Codebase Memory MCP：24K+ 星 — AI 代码智能持久记忆服务器

# 克隆仓库
git clone https://github.com/DeusData/codebase-memory-mcp.git
cd codebase-memory-mcp

# 构建运行
docker build -t codebase-memory .
docker run -d \
  --name codebase-memory \
  -p 8080:8080 \
  -v $(pwd)/data:/app/data \
  -e INDEX_PATH=/app/data/my-project \
  codebase-memory

from codebase_memory import Indexer

# 初始化索引器
indexer = Indexer(
    codebase_path="./my-project",
    embedding_model="sentence-transformers/all-MiniLM-L6-v2",
    storage_backend="chroma"
)

# 索引整个代码库
results = indexer.index()
print(f"索引了 {results['files']} 个文件，{results['tokens']} tokens")
# 输出: 索引了 342 个文件，1,247,832 tokens

# 获取查询的语义相似度
query = "认证流程如何工作？"
similar = indexer.search(query, top_k=5)
for doc in similar:
    print(f"[{doc['score']:.2f}] {doc['path']}: {doc['snippet'][:100]}")

{
  "mcpServers": {
    "codebase-memory": {
      "command": "npx",
      "args": [
        "-y",
        "@deusdata/codebase-memory-mcp"
      ],
      "env": {
        "INDEX_PATH": "/path/to/your/codebase",
        "VECTOR_STORE": "chroma",
        "EMBEDDING_MODEL": "all-MiniLM-L6-v2"
      }
    }
  }
}

{
  "mcpServers": {
    "codebase-memory": {
      "command": "python",
      "args": ["-m", "codebase_memory.server"],
      "env": {
        "INDEX_PATH": "~/projects/my-app",
        "PERSIST": "true"
      }
    }
  }
}

// Rust 增量索引器
pub struct IncrementalIndexer {
    file_hashes: HashMap<PathBuf, String>,
    vector_store: ChromaStore,
}

impl IncrementalIndexer {
    pub fn index_changed(&mut self, codebase_path: &Path) -> IndexResult {
        let mut changed_files = Vec::new();
        let mut deleted_files = Vec::new();
        
        for entry in walk_dir(codebase_path)? {
            let current_hash = compute_hash(&entry.path)?;
            
            match self.file_hashes.get(&entry.path) {
                Some(stored_hash) if stored_hash != &current_hash => {
                    changed_files.push(entry.path);
                }
                None => {
                    changed_files.push(entry.path);
                }
                _ => {} // 未变更
            }
        }
        
        // 仅重新索引变更文件
        for path in &changed_files {
            self.vector_store.update(path)?;
        }
        
        Ok(IndexResult {
            indexed: changed_files.len(),
            skipped: 0,
            duration_ms: elapsed.as_millis() as u64,
        })
    }
}

from codebase_memory.parsers import BaseParser, register_parser

@register_parser("mylang")
class MyLangParser(BaseParser):
    def parse(self, file_path):
        with open(file_path) as f:
            content = f.read()
        segments = []
        for match in re.finditer(r"(def|class|module)\s+(\w+)", content):
            segments.append({
                "type": match.group(1),
                "name": match.group(2),
                "content": content[match.start():match.end()+200],
                "line": content[:match.start()].count("\n") + 1,
            })
        return segments

indexer = Indexer(
    codebase_path="./project",
    exclude_patterns=[
        "**/node_modules/**",
        "**/__pycache__/**",
        "**/*.lock",
        "**/test/fixtures/**",
    ],
    include_patterns=[
        "**/*.py",
        "**/*.ts",
        "**/*.go",
        "**/src/**",
    ]
)

from sentence_transformers import SentenceTransformer

code_model = SentenceTransformer("Salesforce/codet5p-220m-paraphrase")

indexer = Indexer(
    codebase_path="./project",
    embedding_model=code_model,
    embedding_dimension=220,
)

repositories = [
    "/home/user/project-alpha",
    "/home/user/project-beta",
    "/home/user/shared-libraries",
]

multi_indexer = MultiRepoIndexer(
    repositories=repositories,
    shared_embeddings=True,
    cross_reference_resolution=True,
)

results = multi_indexer.search("认证流程")

mcp call codebase-memory security-audit --path ./src/api
mcp call codebase-memory api-review --diff ./pr-123.diff
mcp call codebase-memory changelog --since v2.0.0

docs = indexer.generate_documentation(
    format="markdown",
    include_examples=True,
    include_diagrams=True,
    output_dir="./docs"
)