Agent Frameworks

If you’ve been building AI agents with LangGraph or CrewAI — defining state graphs, tool nodes, conditional edges, and bolting on separate memory stores — this guide shows how Pixeltable replaces the graph DSL with declarative tables.

Related use case: Agents & MCP

Concept Mapping

Agent Framework	Pixeltable Equivalent
`StateGraph` / `AgentExecutor`	`pxt.create_table()` with computed columns
Graph nodes (functions)	Computed columns — dependencies resolved automatically
Graph edges / conditional routing	Column references — Pixeltable infers the DAG
`ToolNode` / `@tool`	`pxt.tools()` + `invoke_tools()`
`MemorySaver` / checkpointer	Tables are persistent by default
Separate vector DB for RAG	`add_embedding_index()` + `@pxt.query`
LangSmith for observability	`t.select()` on any column — every step is queryable

Side by Side: Tool-Calling Agent

An agent that picks tools, calls them, and answers based on the results.

LangGraph
Pixeltable

from typing import Annotated, Sequence, TypedDict
from langchain_core.messages import BaseMessage, HumanMessage
from langchain_openai import ChatOpenAI
from langgraph.graph import StateGraph, END, add_messages
from langgraph.prebuilt import ToolNode
from langchain_core.tools import tool

class AgentState(TypedDict):
    messages: Annotated[Sequence[BaseMessage], add_messages]

@tool
def get_weather(city: str) -> str:
    """Get current weather for a city."""
    return f'Weather in {city}: 72°F, sunny'

@tool
def search_docs(query: str) -> str:
    """Search internal documents."""
    return f'Results for: {query}'

tools = [get_weather, search_docs]
model = ChatOpenAI(model='gpt-4o-mini').bind_tools(tools)

def call_model(state):
    return {'messages': [model.invoke(state['messages'])]}

def should_continue(state):
    last = state['messages'][-1]
    return 'tools' if last.tool_calls else END

workflow = StateGraph(AgentState)
workflow.add_node('agent', call_model)
workflow.add_node('tools', ToolNode(tools))
workflow.set_entry_point('agent')
workflow.add_conditional_edges(
    'agent', should_continue, {'tools': 'tools', END: END})
workflow.add_edge('tools', 'agent')
graph = workflow.compile()

result = graph.invoke(
    {'messages': [HumanMessage(content='Weather in SF?')]})
print(result['messages'][-1].content)

Packages: langgraph, langchain-openai, langchain-core, plus a vector DB client for RAG

import pixeltable as pxt
from pixeltable.functions.openai import chat_completions, invoke_tools

@pxt.udf
def get_weather(city: str) -> str:
    """Get current weather for a city."""
    return f'Weather in {city}: 72°F, sunny'

@pxt.udf
def search_docs(query: str) -> str:
    """Search internal documents."""
    return f'Results for: {query}'

tools = pxt.tools(get_weather, search_docs)

agent = pxt.create_table('agents.assistant', {'message': pxt.String})

agent.add_computed_column(response=chat_completions(
    messages=[{'role': 'user', 'content': agent.message}],
    model='gpt-4o-mini', tools=tools))
agent.add_computed_column(
    tool_output=invoke_tools(tools, agent.response))

@pxt.udf
def build_followup(message: str, tool_output: dict) -> list[dict]:
    results = [
        str(r) for vals in (tool_output or {}).values()
        if vals for r in vals
    ]
    return [
        {'role': 'user', 'content': message},
        {'role': 'assistant', 'content': '\n'.join(results)},
        {'role': 'user', 'content':
            'Answer my original question using that information.'},
    ]

agent.add_computed_column(
    followup=build_followup(agent.message, agent.tool_output))
agent.add_computed_column(
    final=chat_completions(messages=agent.followup, model='gpt-4o-mini'))
agent.add_computed_column(
    answer=agent.final.choices[0].message.content)

agent.insert([{'message': 'What is the weather in SF?'}])
agent.select(agent.message, agent.answer).collect()

Packages: pixeltable, openai

What Changes

	LangGraph / CrewAI	Pixeltable
State	Ephemeral — lost when the process ends	Persistent — every row survives restarts
Caching	No built-in caching of tool results	Same input returns cached result
Observability	LangSmith (separate service + API key)	`agent.select(agent.tool_output).collect()`
Adding RAG	Separate vector DB integration	`add_embedding_index()` + `@pxt.query` — no extra service
Graph definition	Nodes, edges, conditional routing DSL	Computed columns — Pixeltable infers the DAG
MCP tools	Custom integration	`pxt.mcp_udfs()` loads tools from any MCP server

Common Patterns

Adding persistent memory

LangGraph
Pixeltable

from langgraph.checkpoint.memory import MemorySaver

checkpointer = MemorySaver()
graph = workflow.compile(checkpointer=checkpointer)
# In-process only — lost on restart

from pixeltable.functions.openai import embeddings

memories = pxt.create_table('agents.memories', {
    'content': pxt.String, 'timestamp': pxt.Timestamp})
memories.add_embedding_index('content',
    string_embed=embeddings.using(model='text-embedding-3-small'))

@pxt.query
def recall(query: str, top_k: int = 5) -> pxt.Query:
    sim = memories.content.similarity(string=query)
    return memories.order_by(sim, asc=False) \
        .limit(top_k).select(memories.content)

Adding RAG to an agent

LangGraph
Pixeltable

from langchain_pinecone import PineconeVectorStore

vector_store = PineconeVectorStore(
    index_name='docs', embedding=embeddings)

@tool
def search_kb(query: str) -> str:
    """Search the knowledge base."""
    docs = vector_store.as_retriever() \
        .get_relevant_documents(query)
    return '\n'.join(d.page_content for d in docs)
# Must add tool to graph, re-compile...

@pxt.query
def search_kb(query: str) -> pxt.Query:
    """Search the knowledge base."""
    sim = chunks.text.similarity(string=query)
    return chunks.order_by(sim, asc=False) \
        .limit(5).select(chunks.text)

tools = pxt.tools(get_weather, search_kb)

Inspecting agent behavior

LangGraph
Pixeltable

# Requires LangSmith: set LANGSMITH_API_KEY,
# LANGSMITH_PROJECT, then view traces in dashboard

agent.select(
    agent.message,
    agent.tool_output,
    agent.answer
).collect()

Welcome to Pixeltable

Core Concepts

How-To

Concept Mapping

Side by Side: Tool-Calling Agent

What Changes

Common Patterns

Adding persistent memory

Adding RAG to an agent

Inspecting agent behavior

Next Steps

Agents & MCP

Agentic Patterns

Tool Calling

Pixelagent

Welcome to Pixeltable

Core Concepts

How-To

​Concept Mapping

​Side by Side: Tool-Calling Agent

​What Changes

​Common Patterns

​Adding persistent memory

​Adding RAG to an agent

​Inspecting agent behavior

​Next Steps

Agents & MCP

Agentic Patterns

Tool Calling

Pixelagent

Concept Mapping

Side by Side: Tool-Calling Agent

What Changes

Common Patterns

Adding persistent memory

Adding RAG to an agent

Inspecting agent behavior

Next Steps