XERJ: Rust-based search engine for AI agents and RAG

Repositoryxerj-org/xerjTool

XERJ is a Rust-based search engine designed as an alternative to Elasticsearch and grep for AI workflows. It provides zero-config auto-indexing for code, documentation, logs, and PDFs, aiming to significantly cut token usage for AI agents handling search, RAG, and memory tasks.

Key points

  1. Built in Rust as a single static binary without JVM dependencies.
  2. Supports BM25, kNN, and hybrid search with an offline lexical embedder and an opt-in neural model.
  3. Provides native support for Model Context Protocol (MCP), llms.txt, and dedicated agent memory endpoints.
  4. Reports 1366 out of 1369 passing tests on the Elasticsearch YAML conformance test suite.
  5. Promises up to 40x lower token consumption compared to standard grep workflows, alongside reduced infrastructure costs.

Why it matters

AI agents require fast, token-efficient access to codebase and document context. Traditional search engines like Elasticsearch often carry significant infrastructure overhead. A lightweight binary offering Elasticsearch compatibility and native MCP connectivity streamlines both local tooling and production agent architectures.

Analysis

The project tackles the token inefficiency of raw grep searches alongside the operational weight of traditional JVM search clusters. With roughly 7,900 stars on GitHub, an Apache 2.0 license, and near-complete ES-YAML test suite coverage, XERJ presents a mature, practical option for teams building agentic workflows and local RAG systems.

Mentioned links

Found in

Summary generated by AI (Gemini 3.8 Flash, 18 October 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • Repository:alexeyban/EKOS

    EKOS: Enterprise Knowledge Compiler for AI Agents

    EKOS (Enterprise Knowledge Operating System) is an open-source Rust-based platform designed to observe, compile, and serve enterprise knowledge from disparate sources via the Model Context Protocol (MCP) for AI agents.

    10starsRust

    AI & LLMs· Tool

  • Repository:mixedbread-ai/toast-harness

    toast-harness: Framework and API Interface for Mixedbread's toast-1 Search Agent

    Mixedbread's toast-harness is a Python repository designed for the toast-1 search agent. It allows developers to query the model via an OpenAI-compatible Completions API and provides the open-source agent harness used for training and running retrieval loops with exact token accounting.

    33starsPython

    AI & LLMs· Tool

  • Repository:DeusData/codebase-memory-mcp

    codebase-memory-mcp: High-Performance Knowledge-Graph Code Intelligence via MCP

    codebase-memory-mcp is a pure C Model Context Protocol (MCP) server that indexes codebases into persistent knowledge graphs, providing AI coding agents with sub-millisecond structural search while dramatically reducing token consumption.

    42.3kstarsC

    AI & LLMs· Tool

  • Repository:xai-org/grok-build

    Grok Build: Terminal-Based AI Coding Agent by SpaceXAI

    Grok Build is a Rust-based AI coding agent featuring a full-screen, mouse-interactive TUI. It analyzes codebases, modifies files, runs shell commands, and supports interactive use, headless CI scripting, and editor embedding via the Agent Client Protocol.

    26.5kstarsRust

    AI & LLMs· Tool

  • Repository:openai/codex

    OpenAI Codex CLI: Local Terminal Coding Agent Built in Rust

    Codex CLI is an open-source, lightweight coding agent developed by OpenAI that runs locally in your terminal. Written in Rust, it connects directly to ChatGPT plans or standard API keys.

    121.7kstarsRust

    AI & LLMs· Tool

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.