One prompt. Your AI team. Parallel.

Auto-breaks down complex tasks. Multiple AI Agents work simultaneously, delivering complete results in one go.

Desktop Native16x Parallel Execution100% Local Privacy

Works with all major models — use your own API keys

Doforu

Refactor a legacy monolith into microservices with proper auth

Step 1 — Architecture Scan: Identified 3 independent modules (Auth API, Frontend UI, Database Schema). Zero cross-dependencies detected between them.

Step 2 — DAG Construction: Running Kahn topological sort → All 3 nodes have in-degree 0. Superstep 1: dispatch all in parallel.

Step 3 — Parallel Dispatch: Spawning 3 SubAgents simultaneously. Each handles one module independently. Orchestrator monitors and merges results.

Task decomposition complete. Deploying 3 SubAgents in parallel across Superstep 1:

Designing JWT auth endpoints, bcrypt hashing & middleware

  • Implementing POST /api/auth/register with bcrypt (cost 10)
  • Implementing POST /api/auth/login with JWT access/refresh tokens
  • Building auth middleware with jose for token verification

Building login/register UI with form validation

  • Creating LoginForm component with email/password fields
  • Creating RegisterForm with password confirmation validation
  • Adding client-side error handling and loading states

Defining User model, Prisma schema & migrations

  • Designing User model: id, email, hashedPassword, timestamps
  • Creating Prisma migration for users table
  • Adding seed script for development testing
app/api/auth/register/route.ts
+120-0
app/api/auth/login/route.ts
+85-0
components/auth/login-form.tsx
+156-0
components/auth/register-form.tsx
+98-0
prisma/schema.prisma
+45-0
prisma/seed.ts
+32-0
middleware.ts
+28-0

3

Execution Modes

15+

Model Support

2+

Platforms (Linux soon)

100%

Local Privacy

Core Capabilities

Orchestrator · Plan · Agent Desktop AI agent orchestrator. One prompt, your AI team works in parallel — zero-wait, no context loss.

Orchestrator Intelligent Dispatch

Receives your instruction, understands intent, evaluates complexity, breaks tasks into parallel subtasks, and dynamically assigns them to the most suitable sub-Agents.

Plan Instant Planning

Analyzes your requirements and outputs a complete execution blueprint (steps, tool selection, estimated time). Confirm manually, then switch to Agent or Orchestrator mode to run.

Agent Parallel Execution

Multiple sub-Agents work simultaneously, each responsible for their part, automatically correcting errors, collaborating, and aggregating results into a complete deliverable.

100% Local Privacy

All code, data, and API calls stay on your machine. No cloud upload, no data leakage — your sensitive work never leaves your desktop.

Evolving Skills

Create or refine custom Skills in one sentence. Teach it once, reuse forever. The more your team uses it, the better it understands you.

MCP Ecosystem Integration

Seamlessly connects with databases, Figma, Slack, GitHub, and other external tools to extend Agent capabilities.

Desktop-Native Experience

Direct read/write to the local file system, deeply integrated with your development environment. Supports 15+ local and international models.

30-Day Guarantee

Not satisfied? Full refund within 30 days. No questions asked.

100% Local Privacy

Your code and API keys never leave your machine. No cloud upload.

1 Year Updates

All major updates included. Renew at $29/yr to keep receiving.

4h Response Support

Enterprise-grade support. We respond within 4 hours.

Pricing

Free to start. Pro unlocks unlimited Agent runs, parallel delivery & multi-window.

Free

Chat unlimited, Agent/Plan/Orchestrator 20/day each

$0
Get Started
  • Chat: Unlimited
  • Agent: 20 runs/day
  • Plan: 20 runs/day
  • Orchestrator: 20 runs/day
  • Sub-agents: 20 runs/day
  • Windows: 1 window
  • Custom Skills: Up to 5
  • MCP servers: 3
  • macOS & Windows clients
  • 15+ model support
Most Popular

Pro

Perpetual license, use forever

$99$49

One-time purchase, lifetime use

Perpetual license. Includes 1 year of updates. Renew for $29/year to keep receiving updates.

  • Chat: Unlimited
  • Agent: Unlimited
  • Plan: Unlimited
  • Orchestrator: Unlimited
  • Sub-agents: Unlimited
  • Per-agent model selection
  • Windows: Up to 8 windows
  • Custom Skills: Unlimited
  • MCP servers: Unlimited
  • macOS & Windows clients
  • 15+ model support
  • Custom models: Supported
  • Perpetual license — use the software forever
  • 1 year of updates included
  • Proactive context compression

Enterprise

For teams and organizations

Custom
Get Started
  • Everything in Pro
  • Priority support (4h response)
  • Custom integrations & deployment
  • Team workspaces & shared Skills
  • Dedicated account manager

Frequently Asked Questions

Doforu is a desktop AI agent orchestrator, unlike Cursor (IDE plugin) or Claude Code (terminal CLI). One prompt, your entire AI team delivers in parallel — zero-wait, no context loss. Supports Plan / Agent / Orchestrator modes.

Supports 15+ local and international models: OpenAI (GPT-5.5), Anthropic (Claude Opus 4.7), Google (Gemini 3.1), DeepSeek (V4), Alibaba Qwen, ByteDance Doubao (Seed 2.0), Moonshot (Kimi K2.6), Baidu ERNIE 5, Zhipu (GLM-5.1), and more. Also compatible with local models via Ollama and vLLM.

Describe it in natural language within Doforu to create a Skill — teach it once, reuse forever. Skills support local directory management and Claude Code-compatible formats. Team sharing is coming soon.

Free includes unlimited Chat mode, 20 Plan/Agent/Orchestrator runs per day combined, up to 5 custom Skills, and 3 MCP servers. Pro unlocks unlimited runs, unlimited Skills, long-term Memory, unlimited MCP servers, and proactive context compression.

Doforu only charges a platform fee per complete task run. API usage is billed directly by the model provider through your own API Key. Doforu does not intermediate, markup, or profit from API usage — costs are fully transparent.

macOS 12+ and Windows 10+ are both supported (Linux support coming soon). Download the client for your platform, select a model, and enter your API Key to get started.

Visit the documentation center for self-service help, or submit feedback via GitHub Issues. Enterprise users can email support@doforu.ai for support with a 4-hour response time.

Get Started in Seconds

Native macOS & Windows app. Your AI team, ready to work in parallel.

macOS

Apple Silicon

Version 3.6.0

Download for macOS

macOS 12+ required

macOS

Intel

Version 3.6.0

Download for macOS

macOS 12+ required

Windows

x64

Version 3.6.0

Download for Windows

Windows 10/11 required

Doforu | Desktop AI Agent Orchestrator