macOS Native SwiftUI

Eldric GUI Client

A native macOS application built with SwiftUI, offering visual workbenches for complex AI tasks. Train models with live charts, analyze reasoning patterns, merge models with drag-drop, and manage knowledge bases visually.

🎓 Training Workbench ⚖️ Alignment Training 🧠 Reasoning Analysis 🔀 Model Merging 🎭 MoE Support 🔌 Multi-Backend 🧙 Setup Wizard
Eldric - Training Workbench
Training
Alignment
Merging
RAG Manager
Reasoning
Agents

Training Progress - LoRA on llama3.1:8b

2/3
Epoch
0.42
Loss
~8m
ETA

Visual Workbenches

Powerful visual interfaces for complex AI tasks that would be tedious in a terminal

🎓

Training Workbench Popular

Visual Model Fine-Tuning

Complete training pipeline in a visual interface. Create datasets from your prompts, sessions, or files. Configure hyperparameters with intuitive sliders. Monitor training with real-time loss charts and deploy to Ollama when complete.

Dataset Builder

Create training data from saved prompts, chat sessions, RAG sources, or import existing datasets in Alpaca/ShareGPT format.

Hyperparameter UI

Visual sliders for learning rate, batch size, LoRA rank/alpha, warmup steps. Presets for common configurations.

Live Training Charts

Real-time loss curves, learning rate schedules, epoch progress, and ETA. Export charts as images.

Multi-Backend

Choose between Unsloth (fast), Axolotl (flexible), or llama.cpp for training. Auto-detects available backends.

Training Configuration Preview

┌─────────────────────────────────────────────────────────────────┐
│  Training Job: company-assistant-v1                              │
├─────────────────────────────────────────────────────────────────┤
│  Base Model:     llama3.1:8b                                     │
│  Training Type:  LoRA                                            │
│  Dataset:        company-docs (2,847 samples)                    │
│                                                                  │
│  Hyperparameters:                                                │
│  ├─ Learning Rate:  ████████░░░░░░  2e-4                        │
│  ├─ Batch Size:     ████░░░░░░░░░░  4                           │
│  ├─ LoRA Rank:      ████████░░░░░░  16                          │
│  ├─ LoRA Alpha:     ████████████░░  32                          │
│  └─ Epochs:         ██████░░░░░░░░  3                           │
│                                                                  │
│  [Start Training]  [Save Config]  [Load Preset]                 │
└─────────────────────────────────────────────────────────────────┘
⚖️

Alignment Training Advanced

DPO, RLHF & Constitutional AI

Train models to follow your guidelines using Direct Preference Optimization (DPO), RLHF, or Constitutional AI. Create preference datasets where you mark responses as "chosen" or "rejected", then train the model to prefer your style.

Preference Editor

Side-by-side interface to mark responses as chosen/rejected. Import existing preference datasets or create from scratch.

DPO Training

Direct Preference Optimization without needing a reward model. Faster and simpler than traditional RLHF.

Constitutional AI

Define principles and let the model self-critique. Train on self-generated corrections for scalable alignment.

Safety Tuning

Create refusal datasets to train models to decline harmful requests while remaining helpful for legitimate queries.

🧠

Latent Reasoning Workbench Beta

Visualize AI Thinking

Extract and visualize the model's internal reasoning process. See chain-of-thought steps broken down, confidence scores at each stage, and reasoning dependency graphs. Understand why the model reached its conclusions.

Reasoning Extraction

Parse responses to identify discrete reasoning steps, premises, and conclusions. Works with any chain-of-thought model.

Confidence Visualization

See model confidence at each reasoning step. Identify weak links in the reasoning chain.

Reasoning Graphs

Visual DAG showing how reasoning steps depend on each other. Export as images for documentation.

Model Comparison

Compare reasoning approaches between different models on the same problem. Find the best reasoner.

📊

Model Visualizer

Understand Model Architecture

Interactive visualization of transformer architectures. Explore attention patterns, see layer activations, and understand the structure of your models. Great for learning and debugging.

Architecture Diagrams

Visual layer-by-layer breakdown of model structure. See embedding layers, attention blocks, FFN layers, and output heads.

Attention Maps

Visualize which tokens attend to which. Understand how the model processes context and relationships.

Parameter Statistics

See layer sizes, total parameters, memory usage. Compare architectures between models.

Export Diagrams

Export architecture visualizations as PNG/SVG for presentations and documentation.

🔀

Model Merging Studio

Combine Model Capabilities

Visual interface for creating model merge recipes. Drag models onto the canvas, adjust weights with sliders, preview merge results, and create combined models that inherit capabilities from multiple sources.

Drag-Drop Recipe Builder

Select models from your library and drop them into the merge canvas. Intuitive visual workflow.

Weight Sliders

Fine-tune each model's contribution to the final merge. See weight distribution in real-time.

Merge Methods

Choose SLERP (smooth), TIES (task-preserving), DARE (dropout-based), or linear averaging.

Recipe History

Save and reload merge recipes. Track what combinations worked best. Share recipes with team.

⚔️

Model Comparison

Side-by-Side Evaluation

Test models head-to-head with the same prompts. Compare response quality, speed, and style to find the best model for your use case. Run benchmark suites and export comparison reports.

Dual Response View

See two models respond to the same prompt simultaneously. Compare output quality in real-time.

Benchmark Suites

Run standardized test prompts for coding, reasoning, writing. Get objective comparison metrics.

Performance Metrics

Response time, tokens per second, memory usage. Find the best speed/quality tradeoff.

Export Reports

Generate comparison reports in Markdown or PDF. Document your model selection decisions.

📚

RAG Manager

Visual Knowledge Base

Manage your knowledge bases with a visual interface. Create profiles for different projects, drag-drop files to learn, search your knowledge, and preview what context gets injected into prompts.

Knowledge Profiles

Create separate knowledge bases for different projects. Switch profiles to change context.

Drag-Drop Import

Drop files, folders, or URLs onto the window to add to your knowledge base. Supports 20+ formats.

Search Preview

Test queries and see exactly what chunks get retrieved. Tune similarity thresholds visually.

Source Management

Browse learned sources, see chunk counts, remove outdated content. Keep your knowledge fresh.

🗄️

Database Browser

Visual SQL Interface

Connect to databases and explore them visually. Browse tables, view schemas, run queries with syntax highlighting, and export results. Supports SQLite, PostgreSQL, and MySQL.

Multi-Database

Connect to SQLite files, PostgreSQL servers, or MySQL instances. Save connection profiles.

Schema Browser

Visual tree of tables, columns, types, and relationships. Understand database structure at a glance.

Query Editor

SQL editor with syntax highlighting, auto-complete, and query history. Run queries and see results.

Results Grid

Sortable, filterable result tables. Export to CSV, JSON, or copy to clipboard.

More Workbenches

🔧

MCP Creator

Build custom MCP servers visually. Define tools with JSON schemas, create resources, generate TypeScript or Python server code.

🤖

Agent Designer

Create custom agents with specific tool permissions, system prompts, and behavior rules. Test before deploying.

✍️

Prompt Engineering

Develop prompts with variable templates, version history, and A/B testing. Compare prompt variants across models.

🎭

MoE Manager

Manage Mixture-of-Experts configurations. Visualize expert routing, monitor utilization, configure selection strategies.

👤

Personalization

Configure user profiles, provide feedback on responses, train personalization adapters from your interactions.

🌐

Multi-Backend Support

Connect to Ollama, vLLM, llama.cpp, TGI, TensorFlow Serving, NVIDIA Triton, or any OpenAI-compatible API. Manage multiple backends from one interface.

🧙

Setup Wizard

Guided setup for new users. Configure backends, download models, set up RAG, and customize preferences step by step.

📋

Task Manager

Visual task tracking for AI operations. Monitor training jobs, batch processing, and long-running tasks with progress indicators.

🔬

Model Inspector

Deep inspection of model weights, layers, and architecture. Analyze quantization, view tensor statistics, and debug model issues.

📈

Metrics Dashboard

Real-time performance metrics. Track tokens/sec, memory usage, GPU utilization, and response latencies across all backends.

📦

Model Library

Browse, download, and manage models. Search Ollama library, import GGUF files, organize by capability and size.

Ready to Try Eldric GUI?

Request a demo to see the visual workbenches in action.

Request Demo