xerj

Local-first AI agent search engine and MCP server.

MCPDevOpen source

Type: MCP
Transport: http
Open source: Yes
GitHub Stars: ★ 12.4k
Source: mcp-github
Repository: github.com/xerj-org/xerj

Overview

XERJ is a local-first AI agent search engine and MCP server that indexes code, documentation, logs, JSONL/CSV, and PDF files via a Rust binary. It supports BM25 full-text search, vector search, and hybrid search. It provides an Elasticsearch-compatible API and can be used as an agent memory. Ideal for scenarios requiring efficient code search and reference coding, reducing token consumption and improving coding efficiency.

Capabilities

▪BM25 full-text search
▪Vector search
▪Hybrid search
▪Code search
▪Agent memory
▪Elasticsearch-compatible API

Use cases

Code searchReference codingAgent memoryDocument indexing

Setup

Requires: API KeyNode环境

curl -fsSL https://xerj.org/get | sh; xerj --insecure --data-dir ./data &; xerj init

This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.

FAQ

How do I install XERJ?

Download and run the installation script using curl.

What file types does XERJ support?

Supports code, documentation, logs, JSONL/CSV, and PDF files.

Is XERJ open source?

Yes, XERJ is an open-source project.

Related skills

coop-anything

An MCP server that converts single-player games into cooperative multiplayer experiences.

MCP

sast-skills

Transform your AI coding assistant into a SAST scanner to automatically detect vulnerabilities in code.

Agent Skill

Lightswind-UI-Library

AI-native CLI-first React component library with MCP Server support.

MCP

scientific-agent-skills

Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.

Agent Skill

susi_alexa_skill

A skill that enables question-and-answer interactions between Alexa and Susi AI.

Agent Skill

claude-context

Provides code search capabilities for Claude Code, turning the entire codebase into context.

MCP