How to Add Live Market Data to Your OpenClaw Agent

To add live market data to an OpenClaw agent, get a free SentiSense API key and install the SentiSense skills from ClawHub with one command. From there the agent can screen stocks, read sentiment, pull analyst coverage, check insider and institutional activity, and look up the earnings calendar, from whatever chat app you already talk to it in.

Every SentiSense skill is published on ClawHub under one publisher, versioned, and security-scanned on each release, so the path below is the same one we maintain for our own agents.

What is OpenClaw?

OpenClaw describes itself as a multi-channel gateway for AI agents that runs on any OS. You install it once on a machine you control, and your agent becomes reachable from Discord, Telegram, WhatsApp, Slack, Signal, iMessage, Microsoft Teams, Matrix, Google Chat and a web chat. It keeps running as a daemon, so the agent is there when you message it, not only when a terminal is open.

Skills are markdown instruction files that teach the agent how and when to use a tool. ClawHub is the registry they install from, with a security scan on every published version. That combination is why this guide is short: the skill carries the instructions, ClawHub carries the trust, and you carry a key.

What does an unconnected agent know about markets?

Nothing current. Ask it about a stock and it answers from training data that is months old, or it searches the web and pastes whatever headline came back, in a confident voice. For a question like "which firms moved after the print" that is worse than silence.

A data feed changes the shape of the answer. The agent calls a tool, the tool returns numbers with dates on them, and the agent reads them back. When it says a specific number of covering firms moved in the five sessions after a report, that sentence came out of a response, not a guess.

How do you set it up?

Two minutes, three steps.

1. Get a free API key. Create one at sentisense.ai/get-api-key. No card, and a free key is enough to try everything in this post.

2. Install the skills. The fastest path is the bundle plugin, which installs all nineteen SentiSense skills in one command:

openclaw plugins install clawhub:@sentisenseapp/stock-analysis

Prefer one skill at a time? Each installs on its own. The full API reference, for example:

openclaw skills install @thesentitrader/sentisense

3. Give the skill your key. OpenClaw keeps skill-scoped settings in ~/.openclaw/openclaw.json under skills.entries.<skill-name>. Put the key in that entry's apiKey field (or set SENTISENSE_API_KEY in its env block). Every SentiSense skill reads the same key, so you enter it once.

Then message your agent a market question from the chat app of your choice. That is the whole setup. The onboarding skill in the collection routes the agent to the right skill for whatever you typed, so you do not have to remember names.

What can it actually do?

Every line below is a question the installed skills answer today, given only the question:

• "Who covers NVDA and where does each firm stand?" The covering firms bucketed into Buy, Hold and Sell, with the named analyst on each row.
• "Which firms moved after CRM's print?" Who published in the five sessions that followed, and who has not.
• "Do analysts and the crowd agree on HOOD?" The Street's rating split next to the news and social read on the same name.
• "Screen for large caps with a rising SentiSense Score."
• "Is the insider selling in this name conviction selling or planned 10b5-1 sales?"
• "What is on the earnings calendar next week for my watchlist?"

The feed behind these covers sentiment, analyst, insider, institutional, options and earnings data for roughly a thousand of the most-watched US stocks. It is read-only by design: the agent can look things up, and nothing more. No trading, no orders, no wallet.

The pocket-analyst pattern

OpenClaw's channels are what make this setup different from a terminal agent. The same agent answers you in a Telegram thread on the train, in a Discord server you run with friends, or in WhatsApp at the kitchen table. Give it the feed once and the phone in your pocket has an analyst behind it: a screen before the open, a check on who moved after a print, a look at whether the insider selling in a name is routine before you read the headline about it.

The same skills run in Claude Code, Codex, Cursor and Gemini through skills.sh, so the analyst moves with you if your runtime does. Data is provided for research and education, not investment advice.

Get an API key →