](#-your-personal-email-secretary-rag-on-apple-mail)**, **[browser history](#-time-machine-for-the-web-rag-your-entire-browser-history)**, **[chat history](#-wechat-detective-unlock-your-golden-memories)**, or external knowledge bases (i.e., 60M documents) - all on your laptop, with zero cloud costs and complete privacy.
+**Ready to RAG Everything?** Transform your laptop into a personal AI assistant that can search your **[codebase](#-claude-code-integration-transform-your-development-workflow)**, **[file system](#-personal-data-manager-process-any-documents-pdf-txt-md)**, **[emails](#-your-personal-email-secretary-rag-on-apple-mail)**, **[browser history](#-time-machine-for-the-web-rag-your-entire-browser-history)**, **[chat history](#-wechat-detective-unlock-your-golden-memories)**, or external knowledge bases (i.e., 60M documents) - all on your laptop, with zero cloud costs and complete privacy.
 
 
 
@@ -211,6 +211,30 @@ All RAG examples share these common parameters. **Interactive mode** is availabl
 
 </details>
 
+### 🚀 Claude Code Integration: Transform Your Development Workflow!
+
+**The future of code assistance is here.** Transform your development workflow with LEANN's native MCP integration for Claude Code. Index your entire codebase and get intelligent code assistance directly in your IDE.
+
+<p align="center">
+  <img src="https://img.shields.io/badge/MCP-Native%20Integration-blue?style=flat-square" alt="MCP Integration">
+  <a href="https://github.com/yichuan-w/LEANN/tree/feature/graph-partition-support?tab=readme-ov-file#rag-on-everything"><img src="https://img.shields.io/twitter/url?url=https%3A%2F%2Fgithub.com%2Fyichuan-w%2FLEANN&style=social" alt="Twitter"></a>
+</p>
+
+**Key features:**
+- 🔍 **Semantic code search** across your entire project
+- 📚 **Context-aware assistance** for debugging and development
+- 🚀 **Zero-config setup** with automatic language detection
+- 🔒 **Complete privacy** - your code never leaves your machine
+
+```bash
+# Install LEANN globally for MCP integration
+uv tool install leann-core
+
+# Setup is automatic - just start using Claude Code!
+```
+
+**Ready to supercharge your coding?** [Complete Setup Guide →](packages/leann-mcp/README.md)
+
 ### 📄 Personal Data Manager: Process Any Documents (`.pdf`, `.txt`, `.md`)!
 
 Ask questions directly about your personal PDFs, documents, and any directory containing your files!
@@ -415,7 +439,6 @@ Once the index is built, you can ask questions like:
 </details>
 
 
-
 ## 🖥️ Command Line Interface
 
 LEANN includes a powerful CLI for document processing and search. Perfect for quick document indexing and interactive chat.
@@ -428,7 +451,7 @@ source .venv/bin/activate
 leann --help
 ```
 
-**To make it globally available (recommended for daily use):**
+**To make it globally available:**
 ```bash
 # Install the LEANN CLI globally using uv tool
 uv tool install leann
@@ -437,12 +460,17 @@ uv tool install leann
 leann --help
 ```
 
+> **Note**: Global installation is required for Claude Code integration. The `leann_mcp` server depends on the globally available `leann` command.
+
 
 
 ### Usage Examples
 
 ```bash
-# Build an index from documents
+# Build an index from current directory (default)
+leann build my-docs
+
+# Or from specific directory
 leann build my-docs --docs ./documents
 
 # Search your documents

packages/leann-backend-diskann/pyproject.toml

@@ -4,8 +4,8 @@ build-backend = "scikit_build_core.build"
 
 [project]
 name = "leann-backend-diskann"
-version = "0.2.1"
-dependencies = ["leann-core==0.2.1", "numpy", "protobuf>=3.19.0"]
+version = "0.2.4"
+dependencies = ["leann-core==0.2.4", "numpy", "protobuf>=3.19.0"]
 
 [tool.scikit-build]
 # Key: simplified CMake path

packages/leann-backend-hnsw/pyproject.toml

@@ -6,10 +6,10 @@ build-backend = "scikit_build_core.build"
 
 [project]
 name = "leann-backend-hnsw"
-version = "0.2.1"
+version = "0.2.4"
 description = "Custom-built HNSW (Faiss) backend for the Leann toolkit."
 dependencies = [
-    "leann-core==0.2.1",
+    "leann-core==0.2.4",
     "numpy",
     "pyzmq>=23.0.0",
     "msgpack>=1.0.0",

packages/leann-core/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "leann-core"
-version = "0.2.1"
+version = "0.2.4"
 description = "Core API and plugin system for LEANN"
 readme = "README.md"
 requires-python = ">=3.9"
@@ -44,6 +44,7 @@ colab = [
 
 [project.scripts]
 leann = "leann.cli:main"
+leann_mcp = "leann.mcp:main"
 
 [tool.setuptools.packages.find]
 where = ["src"]

packages/leann-core/src/leann/cli.py

@@ -41,13 +41,23 @@ def extract_pdf_text_with_pdfplumber(file_path: str) -> str:
 
 class LeannCLI:
     def __init__(self):
-        self.indexes_dir = Path.home() / ".leann" / "indexes"
+        # Always use project-local .leann directory (like .git)
+        self.indexes_dir = Path.cwd() / ".leann" / "indexes"
         self.indexes_dir.mkdir(parents=True, exist_ok=True)
 
+        # Default parser for documents
         self.node_parser = SentenceSplitter(
             chunk_size=256, chunk_overlap=128, separator=" ", paragraph_separator="\n\n"
         )
 
+        # Code-optimized parser
+        self.code_parser = SentenceSplitter(
+            chunk_size=512,  # Larger chunks for code context
+            chunk_overlap=50,  # Less overlap to preserve function boundaries
+            separator="\n",  # Split by lines for code
+            paragraph_separator="\n\n",  # Preserve logical code blocks
+        )
+
     def get_index_path(self, index_name: str) -> str:
         index_dir = self.indexes_dir / index_name
         return str(index_dir / "documents.leann")
@@ -64,10 +74,11 @@ class LeannCLI:
             formatter_class=argparse.RawDescriptionHelpFormatter,
             epilog="""
 Examples:
-  leann build my-docs --docs ./documents    # Build index named my-docs
-  leann search my-docs "query"             # Search in my-docs index
-  leann ask my-docs "question"             # Ask my-docs index
-  leann list                              # List all stored indexes
+  leann build my-docs --docs ./documents                    # Build index named my-docs
+  leann build my-ppts --docs ./ --file-types .pptx,.pdf    # Index only PowerPoint and PDF files
+  leann search my-docs "query"                             # Search in my-docs index
+  leann ask my-docs "question"                             # Ask my-docs index
+  leann list                                              # List all stored indexes
             """,
         )
 
@@ -76,7 +87,9 @@ Examples:
         # Build command
         build_parser = subparsers.add_parser("build", help="Build document index")
         build_parser.add_argument("index_name", help="Index name")
-        build_parser.add_argument("--docs", type=str, required=True, help="Documents directory")
+        build_parser.add_argument(
+            "--docs", type=str, default=".", help="Documents directory (default: current directory)"
+        )
         build_parser.add_argument(
             "--backend", type=str, default="hnsw", choices=["hnsw", "diskann"]
         )
@@ -87,6 +100,11 @@ Examples:
         build_parser.add_argument("--num-threads", type=int, default=1)
         build_parser.add_argument("--compact", action="store_true", default=True)
         build_parser.add_argument("--recompute", action="store_true", default=True)
+        build_parser.add_argument(
+            "--file-types",
+            type=str,
+            help="Comma-separated list of file extensions to include (e.g., '.txt,.pdf,.pptx'). If not specified, uses default supported types.",
+        )
 
         # Search command
         search_parser = subparsers.add_parser("search", help="Search documents")
@@ -96,7 +114,12 @@ Examples:
         search_parser.add_argument("--complexity", type=int, default=64)
         search_parser.add_argument("--beam-width", type=int, default=1)
         search_parser.add_argument("--prune-ratio", type=float, default=0.0)
-        search_parser.add_argument("--recompute-embeddings", action="store_true")
+        search_parser.add_argument(
+            "--recompute-embeddings",
+            action="store_true",
+            default=True,
+            help="Recompute embeddings (default: True)",
+        )
         search_parser.add_argument(
             "--pruning-strategy",
             choices=["global", "local", "proportional"],
@@ -119,7 +142,12 @@ Examples:
         ask_parser.add_argument("--complexity", type=int, default=32)
         ask_parser.add_argument("--beam-width", type=int, default=1)
         ask_parser.add_argument("--prune-ratio", type=float, default=0.0)
-        ask_parser.add_argument("--recompute-embeddings", action="store_true")
+        ask_parser.add_argument(
+            "--recompute-embeddings",
+            action="store_true",
+            default=True,
+            help="Recompute embeddings (default: True)",
+        )
         ask_parser.add_argument(
             "--pruning-strategy",
             choices=["global", "local", "proportional"],
@@ -138,40 +166,114 @@ Examples:
 
         return parser
 
+    def register_project_dir(self):
+        """Register current project directory in global registry"""
+        global_registry = Path.home() / ".leann" / "projects.json"
+        global_registry.parent.mkdir(exist_ok=True)
+
+        current_dir = str(Path.cwd())
+
+        # Load existing registry
+        projects = []
+        if global_registry.exists():
+            try:
+                import json
+
+                with open(global_registry) as f:
+                    projects = json.load(f)
+            except Exception:
+                projects = []
+
+        # Add current directory if not already present
+        if current_dir not in projects:
+            projects.append(current_dir)
+
+        # Save registry
+        import json
+
+        with open(global_registry, "w") as f:
+            json.dump(projects, f, indent=2)
+
     def list_indexes(self):
         print("Stored LEANN indexes:")
 
-        if not self.indexes_dir.exists():
+        # Get all project directories with .leann
+        global_registry = Path.home() / ".leann" / "projects.json"
+        all_projects = []
+
+        if global_registry.exists():
+            try:
+                import json
+
+                with open(global_registry) as f:
+                    all_projects = json.load(f)
+            except Exception:
+                pass
+
+        # Filter to only existing directories with .leann
+        valid_projects = []
+        for project_dir in all_projects:
+            project_path = Path(project_dir)
+            if project_path.exists() and (project_path / ".leann" / "indexes").exists():
+                valid_projects.append(project_path)
+
+        # Add current project if it has .leann but not in registry
+        current_path = Path.cwd()
+        if (current_path / ".leann" / "indexes").exists() and current_path not in valid_projects:
+            valid_projects.append(current_path)
+
+        if not valid_projects:
             print("No indexes found. Use 'leann build <name> --docs <dir>' to create one.")
             return
 
-        index_dirs = [d for d in self.indexes_dir.iterdir() if d.is_dir()]
+        total_indexes = 0
+        current_dir = Path.cwd()
 
-        if not index_dirs:
-            print("No indexes found. Use 'leann build <name> --docs <dir>' to create one.")
-            return
+        for project_path in valid_projects:
+            indexes_dir = project_path / ".leann" / "indexes"
+            if not indexes_dir.exists():
+                continue
 
-        print(f"Found {len(index_dirs)} indexes:")
-        for i, index_dir in enumerate(index_dirs, 1):
-            index_name = index_dir.name
-            status = "✓" if self.index_exists(index_name) else "✗"
+            index_dirs = [d for d in indexes_dir.iterdir() if d.is_dir()]
+            if not index_dirs:
+                continue
 
-            print(f"  {i}. {index_name} [{status}]")
-            if self.index_exists(index_name):
-                index_dir / "documents.leann.meta.json"
-                size_mb = sum(f.stat().st_size for f in index_dir.iterdir() if f.is_file()) / (
-                    1024 * 1024
-                )
-                print(f"     Size: {size_mb:.1f} MB")
+            # Show project header
+            if project_path == current_dir:
+                print(f"\n📁 Current project ({project_path}):")
+            else:
+                print(f"\n📂 {project_path}:")
 
-        if index_dirs:
-            example_name = index_dirs[0].name
-            print("\nUsage:")
-            print(f'  leann search {example_name} "your query"')
-            print(f"  leann ask {example_name} --interactive")
+            for index_dir in index_dirs:
+                total_indexes += 1
+                index_name = index_dir.name
+                meta_file = index_dir / "documents.leann.meta.json"
+                status = "✓" if meta_file.exists() else "✗"
 
-    def load_documents(self, docs_dir: str):
+                print(f"  {total_indexes}. {index_name} [{status}]")
+                if status == "✓":
+                    size_mb = sum(f.stat().st_size for f in index_dir.iterdir() if f.is_file()) / (
+                        1024 * 1024
+                    )
+                    print(f"     Size: {size_mb:.1f} MB")
+
+        if total_indexes > 0:
+            print(f"\nTotal: {total_indexes} indexes across {len(valid_projects)} projects")
+            print("\nUsage (current project only):")
+
+            # Show example from current project
+            current_indexes_dir = current_dir / ".leann" / "indexes"
+            if current_indexes_dir.exists():
+                current_index_dirs = [d for d in current_indexes_dir.iterdir() if d.is_dir()]
+                if current_index_dirs:
+                    example_name = current_index_dirs[0].name
+                    print(f'  leann search {example_name} "your query"')
+                    print(f"  leann ask {example_name} --interactive")
+
+    def load_documents(self, docs_dir: str, custom_file_types: str | None = None):
         print(f"Loading documents from {docs_dir}...")
+        if custom_file_types:
+            print(f"Using custom file types: {custom_file_types}")
 
         # Try to use better PDF parsers first
         documents = []
@@ -203,17 +305,140 @@ Examples:
                 documents.extend(default_docs)
 
         # Load other file types with default reader
-        other_docs = SimpleDirectoryReader(
-            docs_dir,
-            recursive=True,
-            encoding="utf-8",
-            required_exts=[".txt", ".md", ".docx"],
-        ).load_data(show_progress=True)
-        documents.extend(other_docs)
+        if custom_file_types:
+            # Parse custom file types from comma-separated string
+            code_extensions = [ext.strip() for ext in custom_file_types.split(",") if ext.strip()]
+            # Ensure extensions start with a dot
+            code_extensions = [ext if ext.startswith(".") else f".{ext}" for ext in code_extensions]
+        else:
+            # Use default supported file types
+            code_extensions = [
+                # Original document types
+                ".txt",
+                ".md",
+                ".docx",
+                ".pptx",
+                # Code files for Claude Code integration
+                ".py",
+                ".js",
+                ".ts",
+                ".jsx",
+                ".tsx",
+                ".java",
+                ".cpp",
+                ".c",
+                ".h",
+                ".hpp",
+                ".cs",
+                ".go",
+                ".rs",
+                ".rb",
+                ".php",
+                ".swift",
+                ".kt",
+                ".scala",
+                ".r",
+                ".sql",
+                ".sh",
+                ".bash",
+                ".zsh",
+                ".fish",
+                ".ps1",
+                ".bat",
+                # Config and markup files
+                ".json",
+                ".yaml",
+                ".yml",
+                ".xml",
+                ".toml",
+                ".ini",
+                ".cfg",
+                ".conf",
+                ".html",
+                ".css",
+                ".scss",
+                ".less",
+                ".vue",
+                ".svelte",
+                # Data science
+                ".ipynb",
+                ".R",
+                ".py",
+                ".jl",
+            ]
+        # Try to load other file types, but don't fail if none are found
+        try:
+            other_docs = SimpleDirectoryReader(
+                docs_dir,
+                recursive=True,
+                encoding="utf-8",
+                required_exts=code_extensions,
+            ).load_data(show_progress=True)
+            documents.extend(other_docs)
+        except ValueError as e:
+            if "No files found" in str(e):
+                print("No additional files found for other supported types.")
+            else:
+                raise e
 
         all_texts = []
+
+        # Define code file extensions for intelligent chunking
+        code_file_exts = {
+            ".py",
+            ".js",
+            ".ts",
+            ".jsx",
+            ".tsx",
+            ".java",
+            ".cpp",
+            ".c",
+            ".h",
+            ".hpp",
+            ".cs",
+            ".go",
+            ".rs",
+            ".rb",
+            ".php",
+            ".swift",
+            ".kt",
+            ".scala",
+            ".r",
+            ".sql",
+            ".sh",
+            ".bash",
+            ".zsh",
+            ".fish",
+            ".ps1",
+            ".bat",
+            ".json",
+            ".yaml",
+            ".yml",
+            ".xml",
+            ".toml",
+            ".ini",
+            ".cfg",
+            ".conf",
+            ".html",
+            ".css",
+            ".scss",
+            ".less",
+            ".vue",
+            ".svelte",
+            ".ipynb",
+            ".R",
+            ".jl",
+        }
+
         for doc in documents:
-            nodes = self.node_parser.get_nodes_from_documents([doc])
+            # Check if this is a code file based on source path
+            source_path = doc.metadata.get("source", "")
+            is_code_file = any(source_path.endswith(ext) for ext in code_file_exts)
+
+            # Use appropriate parser based on file type
+            parser = self.code_parser if is_code_file else self.node_parser
+            nodes = parser.get_nodes_from_documents([doc])
+
             for node in nodes:
                 all_texts.append(node.get_content())
 
@@ -226,11 +451,13 @@ Examples:
         index_dir = self.indexes_dir / index_name
         index_path = self.get_index_path(index_name)
 
+        print(f"📂 Indexing: {Path(docs_dir).resolve()}")
+
         if index_dir.exists() and not args.force:
             print(f"Index '{index_name}' already exists. Use --force to rebuild.")
             return
 
-        all_texts = self.load_documents(docs_dir)
+        all_texts = self.load_documents(docs_dir, args.file_types)
         if not all_texts:
             print("No documents found")
             return
@@ -255,6 +482,9 @@ Examples:
         builder.build_index(index_path)
         print(f"Index built at {index_path}")
 
+        # Register this project directory in global registry
+        self.register_project_dir()
+
     async def search_documents(self, args):
         index_name = args.index_name
         query = args.query

packages/leann-core/src/leann/mcp.py

@@ -0,0 +1,125 @@
+#!/usr/bin/env python3
+
+import json
+import subprocess
+import sys
+
+
+def handle_request(request):
+    if request.get("method") == "initialize":
+        return {
+            "jsonrpc": "2.0",
+            "id": request.get("id"),
+            "result": {
+                "capabilities": {"tools": {}},
+                "protocolVersion": "2024-11-05",
+                "serverInfo": {"name": "leann-mcp", "version": "1.0.0"},
+            },
+        }
+
+    elif request.get("method") == "tools/list":
+        return {
+            "jsonrpc": "2.0",
+            "id": request.get("id"),
+            "result": {
+                "tools": [
+                    {
+                        "name": "leann_search",
+                        "description": "Search LEANN index",
+                        "inputSchema": {
+                            "type": "object",
+                            "properties": {
+                                "index_name": {"type": "string"},
+                                "query": {"type": "string"},
+                                "top_k": {"type": "integer", "default": 5},
+                            },
+                            "required": ["index_name", "query"],
+                        },
+                    },
+                    {
+                        "name": "leann_ask",
+                        "description": "Ask question using LEANN RAG",
+                        "inputSchema": {
+                            "type": "object",
+                            "properties": {
+                                "index_name": {"type": "string"},
+                                "question": {"type": "string"},
+                            },
+                            "required": ["index_name", "question"],
+                        },
+                    },
+                    {
+                        "name": "leann_list",
+                        "description": "List all LEANN indexes",
+                        "inputSchema": {"type": "object", "properties": {}},
+                    },
+                ]
+            },
+        }
+
+    elif request.get("method") == "tools/call":
+        tool_name = request["params"]["name"]
+        args = request["params"].get("arguments", {})
+
+        try:
+            if tool_name == "leann_search":
+                cmd = [
+                    "leann",
+                    "search",
+                    args["index_name"],
+                    args["query"],
+                    "--recompute-embeddings",
+                    f"--top-k={args.get('top_k', 5)}",
+                ]
+                result = subprocess.run(cmd, capture_output=True, text=True)
+
+            elif tool_name == "leann_ask":
+                cmd = f'echo "{args["question"]}" | leann ask {args["index_name"]} --recompute-embeddings --llm ollama --model qwen3:8b'
+                result = subprocess.run(cmd, shell=True, capture_output=True, text=True)
+
+            elif tool_name == "leann_list":
+                result = subprocess.run(["leann", "list"], capture_output=True, text=True)
+
+            return {
+                "jsonrpc": "2.0",
+                "id": request.get("id"),
+                "result": {
+                    "content": [
+                        {
+                            "type": "text",
+                            "text": result.stdout
+                            if result.returncode == 0
+                            else f"Error: {result.stderr}",
+                        }
+                    ]
+                },
+            }
+
+        except Exception as e:
+            return {
+                "jsonrpc": "2.0",
+                "id": request.get("id"),
+                "error": {"code": -1, "message": str(e)},
+            }
+
+
+def main():
+    for line in sys.stdin:
+        try:
+            request = json.loads(line.strip())
+            response = handle_request(request)
+            if response:
+                print(json.dumps(response))
+                sys.stdout.flush()
+        except Exception as e:
+            error_response = {
+                "jsonrpc": "2.0",
+                "id": None,
+                "error": {"code": -1, "message": str(e)},
+            }
+            print(json.dumps(error_response))
+            sys.stdout.flush()
+
+
+if __name__ == "__main__":
+    main()

packages/leann-mcp/README.md

@@ -0,0 +1,69 @@
+# LEANN Claude Code Integration
+
+Intelligent code assistance using LEANN's vector search directly in Claude Code.
+
+## Prerequisites
+
+First, install LEANN CLI globally:
+
+```bash
+uv tool install leann-core
+```
+
+This makes the `leann` command available system-wide, which `leann_mcp` requires.
+
+## Quick Setup
+
+Add the LEANN MCP server to Claude Code:
+
+```bash
+claude mcp add leann-server -- leann_mcp
+```
+
+## Available Tools
+
+- **`leann_list`** - List available indexes across all projects
+- **`leann_search`** - Search code and documents with semantic queries
+- **`leann_ask`** - Ask questions and get AI-powered answers from your codebase
+
+## Quick Start
+
+```bash
+# Build an index for your project
+leann build my-project
+
+# Start Claude Code
+claude
+```
+
+Then in Claude Code:
+```
+Help me understand this codebase. List available indexes and search for authentication patterns.
+```
+
+<p align="center">
+  <img src="../../assets/claude_code_leann.png" alt="LEANN in Claude Code" width="80%">
+</p>
+
+
+## How It Works
+
+- **`leann`** - Core CLI tool for indexing and searching (installed globally)
+- **`leann_mcp`** - MCP server that wraps `leann` commands for Claude Code integration
+- Claude Code calls `leann_mcp`, which executes `leann` commands and returns results
+
+## File Support
+
+Python, JavaScript, TypeScript, Java, Go, Rust, SQL, YAML, JSON, and 30+ more file types.
+
+## Storage
+
+- Project indexes in `.leann/` directory (like `.git`)
+- Global project registry at `~/.leann/projects.json`
+- Multi-project support built-in
+
+## Removing
+
+```bash
+claude mcp remove leann-server
+```

packages/leann/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "leann"
-version = "0.2.1"
+version = "0.2.4"
 description = "LEANN - The smallest vector index in the world. RAG Everything with LEANN!"
 readme = "README.md"
 requires-python = ">=3.9"