# velocirag

A local RAG server that lets agents search indexed documents through MCP. It combines semantic, keyword, graph, and metadata retrieval.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 12
- Author: HaseebKhalid1507
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/HaseebKhalid1507/VelociRAG
- Updated: 2026-04-05
- HTML: https://affpapa.org/en/nevibecode/mcp/velocirag

## What it does

velocirag builds a document index and combines four retrieval paths: vector similarity, BM25 keyword search, knowledge-graph traversal, and metadata filters. Rank fusion and a cross-encoder then reorder the results. Its MCP interface gives an agent tools for search, indexing, single-document insertion, diagnostics, and source listing.

The stack uses ONNX Runtime, FAISS, SQLite FTS5, and local MiniLM and TinyBERT models. Files can be indexed incrementally, while provenance tracking updates affected graph links. A Unix-socket daemon keeps the search engine warm between CLI requests. It runs on CPU and requires 8GB RAM; GPU hardware and API keys are not needed.

## Requirements
- Needs: Python and uv (commands run via uvx)

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add velocirag -- uvx velocirag
```
uvx runs the command named after the package; if the README names another one, use uvx --from velocirag <command>

### Codex

**Platform CLI**
```bash
codex mcp add velocirag -- uvx velocirag
```
uvx runs the command named after the package; if the README names another one, use uvx --from velocirag <command>

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "velocirag": {
            "command": "uvx",
            "args": [
                "velocirag"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from velocirag <command>

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "velocirag": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "velocirag"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from velocirag <command>

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add velocirag uvx velocirag
```
uvx runs the command named after the package; if the README names another one, use uvx --from velocirag <command>

## When to use it
- index a directory of documents
- find exact terms and related concepts
- filter results by tags and status
- add one document to the knowledge base
- check MCP server health

## Example prompts
- Index `./docs` and find material about schema migrations.
- Add `README.md` to the knowledge base, then check the server health.
- Search for documents tagged `python` with status `active` that relate to error handling.

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 392262
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33989
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81163
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119231
- [Codebase Memory](https://affpapa.org/en/nevibecode/mcp/codebase-memory.md) — MCP server · ★ 47577
- [mcp-server](https://affpapa.org/en/nevibecode/mcp/mcp-server.md) — MCP server · ★ 43902

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md