v2.0.0

Osmantic/ODSv2.0.0Mar 4, 2026by Lightheartdevs

AI Summary

Dream Server v2.0.0, codenamed 'Strix Halo', provides a complete local AI stack with a rewritten modular installer and support for high-end hardware like AMD Strix Halo and NVIDIA Ultra-tier GPUs. It includes a bootstrap mode for rapid setup, a management dashboard, and a CLI for controlling the entire stack.

Key Highlights

AMD Strix Halo support with ROCm 7.2 and unified memory tiers
NVIDIA ultra tier support for 90GB+ multi-GPU setups
Modular installer rewriting a 2591-line monolith into 6 libraries
Bootstrap mode allowing chat in under 2 minutes
Extension system for hot-pluggable services via CLI

New Features

Hardware auto-detection for optimal model selection
13 integrated services including LLM inference, chat UI, voice, agents, and RAG
Management dashboard for real-time GPU metrics and service health
dream-cli for full stack management and mode switching
Privacy Shield for PII scrubbing

Full Release Notes

## Dream Server v2.0.0 — Strix Halo

**One command to a full local AI stack.** Buy hardware. Run installer. AI running.

[![Watch the demo](https://img.shields.io/badge/Demo-Watch%20on%20YouTube-red?logo=youtube)](https://youtu.be/nO8xFNHX-HA) [![Website](https://img.shields.io/badge/Website-dreamserver.ai-purple)](https://dreamserver.ai)

### Highlights

- **AMD Strix Halo support** — ROCm 7.2 with unified memory tiers (SH_LARGE, SH_COMPACT), running Qwen3 Coder Next 80B MoE on a single APU
- **NVIDIA ultra tier** — NV_ULTRA for 90GB+ multi-GPU setups (A100/H100)
- **Modular installer** — 2591-line monolith rewritten as 6 libraries + 13 phases, each in its own file
- **Bootstrap mode** — chat in under 2 minutes with a tiny model while the full model downloads in the background
- **Extension system** — every service is a manifest + compose fragment, hot-pluggable via `dream enable/disable`
- **13 integrated services** — LLM inference, chat UI, voice (STT + TTS), AI agents, workflow automation, RAG, web search, deep research, image generation, and privacy tools
- **Management dashboard** — real-time GPU metrics, service health, model info, all in one view
- **dream-cli** — full stack management with mode switching (local/cloud/hybrid), model swapping, presets

### What's Included

| Service | Purpose |
|---------|---------|
| llama-server | LLM inference (CUDA + ROCm) |
| Open WebUI | Chat interface |
| LiteLLM | API gateway (local/cloud/hybrid) |
| OpenClaw | Autonomous AI agents |
| n8n | Workflow automation (400+ integrations) |
| Whisper | Speech-to-text |
| Kokoro | Text-to-speech |
| Qdrant | Vector database for RAG |
| SearXNG | Self-hosted web search |
| Perplexica | Deep research engine |
| ComfyUI | Image generation |
| Privacy Shield | PII scrubbing proxy |
| Dashboard | GPU metrics + service health |

### Hardware Auto-Detection

The installer detects your GPU and picks the optimal model:

| Hardware | VRAM | Model |
|----------|------|-------|
| NVIDIA 8-11 GB | RTX 4060 Ti | Qwen 2.5 7B |
| NVIDIA 12-20 GB | RTX 3090 | Qwen 2.5 14B |
| NVIDIA 20-40 GB | RTX 4090 | Qwen 2.5 32B |
| NVIDIA 40+ GB | A100 | Qwen 2.5 72B |
| NVIDIA 90+ GB | Multi-GPU | Qwen3 Coder Next 80B |
| AMD Strix Halo 64 GB | Ryzen AI MAX+ 395 | Qwen3 30B-A3B |
| AMD Strix Halo 96 GB | Ryzen AI MAX+ 395 | Qwen3 Coder Next 80B |

### Install

```bash
curl -fsSL https://raw.githubusercontent.com/Light-Heart-Labs/DreamServer/main/dream-server/get-dream-server.sh | bash
```

### Full Changelog

See [CHANGELOG.md](https://github.com/Light-Heart-Labs/DreamServer/blob/main/dream-server/CHANGELOG.md) for the complete list of changes.