AI coding agents

Hand the agent get-started.md to install the CLI, the skill, and MCP. After that, follow the Quickstart: generate an example app, create its tables, then start the endpoints. The skill tells the coding agent not to use LangChain, pandas as a database, per-row model loops, or a separate vector database. An application is a Python file that declares tables as TableModel classes. Notebooks can still use pxt.create_table().

Set Up Your AI Tool

npx skills add pixeltable/pixeltable-skill

Works with tools that support Agent Skills: Cursor, Claude Code, Windsurf, Cline, OpenCode, Codex CLI, and others.

Cursor / Windsurf
Claude Code
Any LLM

To install the skill, run npx skills add. Do not copy this repository’s AGENTS.md into an application; that file is for Pixeltable contributors.

Same npx skills add, or the plugin:

/plugin marketplace add pixeltable/pixeltable-skill
/plugin install pixeltable-skill@pixeltable-skill

If your tool has no skill support, append .md to any docs URL and paste that markdown into the chat. Site index: llms.txt (standard). Capability summary: skill.md.

Resource	URL
This page as markdown	building-pixeltable-with-llms.md
Site index	llms.txt
Full map	llms-full.txt
Capability summary	skill.md

What the agent should write

Write an application file, then create its tables with pxt schema update app.py my_app. When you insert a row, computed columns run automatically.

import pixeltable as pxt
import pixeltable.functions as pxtf

TableModel = pxt.model_base()


class Articles(TableModel, name='articles'):
    title: pxt.String
    body: pxt.String
    response = pxtf.openai.chat_completions(
        messages=[{'role': 'user', 'content': body}],
        model='gpt-4o-mini',
    )
    summary = response.choices[0].message.content

pxt schema update app.py my_app

After the schema exists, open the table with t = pxt.get_table('my_app.articles') and insert rows, or serve the same file over HTTP. To run that file on Pixeltable Cloud, pass a pxt://org:db URI instead of my_app: Deploy to Pixeltable Cloud.

Docs search and catalog CLI

Hosted docs MCP for the editor:

https://docs.pixeltable.com/mcp

Catalog inspection without importing Python: pxt ls --json, pxt describe --json, pxt errors. The pxt CLI (v0.7.4+) exposes --json on inspection and query commands. See the CLI. To call remote MCP tools from a table column, use pxt.mcp_udfs(url) (see Agents as tables). Experimental local catalog MCP: mcp-server-pixeltable-developer.

Quickstart

Write app.py, create the tables, then start the endpoints.

Agents as tables

Starter kit

Templates for serving, batch, and FastAPI + React.

Cloud

Deploy the same app.py to a hosted database at pxt://org:db.

Getting started

Tools

How to

Resources

Set Up Your AI Tool

What the agent should write

Docs search and catalog CLI

Next

Quickstart

Agents as tables

Starter kit

Cloud

​Set Up Your AI Tool

​What the agent should write

​Docs search and catalog CLI

​Next

Quickstart

Agents as tables

Starter kit

Cloud

Set Up Your AI Tool

What the agent should write

Docs search and catalog CLI

Next