Neural Companion
GitHub

Neural Companion feature

Visual replies

Generate and manage visual replies through hosted providers or local ComfyUI workflows, with configurable workflow JSON, image size, history, and story-oriented controls.

What it adds

Generate and manage visual replies through hosted providers or local ComfyUI workflows, with configurable workflow JSON, image size, history, and story-oriented controls.

Requirements

  • A configured visual-reply provider.
  • For local ComfyUI, a running ComfyUI server and a compatible saved workflow.
  • Explicitly enable only the screen, webcam, or clipboard sources you intend to share.

Verify in the project documentation →

Feature

Local AI companion

Connect Neural Companion to local chat providers such as LM Studio or Ollama while keeping its speech, memory, avatar, visual-reply, and addon workflows available.

Explore Local AI companion

Feature

AI avatars

Choose no-avatar mode or connect Neural Companion to MuseTalk, Scenic image packs, VSeeFace, or VaM, with each avatar mode configured and enabled independently.

Explore AI avatars

Feature

Persistent companion memory

Continue longer conversations with continuity summaries and a versioned long-term memory archive that supports semantic retrieval, linked image recall, and readable exports.

Explore Persistent companion memory