> ## Documentation Index
> Fetch the complete documentation index at: https://docs.pixeltable.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Building with LLMs
> Use AI coding tools to build Pixeltable applications faster
## Why Pixeltable Is Easy to Vibe-Code
Pixeltable's API is declarative: you say *what* you want, not *how* to wire it up. That means LLMs get it right on the first try. Ask your AI tool to "summarize articles with GPT-4o-mini" and you get working code:
```python theme={"theme":{"light":"light-plus","dark":"dark-plus"}}
import pixeltable as pxt
from pixeltable.functions.openai import chat_completions
t = pxt.create_table('app.articles', {'title': pxt.String, 'body': pxt.String})
t.add_computed_column(response=chat_completions(
messages=[{'role': 'user', 'content': t.body}], model='gpt-4o-mini'))
t.add_computed_column(summary=t.response.choices[0].message.content)
t.insert([{'title': 'Climate Report', 'body': 'Global temperatures rose 1.2°C ...'}])
t.select(t.title, t.summary).collect()
```
Ten lines of code, and the result is **persistent**, **versioned**, **traceable**, and **incrementally optimized**. Every output is stored, every transformation is replayable, and new rows only recompute what changed. The same pattern scales to [RAG pipelines](/howto/cookbooks/agents/pattern-rag-pipeline), [video frame extraction](/howto/cookbooks/video/video-extract-frames), [tool-calling agents](/howto/cookbooks/agents/llm-tool-calling), and [semantic search](/howto/cookbooks/search/search-semantic-text).
***
## Set Up Your AI Tool
Pick the setup that matches your editor. These aren't mutually exclusive; use whichever combination helps.
### Agent Skill (recommended, works everywhere)
The [Pixeltable Agent Skill](https://github.com/pixeltable/pixeltable-skill) teaches AI coding assistants to write correct Pixeltable code on the first attempt. It provides anti-pattern deflection (no LangChain, no pandas-as-store, no for-loops calling AI), correct patterns for 25+ providers, and production recipes for agents, RAG, and multimodal pipelines.
```bash theme={"theme":{"light":"light-plus","dark":"dark-plus"}}
npx skills add pixeltable/pixeltable-skill
```
Works with any tool that supports the [Agent Skills specification](https://agentskills.io/specification): Cursor, Claude Code, Windsurf, Cline, OpenCode, Codex CLI, and 40+ more.
The `npx skills add` command above is the recommended setup. It installs the full skill with anti-pattern deflection, provider coverage, and progressive reference loading.
Alternatively, drop our [AGENTS.md](https://github.com/pixeltable/pixeltable/blob/main/AGENTS.md) into your project root for contributor-focused context:
```bash theme={"theme":{"light":"light-plus","dark":"dark-plus"}}
curl -o AGENTS.md https://raw.githubusercontent.com/pixeltable/pixeltable/main/AGENTS.md
```
The `npx skills add` command works with Claude Code. You can also install as a Claude Code plugin for auto-updates:
```bash theme={"theme":{"light":"light-plus","dark":"dark-plus"}}
/plugin marketplace add pixeltable/pixeltable-skill
/plugin install pixeltable-skill@pixeltable-skill
```
The skill loads a concise `SKILL.md` first (\~480 lines), then pulls in reference files on demand only when the task requires them.
Append `.md` to any docs URL to get a plain-text version optimized for LLMs. Paste it straight into your chat.
| Resource | URL |
| --------------------------- | --------------------------------------------------------------------------------------------------------------------------------- |
| Any docs page as markdown | `https://docs.pixeltable.com/.md`, e.g., [this page](https://docs.pixeltable.com/overview/building-pixeltable-with-llms.md) |
| Site index for LLMs | [llms.txt](https://docs.pixeltable.com/llms.txt) ([standard](https://llmstxt.org/)) |
| Full site map with metadata | [llms-full.txt](https://docs.pixeltable.com/llms-full.txt) |
***
## MCP Servers
Connect your AI tool to Pixeltable directly via the [Model Context Protocol](https://modelcontextprotocol.io). We ship two servers, or you can build your own using [`pxt.mcp_udfs()`](/libraries/mcp).
Search the full documentation from Claude Desktop, Cursor, or Windsurf:
```
https://docs.pixeltable.com/mcp
```
Exposes a `SearchPixeltableDocumentation` tool that returns relevant content, code examples, and direct links.
32 tools for creating tables, running queries, managing dependencies, and executing Python, all from your AI editor. Experimental; great for prototyping.
```bash theme={"theme":{"light":"light-plus","dark":"dark-plus"}}
# Install
uv tool install --from git+https://github.com/pixeltable/mcp-server-pixeltable-developer.git mcp-server-pixeltable-developer
# Add to Claude Code
claude mcp add pixeltable mcp-server-pixeltable-developer
```
See [configuration for Cursor, Claude Desktop, and more](https://github.com/pixeltable/mcp-server-pixeltable-developer) in the repo README.
The `pxt` CLI (v0.6.5+) exposes the same catalog with `--json` on every inspection and query command, plus `pxt shell` for multi-command sessions. Agents can inspect tables, count rows, and debug computed-column failures without importing Python.
See the [Working with the Pixeltable CLI](/howto/cookbooks/core/working-with-cli) cookbook.
Any Pixeltable UDF or query function can be exposed as an MCP tool with a single call:
```python theme={"theme":{"light":"light-plus","dark":"dark-plus"}}
import pixeltable as pxt
@pxt.udf
def lookup_customer(name: str) -> str:
"""Look up customer info by name."""
t = pxt.get_table('app.customers')
return t.where(t.name == name).select(t.info).collect()[0]['info']
tools = pxt.tools(lookup_customer)
```
`pxt.tools()` wraps your functions so any MCP-compatible client can call them. See the [MCP integration guide](/libraries/mcp) for the full setup.
***
## Start Building
Scaffold a full project in one command with `pixeltable-new`. It generates a working Pixeltable project (serving, backend, or batch) with schema, configuration, and deployment configs already wired up. Ask your AI tool to customize it from there.
```bash theme={"theme":{"light":"light-plus","dark":"dark-plus"}}
uvx pixeltable-new myapp # declarative serving (default)
uvx pixeltable-new myapp --backend # full FastAPI + React app
uvx pixeltable-new myapp --template knowledge-base my-kb # vertical template
```
Reference implementations for all three deployment patterns, plus 7 vertical application templates
***
## Next Steps
Install and run your first pipeline in 5 minutes
The core pattern LLMs generate. Learn how it works
Build agents with UDFs, queries, and MCP tools
Full use case walkthrough for AI agents