Pages

Home Features Solutions Documentation About Founders Privacy Promise

Resources

Getting Started API Reference Tutorials Changelog Roadmap

Company

Our Story Contact Privacy Policy Terms of Service

Every Feature You Need to
Command AI Teams

Mix any models. Persistent context. 18 specialized roles. Full control.

Mix & Match Any AI Models

The Command Center enables true multi-model collaboration where different AI providers work together seamlessly.

Claude + Local Ollama

Use Claude as Commander for strategic thinking while local Ollama models handle coding tasks, saving API costs.

GPT + Local Ollama

Assign GPT to architecture decisions while free local models execute implementation.

Gemini + Local Ollama

Let Gemini handle security reviews while Ollama models write code.

All Cloud Models Together

Mix Claude, GPT, and Gemini on one team, each assigned to roles matching their strengths.

All Ollama Models Together

Run entirely offline with 24+ local models, paying nothing for API calls.

Any Combination

Assign any model to any role based on your budget, privacy needs, and task requirements.

Persistent Context Across Models

Unlike other platforms where each AI forgets everything between messages, the Command Center maintains context as work passes between models.

When Commander (Claude) hands off to Coder (Ollama), the Coder receives full context. When Coder hands off to Reviewer (GPT), the Reviewer sees everything that came before. This enables genuine collaboration rather than isolated responses.

Local Storage

IndexedDB and localStorage keep everything on your machine. Multi-conversation support with separate history per conversation. Import/export as JSON.

Role-Based Model Assignment

Each of the 18 crew roles has its own model dropdown. You choose which AI handles each job.

Role Suggested Model Why
Commander Cloud (Claude, GPT) Strategic reasoning requires advanced capability
Coder Local (Ollama) or Cloud High-volume work benefits from free local models
Reviewer Cloud (GPT, Gemini) Quality gates benefit from strong reasoning
Security Cloud (Gemini) Security analysis needs comprehensive knowledge
Docs Writer Local (Ollama) Documentation is high-volume, lower complexity

Model Catalog with Capability Display

At-a-glance model selection with clear capability indicators.

🔴 Tools — Functions and web search
🔵 Vision — Image analysis
🟡 Embed — Semantic search
🟢 Thinking — Extended reasoning

Context Window Badges: 8K, 32K, 128K, 200K, or 1M tokens
Size Display (Local): Small (0.3–2 GB), Medium (3–8 GB), Large (12–20 GB)

Warm State System

Visual badges show each model's readiness.

🟢 Warm — Loaded, instant responses
🟠 Warming — Loading into memory
⚫ Cold — Needs startup time

Warmup Allowlist

Restricts which models can auto-warm, preventing accidental resource consumption.

Per-Model Timeouts

Override warmup timeouts for large models that need more initialization time.

Keepalive Settings

Control how long models stay loaded. Idle cooldown automatically unloads inactive models.

Cloud models (Claude, GPT, Gemini) display as permanently "ready" since they require no local warmup.

18 Crew Roles in 7 Categories

Organized by function with color-coded categories.

Commander Coordinator PM Architect UX Designer Coder 1 Coder 2 Reviewer QA Reviewer Tester Security DevOps Analyst Researcher Docs Reporter Image Gen Video Gen

"Add to Workspace" Checkbox

Include a role in the active team with a single click.

"Seat at Table" Button

Activate a role for the current session instantly.

Team Presets

One-click configuration for common workflows.

Solo Commander

Just the commander for quick tasks

Duo Coder

Commander + Coder pair

Trio Review

Commander + Coder + Reviewer

App Builder

Full development team

Bug Fixer

Focused debugging team

Doc Writer

Documentation-focused team

Solo Pipeline & Workflow Modes

Automated multi-step execution.

Commander Plans task
→
Coder Implements
→
Reviewer Validates

Workflow Modes

Sequential — One role at a time
Parallel — Multiple roles simultaneously

Pipeline Features

Context forwarding passes full history to each step.
Approval Gates create human checkpoints: Plan OK, Code Review OK, Security OK.

Skill Levels & Work Roles

Interface adapts to your experience.

Skill Levels

Beginner Guided
Beginner Autopilot
Intermediate
Advanced
Expert

Work Roles

Coder
Reviewer
Architect
Manager
Researcher
Security
DevOps
Analyst
Docs
UX Designer
Reporter

Visibility matrix shows or hides UI sections based on skill level.

Ready to Command Your
AI Team?

Start free. No credit card required.

Get Started Free