Get started

Eldric 5.0.
Production install
in five minutes.

Three install paths cover the great majority of deployments: a Linux server for a team or department, a macOS workstation for evaluation and solo work, or a multi-node cluster for a hospital network or research consortium. Pick the one that fits — the commands below assume root and a clean host.

Linux server macOS workstation Cluster
Linux server

Fedora 42+, RHEL 9+, CentOS Stream 9+.

Bootstrap the repository, install the metapackage, and start the service. The one-line installer below adds the signed Eldric repository to /etc/yum.repos.d/, imports the GPG key, and installs the kernel module set.

curl -fsSL https://repo.eldric.ai/install.sh | sudo bash
sudo dnf install eldric-aios
sudo systemctl enable --now eldric-aios

Within thirty seconds the controller, edge, router, worker and data daemons are all up. Open https://<your-host>/chat in a browser — the very first signup becomes the system administrator. There is no default password.

Prefer a single command that handles everything from repository setup through first-launch readiness?

curl -fsSL https://repo.eldric.ai/install-eldric.sh | sudo bash

That wraps the three commands above plus a health check on each daemon before it returns.

macOS workstation

One PKG, double-click, done.

For evaluation, single-user work, or developing against a local Eldric, download the macOS PKG and run the installer. The package places binaries under /usr/local/libexec/eldric-aios/, registers a LaunchAgent, and starts the daemons on the next login.

Download Eldric for macOS

Gatekeeper note. macOS will prompt “unidentified developer” on first launch. Right-click the PKG, choose Open, then confirm with Open again in the security dialog. Eldric 5.0 packages are not Apple-notarized; notarized releases are planned for 5.1.

The chat interface comes up at https://localhost/chat after install. The first signup on that machine becomes the local administrator.

Multi-node cluster

Beyond a single host.

For a hospital network, research consortium, or any deployment that needs more than one node, install the controller on one machine first, then join workers, routers and data nodes from there. The cluster setup guide walks through SSH-based fanout deployment, license placement, replication policy and TLS configuration.

Cluster & enterprise overview

What you get

Out of the install command.

Chat shell + 25 agents

Web chat at /chat, twenty-five specialised agents (researcher, coder, validator, planner, scientist, and more), tool-calling out of the box.

140+ scientific APIs

NASA, ESA, CERN, LIGO, ClinicalTrials.gov, PubMed, BLAST, AlphaFold, Materials Project, and the rest — all federated through the science worker.

Plugin marketplace

Browse and install plugins from /api/v1/marketplace/catalog. Five plugin types: Tool, Filter, Pipe, Action, Widget.

Multi-tenant + RBAC

Departments, studies or projects each get their own tenant. Viewer, Developer, Admin, SuperAdmin roles. Cross-tenant access denied at the gateway.

Training pipeline

Fine-tune a model on your own data — LoRA, QLoRA, SFT, DPO. The dataset never leaves the data worker.

Audit ledger

Hash-chained log of every AI-assisted decision. Defensible record for compliance reviews.

Licensing

Free tier or paid — same install.

The free tier ships with the full kernel: one controller, one router, two workers, all features. To scale beyond that, request a Standard, Professional or Enterprise license from license@core.at and drop the signed license file into /etc/eldric/license.json. The controller picks it up on next start and the limits lift accordingly.

Pricing tiers

Next step.

Installed, but nothing's happening? Walk through the first-run guide. Something failed during install? Common errors and recoveries are collected in the troubleshooting page. Stuck on something neither covers? Write to office@eldric.ai.