Skip to content
Conduit

mcp server

langchain

LangChain integration for Ceki — real Chrome sessions for AI agents (TS + Python packages).

Ceki-me/langchaincommunitylistedunreviewed

Set up

Runs on your computer. Pick your agent and operating system.

This project does not publish an install method we can turn into a config. Follow the README instead.

README

synced Oct 23, 2026

Ceki LangChain integrations

LangChain integrations for Ceki — drive a real Chrome browser from your LangChain or LangGraph agent.

This monorepo ships two packages:

PackageLangPathStatus
@ceki/langchain-cekiTypeScript / JSpackages/tsv0.1.0 (pre-publish)
langchain-cekiPythonpackages/pythonv0.1.0 (pre-publish)

Both packages are a thin wrapper over ceki-sdk / @ceki/sdk. They expose Ceki as a toolkit of structural LangChain tools — ceki_rent_browser, ceki_navigate, ceki_click, ceki_type, ceki_scroll, ceki_screenshot, ceki_snapshot, ceki_chat_send, ceki_stop — and let the agent's own LLM plan the sequence. No server-side natural-language endpoint, no LLM inside the wrapper.

Install

# TypeScript / Node
npm install @ceki/langchain-ceki @langchain/core

# Python
pip install langchain-ceki

Use

from langchain_ceki import CekiToolkit

toolkit = CekiToolkit(default_rent={"schedule_id": 4242})
tools = toolkit.get_tools()
# pass `tools` to any LangChain agent (create_tool_calling_agent, ...).
# When the run finishes:
await toolkit.aclose()
import { CekiToolkit } from "@ceki/langchain-ceki";

const toolkit = new CekiToolkit({ defaultRent: { scheduleId: 4242 } });
const tools = await toolkit.getTools();
// pass `tools` to any LangChain agent.
await toolkit.close();

Get an API key at ceki.me.

Use responsibly

Use only on sites you own or have authorization to operate on — your own apps, your own dashboards, public data within site Terms of Service, accessibility audits you're responsible for.

Related

License

MIT.

↑↓ navigate openesc close