Coderag

Created By
packages6 months ago
Overview

what is CodeRAG?

CodeRAG is a lightning-fast hybrid code search tool designed for AI assistants, enabling efficient code searching and indexing without external dependencies.

how to use CodeRAG?

To use CodeRAG, you can either run it as an MCP server using the command npx @sylphx/coderag-mcp --root=/path/to/project or install it as a library with npm install @sylphx/coderag and integrate it into your project.

key features of CodeRAG?

  • Hybrid search combining TF-IDF and vector embeddings for accurate results.
  • Fast indexing of 1000-2000 files per second with SQLite persistence for instant startup.
  • Real-time index updates with file watching and incremental updates.

use cases of CodeRAG?

  1. Assisting AI tools in searching codebases efficiently.
  2. Providing instant search results for large codebases in development environments.
  3. Enhancing code navigation and understanding for developers.

FAQ from CodeRAG?

  • Does CodeRAG require external services?

No, CodeRAG operates with zero external dependencies.

  • How fast is the search functionality?

CodeRAG offers search latency of less than 50ms, even on large codebases.

  • Can I use CodeRAG offline?

Yes, CodeRAG supports offline usage.

Server Config

{
  "mcpServers": {
    "coderag": {
      "command": "npx",
      "args": [
        "-y",
        "@sylphx/coderag-mcp",
        "--root=/path/to/project"
      ]
    }
  }
}
Project Info
Created At
6 months ago
Updated At
6 months ago
Author Name
packages
Star
-
Language
-
License
-

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

20 hours ago
Gpt Scrambler

2 days ago