Edelux Foundry

Build AI.
Keep control.

Models, agents and applications in one workspace, with your infrastructure and your budgets under control.

Open Edelux Explore deployment

One workspace. Three starting points.

Prompt + knowledge

Agent + tools

Run history

Scoped access · budgets · audit trail

Connect a model to your knowledge and tools. Inspect each run before putting it into a workflow.

Build an agent

Model registry

Choose the model.
Keep your options open.

Open-weight releases, connected to the serving engine your infrastructure can actually run.

vLLMSGLangTGIOllama

Find a model or publisher

55 matching models

Moonshot AI

Kimi K3

2.8T MoE, 104B active, 1M context

Kimi K3 License

Alibaba Qwen

Qwen3.8 Max

2.4T MoE, 95B active, 262K context

Qwen3.8-Max License

DeepSeek

DeepSeek V4 Pro

1.6T MoE, 49B active, 1M context

MIT

Z.ai

GLM-5.2

753B MoE, 40B active, 1M context

MIT

MiniMax

MiniMax-M3

428B MoE, 23B active, 1M context

MiniMax Community License

DeepSeek

DeepSeek V4 Flash

284B MoE, 13B active, 1M context

MIT

Model links open upstream weights. Inclusion in this roster does not mean a hosted endpoint is running.

Run where your workload belongs.

Use managed compute for experiments, or take a deployment bundle to your own infrastructure. Keep the deployment artifact either way.

An accelerator board partially withdrawn from its chassis

Managed compute

Choose CPU or GPU resources for an endpoint. Review the price before starting and configure an idle timeout.

Modal compute endpoints

Explore endpoints

Your infrastructure

Download a portable bundle, review its configuration, and apply it to a Kubernetes cluster, Compose host or Linux server.

Kubernetes · Docker · Linux

Explore bundles

Keep the tools you already use.

The setup script detects the coding tools already installed on your machine and writes the gateway endpoint, token and model profiles into each one.

Oh My Pi~/.omp/agent/models.yml
Claude Code~/.claude.json
Codex CLI~/.codex/config.json
OpenCode~/.config/opencode/opencode.json
Edecode~/.config/edecode/edecode.json
Hermes Agent~/.hermes/config.yaml
Continue.dev~/.continue/config.json
Aider~/.aider.conf.yml

Give teams access.
Keep oversight.

Control who can run workloads, what they can spend, and which steps need a human decision.

An enclosed aisle between data centre racks

Scope access by team: Organizations, roles and API keys define who can access each workspace.
Keep spending visible: Review usage and costs. Set quotas and budgets before your workloads grow.
Put a person in the loop: Require approval in a workflow, assign a reviewer and record the decision.
Review what happened: Use run history and the audit journal to investigate execution and account activity.

Bring your own hardware.

Open Edelux

Build AI.Keep control.

Choose the model.Keep your options open.