Skip to main content

Local-first AI Agent for Mac. Zero cloud dependency.

Project description

🤖 OPC Agent

Your 100% Local AI Agent — Zero Cloud, Zero Cost, Total Privacy

纯本地 AI Agent — 零云依赖、零成本、完全隐私

PyPI version Downloads GitHub stars License Python

Website · Quick Start · Docs · vs Leaper Agent


✨ Why OPC Agent? / 为什么选 OPC Agent?

OPC Agent is a fully local AI agent powered by Ollama. No API keys, no cloud, no subscriptions. Your data never leaves your machine — and the agent gets smarter over time with built-in DeepBrain memory.

  • 🔒 100% Local — Runs entirely on your Mac, PC, or Linux. No internet required after setup.
  • 💰 Zero Cost — No API fees, no subscriptions. Just your hardware.
  • 🧠 Self-Learning Memory — Built-in DeepBrain 6-layer memory. Your agent remembers and evolves.
  • 🛡️ Privacy First — Your conversations, your data, your machine. Period.
  • Simple Setuppip install + ollama pull = ready to go.

🚀 Quick Start

Prerequisites

  • Python 3.10+
  • Ollama installed and running

Install & Run

# 1. Install OPC Agent
pip install opc-agent

# 2. Pull a model via Ollama
ollama pull llama3.1

# 3. Initialize
opc-agent init

# 4. Start chatting!
opc-agent chat

That's it. No API keys. No config files. No cloud accounts. 就这么简单。

🧠 Built-in DeepBrain Memory

OPC Agent includes DeepBrain — a 6-layer self-evolving knowledge engine:

⚡ Flash → 📝 Short-Term → 📚 Long-Term → 🏗️ Consolidated → 🗄️ Archived → 🔮 Meta

Your agent automatically:

  • Remembers key facts from conversations
  • Consolidates patterns across sessions
  • Promotes validated knowledge to long-term storage
  • Evolves its understanding over time

All stored in a local SQLite database. No cloud sync. No data leakage.

📖 Usage

# Interactive chat
opc-agent chat

# Chat with a specific model
opc-agent chat --model mistral

# View memory stats
opc-agent brain stats

# Search agent memory
opc-agent brain search "project deadlines"

# Reset memory (careful!)
opc-agent brain reset

Configuration

# Config location
~/.opc-agent/config.yaml
model: llama3.1
memory:
  enabled: true
  db_path: ~/.opc-agent/brain.db
  auto_learn: true

⚖️ OPC Agent vs Leaper Agent

OPC Agent Leaper Agent
LLM Ollama (local models) OpenAI / Claude / Gemini
Internet Required No Yes (API calls)
Cost $0 Pay-per-token
Privacy ⭐⭐⭐⭐⭐ ⭐⭐⭐
Model Quality Good (local models) Best (GPT-4, Claude 3.5)
Multi-Agent
Telegram Bot
Best For Privacy, offline, zero-cost Power users, teams, integrations

Want cloud models? → Check out Leaper Agent 在中国? → Check out Leaper Agent CN

🖥️ Supported Platforms

Platform Status
macOS (Apple Silicon) ✅ Recommended
macOS (Intel)
Linux (x86_64)
Windows 10/11

📄 License

BSL-1.1 — see LICENSE for details.

🤝 Contributing

We welcome contributions! See CONTRIBUTING.md.

📧 Questions? tech@deepleaper.com


Built with ❤️ by Deepleaper Technology / 跃盟科技

Local AI that remembers. Private AI that evolves.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

opc_agent-0.3.1.tar.gz (176.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

opc_agent-0.3.1-py3-none-any.whl (177.6 kB view details)

Uploaded Python 3

File details

Details for the file opc_agent-0.3.1.tar.gz.

File metadata

  • Download URL: opc_agent-0.3.1.tar.gz
  • Upload date:
  • Size: 176.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.10

File hashes

Hashes for opc_agent-0.3.1.tar.gz
Algorithm Hash digest
SHA256 9fea4a12c328feeb2ab2b1abb7c465d82d725de77548eee58729d20e73d34de0
MD5 6eb488416397124ab8f6fd9168dc4605
BLAKE2b-256 33009b7ade0e0b947beb54de9cee1bfee8c1fcb57e361e71d7d24244a5649e19

See more details on using hashes here.

File details

Details for the file opc_agent-0.3.1-py3-none-any.whl.

File metadata

  • Download URL: opc_agent-0.3.1-py3-none-any.whl
  • Upload date:
  • Size: 177.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.10

File hashes

Hashes for opc_agent-0.3.1-py3-none-any.whl
Algorithm Hash digest
SHA256 d52169575bc4bcfc7582fc711e5974f389f639657ba2cb32a2741e2a8d453f4b
MD5 4052838607e301c495c13dfc038eed59
BLAKE2b-256 4ca416fa6bff058d2ac66b5c321268ed72e4b4d6ccc92effaa83ad4befc8e86c

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page