RustXNG

What it does

Core capabilities at a glance

Agpl
AI Agents
Grounding
MCP
Metasearch
Privacy
RAG
Search Engine

Deep dive

The full breakdown - performance, comparisons, and setup

RustXNGLink to this section

RustXNG is an agent framework - Self-hosted, SSRF-hardened web search and grounding engine for local AI agents (AGPL-3.0-or-later).

OverviewLink to this section

A self-hosted, SSRF-hardened web search and grounding engine for local AI agents.

No API keys. No fees. One request returns ranked results and the page text, so an agent can answer from sources instead of guessing.

An agent searches, reads, and decides — then does it again. What it needs underneath is not another search UI but a retrieval layer:

Download the archive for your platform from Releases and put 'rustxng' on your 'PATH'.

This installs two binaries: 'rustxng' (the server) and 'rustxng-index' (the optional local index).

Published from v0.26.0 onwards. To build it yourself instead:

Bind your own settings with '-v "$PWD/settings.toml:/app/settings.toml:ro"'.

Requires Rust 1.85 or newer. No system libraries beyond a C toolchain.

Two caveats, stated plainly: the numbers move by a few points between runs, and Google is unavailable in this build (its WML endpoint now returns 403, the HTML endpoint requires JavaScript, and headless browsers are detected). See docs/COMPARISON-EXA.md for a plain-language version.

Issues and pull requests are welcome — see CONTRIBUTING.md. The rules are short: run 'cargo fmt', 'cargo clippy', 'cargo test', and keep the nightly benchmark green.

Good first issues live in the tracker; the parsers under 'src/engines/' are deliberately small and each has a fixture test.

RustXNG is open-source, written primarily in Rust, with 456 GitHub stars under the AGPL-3.0 license. The latest release is v0.26.0 (2026-11-01).

Key capabilitiesLink to this section

From the project's documentation:

226 engine types ported from SearXNG, 352 settings entries, 180 enabled by default

InstallLink to this section

A quick way to get started (always check the official docs for the latest):

docker run -p 8888:8888 ghcr.io/sahenjp/rustxng:latest

How it fits a local-AI stackLink to this section

RustXNG runs on your own hardware, so pair it with a model and a GPU sized to your needs. Use the VRAM calculator to pick a model that fits your card, and see what you can run for hardware guidance. Related agent frameworks in the directory:

SourcesLink to this section

Source code & docs: sahenjp/RustXNG

Stats from GitHub, 2026-11-02.

Frequently asked

Quick answers to common questions

What is RustXNG?

RustXNG is a agent-framework tool for local AI workloads. Self-hosted, SSRF-hardened web search and grounding engine for local AI agents (AGPL-3.0-or-later)

Is RustXNG free and open source?

Yes, RustXNG has 456 GitHub stars and is licensed under AGPL-3.0. You can self-host it for free on linux, docker, web.

What platforms does RustXNG support?

RustXNG runs on linux, docker, web.

What hardware do I need for RustXNG?

The hardware requirements depend on which models you run. Check our hardware directory for compatible GPUs and systems. RustXNG has 456 GitHub stars and an active community.

Does RustXNG support GPU acceleration?

RustXNG supports GPU acceleration via CUDA, Metal, or Vulkan depending on your platform. For the best performance, pair it with an NVIDIA RTX 4090 or 5090.

What are the best alternatives to RustXNG?

Popular alternatives include other agent-framework tools in our directory. Browse our full collection at /tool for comparisons, community reviews, and benchmark data to find the right fit for your workflow.

How much does RustXNG cost?

RustXNG is free-open-source. It is completely free and open source to self-host.

Pairs well with

Complementary tools, models, and hardware