The backend your coding agent stops rebuilding

Q: Do I need an account to start?

No. Locally the agent runs pxt init, pxt schema update, and pxt service update with no account. For a hosted database, pxt new makes one with no account; claim it within 48 hours to keep it.

Q: Which coding agents does it work with?

Any agent that loads skills: npx skills add pixeltable/pixeltable-skill installs it for Claude Code, Cursor, Codex, GitHub Copilot, Windsurf, Gemini CLI, OpenCode, and Devin. Each has a setup guide on this page.

Media, models, embeddings, and routes are one Python file. Claude Code, Cursor, and Codex reach a working app with less code, less glue, and fewer wrong turns.

npx skills add pixeltable/pixeltable-skill

Get a free database

Or let the agent run pxt new: one hosted database, no account. Claim it within 48 hours.

Setup guides and 4 more

Same app, two backends

Six wrong turns, numbered on a real Celery task. Switch to the Pixeltable file for the same product.

worker/tasks/process_call.py

1@celery_app.task(name="worker.tasks.process_call", ...)
def process_call(call_id: str) -> None:
    db = SessionLocal()
    try:
        call = db.get(Call, uuid.UUID(call_id))
        call.status = "transcribing"
        db.commit()

2        diarized = transcribe_diarize(call.audio_path)
        labeled = extract_segments(diarized)
3        for pos, seg in enumerate(labeled):
            db.add(TranscriptSegment(call_id=call.id, pos=pos, ...))

        client = OllamaClient()
4        result = client.enrich_call(transcript_text, ...)
        call.summary = result.summary
        # ... action items, sentiment, category, QA scorecard

5        embed_call_segments(db, call.id)
        call.status = "completed"
        db.commit()
    except Exception as exc:
        db.rollback()
        call.status = "failed"
6        call.error_message = str(exc)

1class Calls(TableModel, name="calls"):
    uuid = pxt.Column(type=pxt.UUID, primary_key=True)
2    audio: pxt.Audio | None
    video: pxt.Video | None
    vertical: pxt.String | None
    # ...
    diarized = pxt.Column(value=transcribe(audio=source_audio, ...))
    segments = functions.extract_segments(diarized)
    transcript_text = functions.flatten_transcript_segments(segments)

4    summary_raw = chat(model=config.OLLAMA_MODEL, ...)["message"]["content"]
    summary = functions.parse_summary_content(transcript_text, summary_raw)
    # ... action items, sentiment, category, QA scorecard


class TranscriptSegments(
    TableModel,
    name="transcript_segments",
    base=Calls.where(Calls.segments != None),
3    iterator=list_iterator(Calls.segments),
):
    __indexes__ = [
5        pxt.EmbeddingIndex(text, embedding=embed_fn, name="segments_embed")
    ]

Six wrong turns in one task

Lines in the pipeline

668 · Celery stack

392 · Pixeltable

Files in the pipeline

14 · Celery stack

2 · Pixeltable

The same call-search product on two backends, from pixeltable/showcase-call-intelligence. Code abridged: ... marks what was cut. Counts are its pipeline code, measured on main.

Six habits the skill replaces

Each is a system the agent would build and you would keep running. The skill names the habit and the line that replaces it.

A framework for chunking and retrieval
RecursiveCharacterTextSplitter + Chroma + RetrievalQA
document_splitter
Chunking is a view. Search is .similarity(). Tools are pxt.tools() and invoke_tools().
pandas as the working store
df['summary'] = df['text'].apply(call_openai)
summary = chat_completions(...)
The table is the store. .collect().to_pandas() is for export.
A for-loop calling a model
for row in df.iterrows(): client.chat.completions.create(...)
t.recompute_columns('summary', errors_only=True)
The call is an assignment on the model. Retries rerun only the rows that failed.
A second vector database
index.upsert(ids, vectors)
__indexes__ = [pxt.EmbeddingIndex(...)]
The index lives on the column. Search with .similarity(string=query).
A while-loop agent
while True: ...
invoke_tools(tools, response)
Insert a row. The model call, the tool calls, and the answer are columns that keep their state.
A model loaded on every row
whisper.load_model('tiny.en')
pxtf.whisper.transcribe(audio, model='tiny.en')
The shipped wrappers cache the weights per process, so they load once.

And the small ones

python app.py: pxt schema update, then pxt service update
Drop and recreate tables to reset: Edit app.py, then pxt schema update
Chat history in Redis: A table
A hard-coded api_key=: The environment or config.toml

Every one, with the right code, in the skill

Skill, backend, Cloud

The agent installs the skill, applies one file, and ships the same file hosted. Start free at every step.

1Skill
The agent pulls Pixeltable in.
One install teaches it tables, computed columns, indexes, and routes, and replaces the six habits above.
Any agent
npx skills add pixeltable/pixeltable-skill
Claude Code: add
/plugin marketplace add pixeltable/pixeltable-skill
Claude Code: install
/plugin install pixeltable@pixeltable-skill
Your agent’s setup
Setup guides
What it teaches
Agent Skill
2Backend
One file is the app’s state.
Tables, computed columns, an embedding index, and routes live in app.py. Insert runs the models. Failures, versions, and recomputes stay in the tables, not in a chat scratchpad.
Mark the project root
pxt init
Create the tables
pxt schema update app.py my_app -f
Serve HTTP
pxt service update app.py my_app -f
Read failures
pxt errors my_app/docs
The file, line by line
Backend for AI agents
3Cloud
The same file, hosted.
Start free: pxt new makes one hosted database with no account and prints its URI; claim it within 48 hours. The next three commands apply the same file to that URI. Community is free; Pro is the paid step.
Free database
pxt new
Provision it
pxt db update pxt://trial-x7k2:main -f
Create the tables
pxt schema update app.py pxt://trial-x7k2:main -f
Serve HTTP
pxt service update app.py pxt://trial-x7k2:main -f
What you get free
Free database
Plans
Pricing

Setup guides for your agent

Install steps, MCP configuration, and prompts for each agent.

DevinCognition
Autonomous AI software engineer. Plans, codes, debugs, and deploys independently.
Claude CodeAnthropic
Agentic coding in your terminal. Understands your codebase, runs commands, and edits files.
CursorAnysphere
The AI-first IDE. Agent mode edits across files, runs commands, and iterates on errors.
CodexOpenAI
OpenAI's coding agent for the terminal and cloud. Reads and writes files, executes commands.
GitHub CopilotGitHub
AI pair programmer with agent mode. The workspace agent understands your entire project.
WindsurfCodeium
The agentic IDE. Cascade flows through multi-step coding tasks.
Gemini CLIGoogle
Google's open-source terminal agent powered by Gemini.
OpenCodeSST
Open-source, provider-agnostic coding agent for the terminal.

Agents read the same pages as markdown: add .md to any guide, or start at get-started.md, llms.txt, or agent.json.

Questions

What does the Pixeltable skill change for a coding agent?

It teaches the agent to declare tables, computed columns, an embedding index, and routes in one app.py, and it replaces six habits: a retrieval framework, pandas as the store, model calls in a loop, a second vector database, a while-loop agent, and a model loaded on every row.

Do I need an account to start?

No. Locally the agent runs pxt init, pxt schema update, and pxt service update with no account. For a hosted database, pxt new makes one with no account; claim it within 48 hours to keep it.

Which coding agents does it work with?

Any agent that loads skills: npx skills add pixeltable/pixeltable-skill installs it for Claude Code, Cursor, Codex, GitHub Copilot, Windsurf, Gemini CLI, OpenCode, and Devin. Each has a setup guide on this page.

What does Pixeltable Cloud cost?

Local Pixeltable is free and open source. On Cloud, Community is free and Pro is the paid plan; see the pricing page for what each includes.

Give your agent the backend before it builds one

One command for a hosted database with no account: pxt new. Or install the skill and start locally.

Get a free database Read get-started.md

The backend your coding agent stops rebuilding

Same app, two backends

Six habits the skill replaces

A framework for chunking and retrieval

pandas as the working store

A for-loop calling a model

A second vector database

A while-loop agent

A model loaded on every row

And the small ones

Skill, backend, Cloud

1Skill

2Backend

3Cloud