opc-agent

⚡ OPC Agent

Your own AI employee — local, private, gets smarter over time.

中文文档

Why OPC Agent?

AI Agents are powerful, but hard to use for most people:

• Expensive — Cloud agents charge per token. Costs add up fast.
• No memory — Every conversation starts from scratch.
• Data privacy — Your chats and documents live on someone else's servers.
• Can only chat — Can't read files, search the web, or run code.

OPC Agent fixes all of this:

✅ Runs locally, zero cost (powered by Ollama)
✅ Gets smarter over time (automatic learning & evolution)
✅ Your data stays on your machine
✅ Can read/write files, search the web, execute code, use tools

🚀 Install

Pick your OS, copy one line:

macOS / Linux

curl -fsSL https://raw.githubusercontent.com/Deepleaper/opc-agent/main/install.sh | bash

Windows

irm https://raw.githubusercontent.com/Deepleaper/opc-agent/main/install.ps1 | iex

The installer automatically sets up Node.js, OPC Agent, Ollama, and the best AI model for your hardware. No manual steps.

Manual install

npm install -g opc-agent@alpha

⚡ Get started in 30 seconds

Step 1: Create your AI employee

opc init my-agent
cd my-agent

Step 2: Start chatting

opc chat

That's it. Your AI employee is ready.

More

opc studio        # Web dashboard at localhost:4000
opc run           # Start everything: chat + Telegram + web + dashboard

What can it do?

OPC Agent isn't just a chatbot. It's an AI employee that gets work done:

Capability	Details
💬 Chat	Terminal or web interface
📁 Read & write files	Read your docs, write reports, organize notes
🔍 Web search	Real-time search for up-to-date information
🌐 Read web pages	Fetch and summarize any URL
💻 Execute code	Run JavaScript, TypeScript, Python
🧠 Memory	Remembers past conversations, gets smarter over time
🔧 MCP tool extensions	Connect GitHub, databases, Slack, and more
📱 Telegram bot	Add a bot token and chat via Telegram
🎙 Voice synthesis	Text-to-speech via edge-tts
👥 Sub-agents	Spawn parallel workers for complex tasks
🔄 Provider failover	Circuit breaker, automatic retry with fallback
📋 20 workstation roles	Pre-built templates: customer service, engineer, analyst, executive...
⏰ Scheduled tasks	Cron jobs auto-registered from templates

🧠 Gets smarter over time

This is what makes OPC Agent different: it evolves.

You chat with your AI
    ↓
AI extracts knowledge from the conversation     ← automatic
    ↓
Knowledge is saved to a local database           ← on your machine
    ↓
Next conversation references that knowledge      ← it remembers
    ↓
Knowledge gradually refines and improves         ← gets better over time

All learning runs on local Ollama models. Zero cost.

Knowledge is organized in three layers: industry → job → workstation — precise context for every role.

🎨 Studio Dashboard

opc studio

Open localhost:4000 in your browser to:

• Models — Switch AI models (local or cloud)
• Channels — Configure Telegram bot
• Knowledge — See what your agent has learned
• Settings — Customize personality, skills, behavior

📖 Model support

Local (zero cost)

Auto-recommended based on your RAM:

RAM	Model	Download
≤3 GB	qwen2.5:0.5b	400MB
≤7 GB	qwen2.5:1.5b	1.0GB
≤15 GB	qwen2.5:7b	4.7GB
≤31 GB	qwen2.5:14b	9.0GB
32+ GB	qwen2.5:32b	19GB

Cloud (optional)

Add API keys in Studio: OpenAI, DeepSeek, Anthropic, Qwen, Google Gemini

Automatic failover with circuit breaker — if one provider goes down, the next one takes over instantly.

📋 Commands

Command	What it does
opc init [name]	Create an AI employee
opc chat	Chat in terminal
opc studio	Open web dashboard
opc run	Start all services
opc brain stats	Knowledge base status
opc brain recall "query"	Search knowledge
opc brain learn file.md	Import a document
opc voice test "hello"	Test voice synthesis
opc mcp list	List connected tools
opc doctor	Diagnose issues
opc init --role <name>	Create from workstation template
opc init --list-roles	See available roles
opc template check <path>	Validate template quality
opc template test <path>	Run template tests

🔒 Privacy

• All data stored locally on your machine
• No telemetry
• Local Ollama models never touch the cloud
• Your knowledge, conversations, and files stay private

🤝 Contributing

git clone https://github.com/Deepleaper/opc-agent.git
cd opc-agent
npm install
npx tsc                    # Build
npx vitest run             # Test

📄 License

Apache-2.0 © Deepleaper

Built by Deepleaper

⭐ Star this repo if it helps you!