Claude Code/Cowork Plugin

MultAIALPHA

Leverage the Knowledge and Intelligence of 7 Leading AIs at Once

A Claude Code/Cowork plugin that submits research prompts to Claude.ai, ChatGPT, Copilot, Perplexity, Grok, DeepSeek & Gemini in parallel — then synthesizes the results into structured reports, landscape analyses, and comparison matrices.

Get Started View on GitHub →
Supported Platforms

One Prompt. Seven Perspectives.

Each platform brings a different training set, reasoning style, and search index. MultAI queries all seven simultaneously via Playwright browser automation — no API keys needed.

Gemini
Claude.ai
ChatGPT
Copilot
Perplexity
Grok
DeepSeek
PlatformFree TierDEEP ModeAgent Fallback
Google Gemini✓✓ Deep Research✓
Claude.ai✓✓ Pro plan✓
ChatGPT✓✓ Plus plan✓
Microsoft Copilot✓—✓
Perplexity✓✓ Pro plan✓
Grok✓✓✓
DeepSeek✓✓ DeepThink✓
Capabilities

Everything You Need for Multi-AI Research

From parallel submission to structured reports — built into your Claude Code workflow.

Intelligent Routing

Analyzes your intent and selects the right workflow automatically — no flags, no routing decisions, no skill names to remember.

Parallel Execution

All 7 platforms run concurrently via asyncio.gather(). A typical REGULAR-mode run completes in under 90 seconds.

DEEP Research Mode

Activates each platform's research/think mode (Deep Research, DeepThink, etc.) for comprehensive answers with citations.

Structured Reports

Raw responses from all 7 platforms are synthesized into structured deliverables — 9-section landscape reports, product intelligence reports, or free-form summaries.

XLSX Comparison Matrix

Maintain a capability matrix with weighted scores, combo columns, and auto-reordering. All via Python scripts.

Rate Limiting

Per-platform budgets, cooldowns, and daily caps — persisted across sessions. Never get rate-limited again.

Agent Fallback

When a Playwright selector fails, a vision-based browser-use agent takes over — powered by Claude Sonnet or Gemini Flash.

Self-Improving

A timestamped run log is appended after every execution. Templates and scripts can be updated based on learnings from each run.

Shared Domain Knowledge

domains/{domain}.md is enriched after every research run. New archetypes, terminology, and trends accumulate across sessions.

The Skill

One Skill. Four Workflows.

Just describe what you need. /multai figures out the rest.

/multai

Market Landscape Reports

Ask about a product category or market — get a 9-section structured report with Top 20 commercial and OSS solutions, positioning matrices, and trend analysis.

Landscape 9 Sections
✓
"Run a market landscape on DevOps platforms for SMBs"
✓
"Give me a competitive landscape for observability tools"
✓
"What's the API gateway ecosystem look like right now?"
/multai

Product Deep-Dives

Name a product or URL — get a Competitive Intelligence Report covering capabilities, integrations, pricing, and competitive context. Optionally scored in the comparison matrix.

Product CIR
✓
"Research humanitec.com"
✓
"Evaluate Backstage vs Port.io"
✓
"Analyze Cortex — focus on developer portal capabilities"
/multai

Comparison Matrix

Maintain an XLSX capability matrix — add vendors, update scores, apply combo columns, reorder by weighted total, and verify coverage.

XLSX Matrix
✓
"Add Harness to the comparison matrix"
✓
"Update the score for Cortex on developer portal"
✓
"Rebuild the matrix from archived responses"
/multai

Direct Multi-AI Queries

For anything else — submit your question to all 7 platforms simultaneously and get a synthesized answer drawing on every perspective.

Direct 7 Platforms
✓
"What are the trade-offs between Rust and Go for backend services?"
✓
"Summarize the current state of WebAssembly on the server"
✓
"What consensus is emerging on LLM memory management?"
Workflow

How It Works

From natural language request to structured deliverable in four steps.

1

Describe Your Goal

"Research the DevOps platform landscape for SMBs"

2

Auto-Route

/multai analyzes your intent, selects the right workflow, and builds the prompt

3

7-AI Parallel Run

Playwright submits to all 7 platforms concurrently in DEEP mode

4

Structured Report

Responses are synthesized into a 9-section landscape report with Top 20 vendors

You (Claude Code) | v /multai ── analyzes intent | |--> landscape --> 7 platforms (DEEP) --> 9-section report |--> deep-dive --> 7 platforms (DEEP) --> CIR + optional XLSX |--> matrix --> XLSX operations |--> direct --> 7 platforms --> synthesized answer
Installation

Up and Running in 2 Commands

Python dependencies install automatically on your first session via a SessionStart hook. No manual setup.

# Step 1 — Register the marketplace (one-time)
/plugin marketplace add alo-exp/multai

# Step 2 — Install the plugin
/plugin install multai@multai

# Done! Start a new session and all deps install automatically.
# Claude Desktop GUI:
# Browse Plugins > Personal > + > Add marketplace from GitHub
# Enter: alo-exp/multai, then install the multai plugin

# Or from the CLI:
claude plugin marketplace add alo-exp/multai
claude plugin install multai@multai
git clone https://github.com/alo-exp/multai.git
cd multai
bash install.sh

# Load directly without marketplace registration:
claude --plugin-dir ./multai

No API keys required for core functionality.
The engine uses Playwright browser automation with your existing Chrome logins. Optionally add GOOGLE_API_KEY (free) or ANTHROPIC_API_KEY for vision-based agent fallback.

Examples

Just Describe What You Need

/multai analyzes your intent and routes automatically. No flags or skill names needed.

Landscape Research
"Run a market landscape analysis of Internal Developer Platforms for platform engineering teams" → 9-section report + Top 20 vendors → Auto-launched report viewer
Solution Research
"Research Humanitec.com — I want a Competitive Intelligence Report covering their IDP capabilities" → Competitive Intelligence Report → Optional XLSX matrix update
Comparator
"Add Spinnaker to the comparison matrix based on the latest CIR" → Extracts capabilities from CIR → Updates XLSX matrix
Direct Multi-AI
"What are the main trade-offs between microservices and monoliths?" → All 7 platforms queried in parallel → Single synthesized answer
Rate Limiting

Built-In Budget Management

Per-platform budgets, cooldowns, and daily caps prevent rate limiting. State persists across sessions.

TierBudget / SessionCooldownDaily Cap
free3 requests30 min5
pro10 requests5 min20
Documentation

Comprehensive Docs Included

📖

User Guide

Friendly end-user guide: installation walkthroughs, skill overviews, viewing reports, troubleshooting.
🔧

Contributor Guide

Full 1,100-line technical reference: CLI flags, platform internals, rate limiting, tests, CI/CD.
🏗

Architecture

System topology, data flows, module design, interface contracts, design decisions.

SRS

Software Requirements Specification: functional requirements, use cases, constraints.
✅

Test Strategy

96 automated tests, E2E test plan, test case reference, coverage matrix.
🚀

CI/CD Strategy

Pipeline stages, make targets, deployment scope, regression checks.
📝

Changelog

Version history from v2.0 through v0.3.00.2.26040601 Alpha with migration notes.
Architecture

Self-Contained Skills

Each skill owns its scripts, templates, and guides. No shared engine at the root — skills are portable modules.

multai/
├── skills/
│   ├── orchestrator/         # Router + Playwright engine
│   │   ├── SKILL.md
│   │   └── engine/              # orchestrator.py, platforms/, rate_limiter.py
│   ├── landscape-researcher/ # Market landscape reports
│   ├── solution-researcher/  # Product deep-dives (CIR)
│   ├── comparator/           # XLSX matrix ops scripts
│   └── consolidator/         # Response synthesis
├── domains/                  # Shared domain knowledge
├── reports/                  # Output + preview.html viewer
├── tests/                    # 98 pytest unit tests
└── docs/                     # SRS, Architecture, Test, CI/CD