🪐 Orbis by Memora — Python SDK

The Agentic Browser. Built for Autonomous Intelligence.
🌐 Website: orbis.memora.company • Company: memora.company
⚡ Core Engine: Memora Browser Engine (MBE)

Official Python SDK for Orbis by Memora, the agent-native, ultra-lightweight headless browser engine.

Installation

pip install memora-orbis

Quick Start

from orbis import OrbisAgent  # or: from memora import MemoraAgent

# Connect to running Orbis daemon (started via `npx memora-orbis --port 9222`)
agent = OrbisAgent.connect("http://localhost:9222")

# Navigate and get compact LLM action map (<1000 tokens)
snap = agent.goto("https://example.com")
print(f"Title: {snap.title} | Tokens: ~{snap.token_estimate}")
print(snap.action_map_text)

# Direct interaction via @actionId, Playwright label, or CSS
agent.act("@1")
agent.act("label:Email Address", "agent@memora.company")
agent.act("text=Sign In")

# Check state changes between turns
diff = agent.diff()
print(diff["diff"]["summary"])

# Autonomous self-healing form fill (supports labels, placeholders, @ids, #ids)
agent.fill_form({"label:Username": "agent_007", "placeholder:Password": "secret"}, submit="text=Sign In")

Integration with Browser-Use

from orbis import OrbisAgent
from browser_use import Agent
from langchain_openai import ChatOpenAI

agent = OrbisAgent.connect("http://localhost:9222")

# Browser-Use automatically connects over Orbis's ultra-lightweight CDP
browser_agent = Agent(
    task="Search news for AI agent announcements",
    llm=ChatOpenAI(model="gpt-4o"),
    browser_context_kwargs=agent.to_browser_use()
)

Integration with LangChain

from orbis import OrbisAgent

agent = OrbisAgent.connect("http://localhost:9222")
tools = agent.to_langchain_tools()
# Exported LangChain tools: memora_navigate, memora_act, memora_diff

🏢 About Memora

Memora is an AI organizational memory and knowledge management platform. It connects conversations, code, tickets, documents, and meetings into a shared, verifiable intelligence layer.

Orbis is Memora's official agentic browser engine, giving AI workflows and multi-agent fleets reliable, token-condensed, and stealth-native web execution.

Visit memora.company to learn more.