Vivian

Sign in to continue

🏠 Dashboard

Overview of Vivian's brain and server pool.

🖥️
Servers Online
📊
Total Requests
💬
Conversations
🧠
Memories
💜 Current Emotional State
💭
Loading…
✨ Vivian's Identity
Loading…
🖥️ Server Pool
Loading…

🧠 Smart Loader

Self-tuning model loader. Auto-detects GPU architecture, picks the optimal multi-GPU split, KV-cache compression, flash-attention, and the largest safe context window — then lets you chat with a live test bot. Loads GGUF and safetensors.

🎮 GPUs (live VRAM)
Probing…
📦 Load a Model
🤖 Auto-Tune Plan
Status— pick a model —
💬 Test Chatbot

⚡ Model Engines

Switch between local llama-cpp-python GPU engine and Ollama server pool. Full runtime control — no restart needed.

🔀 Routing Mode

Loading…

⚡ Local Llama Engine (llama-cpp-python)
Package
Model
GGUF path
File exists
Loaded in RAM
Context window
GPU layers
Multi-GPU split
Batch / µBatch
KV cache type
Flash attention
🗂️ GGUF Model Picker
🖥️ Ollama Server Pool
Total servers
Healthy
👁️ Vision Engine (local GGUF multimodal)
Package
Model
GGUF path
mmproj projector
Files exist
Loaded in VRAM
GPU placement
Handler
Context window
CLIP encoder
Endpoints: POST /v1/vision/analyze · POST /v1/vision/chat · GET /v1/vision/status
Loads onto the GPU with the most free VRAM and stays resident there. The CLIP image-encoder runs on CPU so it never fights the text model for GPU 0.
💬 Chat Engine (dedicated 9B, text chat)
Package
Model
GGUF path
File size
File exists
Loaded in VRAM
GPU pin
Context window
Batch (n / u)
KV cache
Flash attention
Status
Endpoints: POST /v1/chat · GET /v1/chat/status · POST /v1/chat/load
A small, fast local model for plain text chat, pinned to its own GPU. When busy or unloaded, /v1/chat automatically falls back to the Ollama manager so requests always complete.
🎛️ Model Control — Load / Kill / Clear
📋 Available Models
Loading…
ℹ️ How routing works:
Auto — the local GPU engine handles requests for its configured model; all other model names go to Ollama.
Llama Only — every chat request is sent to the local GPU engine regardless of model name. Best for speed.
Ollama Only — completely bypasses the local engine. Use this if the GGUF isn't ready or for multi-model use.

🖥️ Ollama Servers

Add and manage Ollama backend servers. Smart routing uses priority + health.

NameURLStatusConnectionsPriorityLatencyRequestsModelsActions
Loading…

🧠 Mind & Memory

Vivian's core identity, knowledge, and episodic memories.

CategoryKeyValueImportanceActions
Loading…

💜 Emotional History

Track how Vivian's emotional state has evolved over time.

💜 Current State
💭
📈 Intensity Timeline
EmotionIntensityValenceTriggerTime
Loading…

👥 Users

Manage API users and their keys.

UsernameDisplay NameRoleMemoryCreatedLast LoginActions
Loading…

⚙️ Settings

Configure Vivian's behaviour and personality.

Loading…

📰 News Feed

Latest aggregated news from 35+ RSS sources, refreshed every 15 minutes.

🧠 Live Learning

Hash-indexed RAG knowledge base. Index files, directories, code, and news to give Vivian grounded context during inference. No retraining needed.

📄
Chunks Indexed
📁
Files Indexed
🔍
Embed Model
💾
DB Size
⚙️ RAG Settings

🔑 Keyword Relevance Index (BM25 — primary retrieval; only injects relevant knowledge)
📥 Ingest Knowledge
📄 Index File
📂 Scan Directory
📝 Paste Text
🔍 Test Retrieval
⚙️ Indexing Jobs

No jobs yet.

📚 Indexed Documents

📋 Request Logs

Every incoming API call — what was sent, what came back, tokens used.

Time Method Path Status Duration User IP Model Tokens↑ Tokens↓ Total Request Response

⚠️ Server Errors

Last 100 unhandled exceptions and 500 errors. Click any row to expand the traceback.

Loading…

📦 Sessions

Manage AI sessions (code sessions and standard sessions).

IDUserTitleStatusOrg UUIDCreatedActions
Loading…

🔌 Bridge & Workers

Monitor bridge environments, work dispatch queues, and active workers.

IDUserBridge IDStatusMachineWorker TypeCreatedActions
Loading…

🔐 OAuth & Trusted Devices

Manage active OAuth access tokens and enrolled trusted devices.

UserClient IDScopesIssuedExpiresActions
Loading…

🖥️ Admin Terminal

Run built-in admin commands or safe shell utilities. Type help to list all commands.

admin@vivian $ 

💳 Purchases

All token purchase orders — approve CashApp payments or review PayPal IPN results.

User Tokens Amount Method Status Ref Date Actions
Loading…

🪙 Token Packages

Manage available token tiers that users can purchase.

Name Tokens Price (USD) Enabled Actions
Loading…

🔐 License Management

Manage license products and generate license keys for users.

Name Description One-Time Monthly Active Actions
Loading…

💬 Forum Manager

Manage categories, boards, threads, posts, and user moderation for forums.d0a.net

🗂️
Categories
📋
Boards
🧵
Threads
💬
Posts
👥
Forum Users
🚫
Banned Users
✦ Chat with Vivian

🔗 Embeddings

Embedding models available in your Ollama pool, and a live tester.

📡 Available Embedding Models
Loading…
🔖 Selected Model
⚡ Embedding Tester

👁️ Vision / Image Analysis

Use Ollama vision models (llava, minicpm-v, moondream…) to describe or query images.

📡 Available Vision Models
Loading…
🖼️ Image Analyzer

🧊 3D Studio

Talk to the local text-to-3D model (Hunyuan3D). Describe an object and get a downloadable 3D mesh, streamed live over a WebSocket that stays open for the whole generation.

Checking 3D service…
💬 Describe your model
🔭 Preview
Your generated model will appear here

🎬 Video Studio

Local text-to-video AI (zeroscope) on the reserve GPU. It shares the 3D service's job queue, so a clip waits its turn if a 3D model is mid-generation.

Checking video service…
💬 Describe your video
📺 Preview
Your generated video will appear here
Recent videos

📊 Site Analytics

Pageviews, unique visitors, top pages, and referrers across all sites.

📈 Daily Pageviews
🌐 Per-Site Traffic
📄 Top Pages
PathSiteHits
Loading…
🔗 Top Referrers
ReferrerHits
Loading…

🔍 SEO Manager

Manage meta titles, descriptions, keywords, and Open Graph settings per site and page.

SitePage KeyTitleDescriptionKeywordsRobotsActions
Loading…

📁 Files

Uploaded files and multipart uploads.

IDFilenamePurposeBytesStatusActions
Loading…

🤖 Assistants

OpenAI-compatible assistants and their threads.

IDNameModelActions
Loading…

🗃️ Vector Stores

Semantic search vector stores and their files.

IDNameFilesStatusActions
Loading…

📦 Batches

Batch API jobs for bulk processing.

IDEndpointStatusProgressActions
Loading…

🎛️ Fine-tuning Jobs

Model fine-tuning job history.

IDBase ModelFine-tuned ModelStatusActions
Loading…

📊 Evals

Model evaluation configurations and run history.

IDNameModelActions
Loading…

📖 Source Code Library

Browse and manage the indexed source code library.

Loading…
PathLangLinesSizeIndexedActions
Loading…

🎮 Xbox 360 / Xbox Live Library

Browse and manage the indexed Xbox source library.

Loading…
PathLangLinesSizeIndexedActions
Loading…

Code Library AI

Chat with an AI that has direct access to the source code library.

History

No history yet

Ask me anything about the source code. I'll search the library to find relevant functions, classes, and implementations.

Xbox Library AI

Chat with an AI that has direct access to the Xbox 360 / Xbox Live source library.

History

No history yet

Ask me anything about the Xbox 360 / Xbox Live source. I'll search the library and GitHub for relevant code.

Confirm