Top AI Product

Light-Heart-Labs (with the OpenClaw Collective) released DreamServer — a full local AI stack that bundles LLM inference, chat UI, voice (STT + TTS), AI agents, workflow automation, RAG, web search, deep research, image generation, and privacy tools into a single installer. No cloud, no subscriptions, no API keys.

## What’s in the box

13 services integrated and orchestrated: vLLM for inference, chat UI, voice agents, workflow automation, RAG, privacy shield, real-time dashboard, and image generation. Runs on Linux (NVIDIA + AMD), Windows (WSL2), and macOS (Apple Silicon). The installer auto-detects hardware and configures accordingly.

## Bootstrap mode

DreamServer ships a lightweight 1.5B model that boots in under a minute, so users can start chatting while the full model downloads in the background. April 2026 updates added per-container CPU/memory stats, read-only service logs, per-service resource metrics aggregation, real-time bootstrap download tracking, and macOS native llama-server hot-swap.

## Why it matters

Self-hosted AI has been a death-by-a-thousand-cuts problem: pick an inference server, find a chat UI, integrate voice separately, hand-wire RAG, manage GPU drivers. DreamServer is the first credible attempt to ship the whole stack as one install. For privacy-sensitive users or anyone tired of monthly AI subscriptions, this is the alternative.