# TimeCopilot

## TL;DR

TimeCopilot is an open-source, unified framework that integrates multiple time series models with large language models to automate and explain forecasting tasks, achieving state-of-the-art results.

## Contribution

It introduces the first open-source agentic framework combining TSFMs and LLMs with a unified API for automated, explainable forecasting.

## Key findings

- Achieves state-of-the-art probabilistic forecasting on GIFT-Eval
- Supports ensembles across diverse forecasting models
- Provides natural language explanations and query capabilities

## Abstract

We introduce TimeCopilot, the first open-source agentic framework for forecasting that combines multiple Time Series Foundation Models (TSFMs) with Large Language Models (LLMs) through a single unified API. TimeCopilot automates the forecasting pipeline: feature analysis, model selection, cross-validation, and forecast generation, while providing natural language explanations and supporting direct queries about the future. The framework is LLM-agnostic, compatible with both commercial and open-source models, and supports ensembles across diverse forecasting families. Results on the large-scale GIFT-Eval benchmark show that TimeCopilot achieves state-of-the-art probabilistic forecasting performance at low cost. Our framework provides a practical foundation for reproducible, explainable, and accessible agentic forecasting systems.