Skip to main content

Orbis Logo 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

Prompt Injection Firewall (domain rules)

Start the daemon with firewall domain rules; refused navigations raise FirewallBlockedError:

npx memora-orbis --port 9222 --block-sensitive-domains --allow-domain docs.example.com
from orbis import OrbisAgent, FirewallBlockedError

agent = OrbisAgent("http://localhost:9222")
try:
    agent.goto("https://mail.google.com/")
except FirewallBlockedError as e:
    print(e.rule, e.blocked_url)   # domain:sensitive:email https://mail.google.com/

Action gates and content isolation run in the MCP server and the TypeScript SDK; see PROMPT_INJECTION_FIREWALL.md in the main package.

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.

Metadata

Release files for memora-orbis 0.2.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for memora-orbis 0.2.0
File Size Uploaded Provenance Actions
memora_orbis-0.2.0.tar.gz 7.8 kB Without provenance Details for memora_orbis-0.2.0.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for memora-orbis 0.2.0
File Interpreter ABI Platform Actions
memora_orbis-0.2.0-py3-none-any.whl Python 3 none any Details for memora_orbis-0.2.0-py3-none-any.whl

Total release size: 16.2 kB

Release files / memora_orbis-0.2.0.tar.gz

Download URL memora_orbis-0.2.0.tar.gz
Size 7.8 kB
Tags Source
SHA-256 checksum
How to use checksums
9221824ec926c8d536e95e39999c3e78298aa94d1eb4e2fdf584e075f97c969f
BLAKE2b-256 checksum
How to use checksums
fb8f29316d98fcd1812eefdaeaf55f5ea919448f4aec7f1ad82a1cc2bb320907
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.14.4

Release files / memora_orbis-0.2.0-py3-none-any.whl

Download URL memora_orbis-0.2.0-py3-none-any.whl
Size 8.4 kB
Tags Python 3
SHA-256 checksum
How to use checksums
8b9dab65d533d8be1a4651a989c1fd526b7bbc38fea12bcc79596df4947db00a
BLAKE2b-256 checksum
How to use checksums
7f9e2ea5b82e3ad3b682af7590894c17a4cb363698dbfde2aea59e1b0c254e9a
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.14.4

Security for memora-orbis 0.2.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page