LibreAI / Agents / xerj
// agents · xerj-org/xerj

xerj

xerj is an open-source agents project by xerj-org (xerj-org/xerj on GitHub). It has 2,628 GitHub stars and 231 forks, is released under the Apache-2.0 license, and was last updated on GitHub on 4 October 2026.

AI-native search that indexes code, docs, and PDFs with 40x fewer tokens than grep.

💎 Hidden gem★ 2.6k stars⑂ 231 forksApache-2.0updated 2026-10
▦ visual — this project's README ships no embeddable screenshot,
so here's a placeholder. The guide below is complete regardless.
// project facts

Project facts

Repository
xerj-org/xerj
GitHub stars
2,628
Forks
231
License
Apache-2.0
Last updated on GitHub
4 October 2026
Category
Agents
Listing
Hidden gem — a shorter page for a lesser-known project
Official site
Official site
// how it works

How it works

  1. Install XERJ

    Get the Rust binary.

  2. Index your data

    One command covers code, docs, logs, and PDFs.

  3. Query from agents

    Agents search instead of grepping.

  4. Use existing clients

    Elasticsearch-compatible APIs just work.

// features

Why people love it

Auto-indexing

One command indexes everything.

40x fewer tokens

Far cheaper than grep-and-read loops.

Multi-format

Code, docs, logs, and PDFs.

Elasticsearch compatible

Existing clients keep working.

Agent memory

Feeds long-term agent recall.

Security audits

Search codebases for issues fast.

Advertisement
// run it

Run it yourself

  1. Step 1 — Clone the repo

    Download the source and move into the project folder.

    git clone https://github.com/xerj-org/xerj.git
    cd xerj
  2. Step 2 — Check the README

    Every project documents its own setup; start with install requirements.

    cat README.md | head -60
  3. Step 3 — Run it

    Follow the project’s launch command — Docker, pip, npm, or a binary release.

    # see README for the exact launch command
// use cases

What you can build

  • Index a codebase for agent search.
  • Cut token costs on RAG pipelines.
  • Audit code for security patterns.
  • Give agents instant project knowledge.
Advertisement
// faq

Questions, answered

Who maintains XERJ?

It is an open-source project at xerj-org/xerj with 231 forks.

Is XERJ free for commercial use?

Yes. Apache-2.0 licensed.

How is it different from Elasticsearch?

Lighter and agent-focused, with token-efficient indexing.

What is the 40x claim based on?

The project’s comparison against grep-based agent search; benchmark it yourself.

Do I need to change my clients?

No. Elasticsearch-compatible APIs keep working.

// keep exploring

Similar tools

AI Agents

mcp-use

The fullstack MCP framework to develop MCP Apps for ChatGPT / Claude & MCP Servers for AI Agents.

★ 10.7k starsMIT
View guide →
AI Agents

TencentDB-Agent-Memory

TencentDB Agent Memory is a team-level memory hub for AI Agents — turning conversations, docs, and code into four reusable memory assets (Chat Memory, Skill,…

★ 27.7k starsUnknown
View guide →
AI Agents

mempalace

The best-benchmarked open-source AI memory system. And it's free.

★ 59.4k starsMIT
View guide →
AI Agents

milvus

The cloud-native vector database for planet-scale similarity search.

★ 46.3k starsApache-2.0
View guide →
Agents

zeron

Native control plane for Claude Code, Codex, Cursor, Devin, and other coding agents.

★ 3.0k starsMIT
View guide →
AI Agents

codebase-memory-mcp

High-performance code intelligence MCP server: your codebase as a persistent knowledge graph

★ 46.1k starsMIT
View guide →
// alternatives

Alternatives in Agents

The most-starred other Agents projects in the LibreAI catalogue — the realistic shortlist if xerj is not the right fit.

  • openclaw★ 391.6k

    A personal AI that really does things — on any OS, with your data staying yours.

  • superpowers★ 294.9k

    An agentic skills framework & software development methodology that works.

  • ECC★ 275.2k

    Agent harness optimization system with skills, memory and security for Claude Code, Codex and more

  • hermes-agent★ 252.0k

    The agent that grows with you — a Python framework for adaptive AI agents.

  • deepseek-harness★ 245.5k

    DeepSeek's plugin-based agent harness where everything is a plugin.

// more in agents

More in Agents

Nearby Agents projects in the catalogue, closest in stars to xerj — keep exploring the shelf either side of it.

  • Memoh★ 2.6k

    Multi-agent platform where every agent gets its own computer and long-term memory.

  • Data-Analysis-Agent★ 2.6k

    Chat with your data: an LLM agent that builds charts and business insights.

  • agent-memory★ 2.6k

    Long-term memory runtime for AI agents — plain Markdown as truth, local ranked retrieval, no API key

  • agentfield★ 2.6k

    Build, run, and scale AI agents like APIs and microservices.

  • Memary★ 2.7k

    The open-source memory layer for autonomous agents — knowledge-graph memory that emulates human memory

  • agentic-context-engine★ 2.6k

    Make your agents learn from experience with a dedicated context engine.

Get xerj

Free and open — grab the source, star the repo, and start creating.