Pixeltable is the unified multimodal backend for AI data apps: the database, orchestration, and serving layers in one Python file. You declare tables, computed columns, and HTTP routes; apply it locally, serve it, then publish the same file to Pixeltable Cloud. Insert a row. Computed columns run. Indexes stay current. No extra vector database, queue, or cache to keep in sync.

Is Pixeltable open source and free?

Yes. Pixeltable is Apache 2.0 licensed and free forever when self-hosted (pip install pixeltable). Declare and run locally, then deploy the same app to Pixeltable Cloud: free Community, $29/mo Pro, or custom Enterprise.

How is Pixeltable different from a vector database or LangChain?

A vector database stores embeddings and LangChain orchestrates calls, but you still wire storage, ETL, and serving yourself. Pixeltable is the database, orchestration, and serving layers in one Python file: computed columns run on insert, indexes stay current, and HTTP comes from the same schema. No extra vector database, queue, or cache to keep in sync.

What data types does Pixeltable support?

Pixeltable natively handles images, video, audio, documents, and structured data, with built-in chunking, frame extraction, embedding, object detection, and LLM inference across 25+ AI providers.

How do AI agents use Pixeltable?

Agents can follow https://pixeltable.com/get-started.md (install pxt, the Pixeltable Skill, and MCP), run `pxt init` then `pxt service example --out app.py`, read /llms.txt, and use MCP to create and maintain multimodal AI data apps across the Declare → Experiment → Serve loop. The /developers page lists OpenAPI, MCP, auth.md, and the pxt CLI.

Where are the public API, OpenAPI, and MCP surfaces?

Onboard at /get-started.md. The OpenAPI spec is /openapi.json (public /ask, /mcp, /health; also /v1/ask, /v1/mcp, /v1/health). The read-only WebMCP server is /mcp and /.well-known/mcp. Discovery catalogs are /.well-known/ard.json and /.well-known/api-catalog. Ask questions at /ask (NLWeb). The Python SDK is the PyPI package pixeltable; the pxt CLI ships with pixeltable[serve]. Human hub: /developers.

Do I need a Pixeltable account to start?

No. Local use is `pip install 'pixeltable[serve]'`, then `pxt init` and `pxt service example --out app.py`. Self-hosting stays Apache 2.0 with no account. Cloud API keys are only for hosted databases and Deploy endpoints after you sign in; Community cloud is free. See /developers for the API, OpenAPI, and MCP hub.

Make Building Multimodal AI Data Apps Dead Simple

The unified multimodal backend for AI data apps in one Python file.

Open in your agent

Cursor Claude ChatGPT

Reading this as an agent? Start at /get-started.md

Declare → Experiment → Serve

Pixeltable is the database, orchestration, and serving layers.

pxt schema update

From the creators of Apache Parquet and Impala.

Insert a row, the rest follows

RAG that stays in sync

class Chunks(TableModel, iterator=document_splitter(Docs.document))

Insert a document. Chunks, embeddings, and answers update. Retrieval is an @pxt.query on that view.

RAG pipeline

Media that processes on insert

class Frames(TableModel, iterator=frame_iterator(video=Videos.video, fps=1))

Insert a video or image. Frames, thumbnails, and captions are the view.

Video frames

Agents you can query later

tool_output = invoke_tools(tools, response)

Insert a message. Tool calls and the answer are assignments, not a loop in memory.

Tool calling

HTTP without writing handlers

api.add_insert_route(Docs, path='/docs', inputs=[Docs.document])

add_insert_route is the insert URL. Keep @router.post for multi-table work or side effects.

Serving

One app.py

No extra blob store, vector database, orchestrator, or glue. The walkthrough is the receipt.

app.py

terminal

Subclass TableModel. Every annotation becomes a stored column.

import pixeltable as pxt

TableModel = pxt.model_base()


class Videos(TableModel, name='videos'):
    video: pxt.Video  # also pxt.Image, pxt.Audio, pxt.Document, pxt.Json
    title: pxt.String

After this step

videos table

videoVideo

titleString

GitHub repo Why AI transformations belong in the schema Deployment patterns

After launch, the same app.py

Only new rows recompute

label = label_scene(detections, Videos.description)

Adding a hundred videos costs a hundred videos of work, not the whole table.

Schema changes ship as a reviewed plan

pxt schema diff app.py my_app

Dropping a column or an index needs --allow-destructive. In CI, a pending change exits 2.

Failed rows stay in the table

pxt errors my_app/frames --col label

The cell is None plus errortype and errormsg. Fix the cause and recompute those rows.

Any version is recoverable

pxt revert my_app/frames --steps 3

pxt history shows what a revert would undo before you run it.

Production operations Version control and lineage Browse media and errors with pxt dashboard

Frequently asked questions

The questions we get first.

What is Pixeltable?: Pixeltable is the unified multimodal backend for AI data apps: the database, orchestration, and serving layers in one Python file. You declare tables, computed columns, and HTTP routes; apply it locally, serve it, then publish the same file to Pixeltable Cloud. Insert a row. Computed columns run. Indexes stay current. No extra vector database, queue, or cache to keep in sync.
Is Pixeltable open source and free?: Yes. Pixeltable is Apache 2.0 licensed and free forever when self-hosted (pip install pixeltable). Declare and run locally, then deploy the same app to Pixeltable Cloud: free Community, $29/mo Pro, or custom Enterprise.
How is Pixeltable different from a vector database or LangChain?: A vector database stores embeddings and LangChain orchestrates calls, but you still wire storage, ETL, and serving yourself. Pixeltable is the database, orchestration, and serving layers in one Python file: computed columns run on insert, indexes stay current, and HTTP comes from the same schema. No extra vector database, queue, or cache to keep in sync.
What data types does Pixeltable support?: Pixeltable natively handles images, video, audio, documents, and structured data, with built-in chunking, frame extraction, embedding, object detection, and LLM inference across 25+ AI providers.
How do AI agents use Pixeltable?: Agents can follow https://pixeltable.com/get-started.md (install pxt, the Pixeltable Skill, and MCP), run `pxt init` then `pxt service example --out app.py`, read /llms.txt, and use MCP to create and maintain multimodal AI data apps across the Declare → Experiment → Serve loop. The /developers page lists OpenAPI, MCP, auth.md, and the pxt CLI.
Where are the public API, OpenAPI, and MCP surfaces?: Onboard at /get-started.md. The OpenAPI spec is /openapi.json (public /ask, /mcp, /health; also /v1/ask, /v1/mcp, /v1/health). The read-only WebMCP server is /mcp and /.well-known/mcp. Discovery catalogs are /.well-known/ard.json and /.well-known/api-catalog. Ask questions at /ask (NLWeb). The Python SDK is the PyPI package pixeltable; the pxt CLI ships with pixeltable[serve]. Human hub: /developers.
Do I need a Pixeltable account to start?: No. Local use is `pip install 'pixeltable[serve]'`, then `pxt init` and `pxt service example --out app.py`. Self-hosting stays Apache 2.0 with no account. Cloud API keys are only for hosted databases and Deploy endpoints after you sign in; Community cloud is free. See /developers for the API, OpenAPI, and MCP hub.

Build and maintain are the same job

The backend is one schema you keep, not a stack you assemble.

10-min quickstart View on GitHub

Video, image, audio, and documents are column types, not paths. See solutions