OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Data Agents

Timecopilot

Timecopilot is an open-source AI forecasting agent that combines large language models with time-series foundation models to handle forecasting, cross-validation and anomaly detection through a single API.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Timecopilot — OpenViST project profile in Data Agents.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Timecopilot when a time-series workflow needs natural-language interaction, model selection, forecast explanation or a common interface across several foundation models.

Who it is for

  • Developers building forecasting workflows in Python.
  • Analysts working with finance, energy or web-analytics time series.
  • Teams comparing multiple time-series foundation models.
  • Operators who need anomaly-detection workflows for time-series data.

Documented uses

  • Generate forecasts from time-series datasets.
  • Ask natural-language questions about expected future values.
  • Cross-validate and compare supported forecasting models.
  • Detect anomalies in operational or analytical data.
  • Add a forecasting capability to a CLI, server or self-hosted Python workflow.
Before you choose

Requirements & limits

The repository and MIT-licensed source are public. The documented setup requires Python 3.10 or later and an OpenAI API key.

  • The workflow is built around Python and supports CLI, server and self-hosted use.
  • The documented model layer includes Amazon Chronos, Salesforce Moirai, Google TimesFM and Nixtla TimeGPT.
  • Input data for the Python example uses unique_id, ds and y columns.
  • Frequency and seasonality can be inferred from the ds column when not provided.
  • The project notes a current macOS Intel limitation and a Python 3.10 recommendation for Windows.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up Timecopilot for a first forecast

Install the package, configure an OpenAI API key and prepare the documented command-line forecasting workflow.

Before you start

  • Python 3.10 or later.
  • An OpenAI account and API key.
  • The uvx tool for the documented one-command quickstart.
  • A public time-series dataset URL for the command-line example.

Steps

  1. Install Timecopilot with pip install timecopilot or uv add timecopilot.

  2. Create an OpenAI API key and export it as OPENAI_API_KEY in the environment.

  3. Run the documented forecast command with a public CSV dataset URL.

  4. Add an LLM selection or natural-language query when the documented command requires it.

Expected outcome

A configured command-line forecasting workflow that can request a forecast from a public time-series dataset.

Guide limitations

  • The documented quickstart uses an OpenAI API key.
  • The project requires Python 3.10 or later.
  • The project notes that macOS on Intel processors is currently unsupported and recommends Python 3.10 on Windows.
  • This setup recipe documents the provided quickstart rather than independently verifying execution.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
4 October 2026
Original website title
TimeCopilot/timecopilot · Official homepage title · retained in its source language
How we review sourcesSuggest a correction