# Long-Running Agent

> An agent designed to keep making progress over many sessions, context windows, or wall-clock hours.

- Category: Agents & Autonomy
- Stage: Emerging
- Also called: Persistent agent, Background agent
- Canonical: https://www.joelcsaji.com/ai-dictionary/long-running-agent

## Plain English

It can leave notes for its future self, resume after interruption, and avoid starting from scratch.

## Example

A research agent checks sources every morning, updates findings, and keeps a running evidence log.

## Why it matters

The next useful agents are less like chat tabs and more like durable workers with memory and accountability.

## Related

- [Agent Harness](https://www.joelcsaji.com/ai-dictionary/agent-harness)
- [Memory](https://www.joelcsaji.com/ai-dictionary/memory)
- [Checkpoint](https://www.joelcsaji.com/ai-dictionary/checkpoint)

## Sources

- [Anthropic: Effective Harnesses](https://www.anthropic.com/engineering/effective-harnesses-for-long-running-agents)
- [LangChain: Long-Term Memory](https://docs.langchain.com/oss/python/deepagents/long-term-memory)