# Coderag

> Lightning-fast semantic code search with AST chunking (15+ languages) - Hybrid TF-IDF + Vector, MCP-ready for AI assistants

- **Type:** MCP server
- **Install:** `agentstack add mcp-sylphxai-coderag`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [SylphxAI](https://agentstack.voostack.com/s/sylphxai)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [SylphxAI](https://github.com/SylphxAI)
- **Source:** https://github.com/SylphxAI/coderag
- **Website:** https://sylphx.com

## Install

```sh
agentstack add mcp-sylphxai-coderag
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# CodeRAG

**Lightning-fast hybrid code search for AI assistants**

[](https://www.npmjs.com/package/@sylphx/coderag)
[](https://www.npmjs.com/package/@sylphx/coderag-mcp)
[](https://github.com/SylphxAI/coderag/actions)
[](LICENSE)

**Zero dependencies** • **

---

## Why CodeRAG?

Traditional code search tools are either **slow** (full-text grep), **inaccurate** (keyword matching), or **complex** (require external services).

CodeRAG is different:

```
❌ Old way: Docker + ChromaDB + Ollama + 30 second startup
✅ CodeRAG: npx @sylphx/coderag-mcp (instant)
```

| Feature | grep/ripgrep | Cloud RAG | CodeRAG |
|---------|-------------|-----------|---------|
| **Semantic understanding** | ❌ | ✅ | ✅ |
| **Zero external deps** | ✅ | ❌ | ✅ |
| **Offline support** | ✅ | ❌ | ✅ |
| **Startup time** | Instant | 10-30s |  {
```

## src/utils/large.ts:1-200 [truncated]
```typescript
1: // First 70% shown...

... [800 chars truncated] ...

195: // Last 20% shown
```
```

---

## 📚 API Reference

### `CodebaseIndexer`

Main class for indexing and searching.

```typescript
import { CodebaseIndexer, PersistentStorage } from '@sylphx/coderag'

const storage = new PersistentStorage({ codebaseRoot: './project' })
const indexer = new CodebaseIndexer({
  codebaseRoot: './project',
  storage,
  maxFileSize: 1024 * 1024, // 1MB default
})

// Index with file watching
await indexer.index({ watch: true })

// Search with options
const results = await indexer.search('query', {
  limit: 10,
  includeContent: true,
  fileExtensions: ['.ts', '.js'],
  excludePaths: ['node_modules'],
})

// Stop watching
await indexer.stopWatch()
```

### `PersistentStorage`

SQLite-backed storage for instant startup.

```typescript
import { PersistentStorage } from '@sylphx/coderag'

const storage = new PersistentStorage({
  codebaseRoot: './project',  // Creates .coderag/ folder
  dbPath: './custom.db',      // Optional custom path
})
```

### Low-Level TF-IDF Functions

```typescript
import { buildSearchIndex, searchDocuments, initializeTokenizer } from '@sylphx/coderag'

// Initialize StarCoder2 tokenizer (4.7MB, one-time download)
await initializeTokenizer()

// Build index
const documents = [
  { uri: 'file://auth.ts', content: 'export function authenticate...' },
  { uri: 'file://user.ts', content: 'export class User...' },
]
const index = await buildSearchIndex(documents)

// Search
const results = await searchDocuments('authenticate user', index, { limit: 5 })
```

### Vector Search (Optional)

For semantic search with embeddings:

```typescript
import { hybridSearch, createEmbeddingProvider } from '@sylphx/coderag'

// Requires OPENAI_API_KEY environment variable
const results = await hybridSearch('authentication flow', indexer, {
  vectorWeight: 0.7,  // 70% vector, 30% TF-IDF
  limit: 10,
})
```

---

## ⚙️ Configuration

### MCP Server Options

| Option | Default | Description |
|--------|---------|-------------|
| `--root=` | Current directory | Codebase root path |
| `--max-size=` | 1048576 (1MB) | Max file size to index |
| `--no-auto-index` | false | Disable auto-indexing on startup |

### Environment Variables

| Variable | Description |
|----------|-------------|
| `OPENAI_API_KEY` | Enable vector search with OpenAI embeddings |
| `OPENAI_BASE_URL` | Custom OpenAI-compatible endpoint |
| `EMBEDDING_MODEL` | Embedding model (default: `text-embedding-3-small`) |
| `EMBEDDING_DIMENSIONS` | Custom embedding dimensions |

---

## 📊 Performance

| Metric | Value |
|--------|-------|
| **Initial indexing** | ~1000-2000 files/sec |
| **Startup with cache** | `/`` tags in HTML.

---

## 🔧 Development

```bash
# Clone
git clone https://github.com/SylphxAI/coderag.git
cd coderag

# Install
bun install

# Build
bun run build

# Test
bun run test

# Lint & Format
bun run lint
bun run format
```

---

## 🤝 Contributing

Contributions are welcome! Please:

1. Open an issue to discuss changes
2. Fork and create a feature branch
3. Run `bun run lint` and `bun run test`
4. Submit a pull request

---

## 📄 License

MIT © [Sylphx](https://sylphx.com)

---

**Powered by [Sylphx](https://github.com/SylphxAI)**

Built with [@sylphx/synth](https://github.com/SylphxAI/synth) • [@sylphx/mcp-server-sdk](https://github.com/SylphxAI/mcp-server-sdk) • [@sylphx/bump](https://github.com/SylphxAI/bump)

## Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [SylphxAI](https://github.com/SylphxAI)
- **Source:** [SylphxAI/coderag](https://github.com/SylphxAI/coderag)
- **License:** MIT
- **Homepage:** https://sylphx.com

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/mcp-sylphxai-coderag
- Seller: https://agentstack.voostack.com/s/sylphxai
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.