> ## Documentation Index
> Fetch the complete documentation index at: https://docs.twill.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Memory

> How Twill agents remember what they learn about your connected repos across tasks

## How It Works

When you ask the agent to remember something, it saves that learning to a project-level file (`CLAUDE.md` or `AGENTS.md`) in the relevant repo, so it persists across tasks. Each connected repo has its own memory file.

Every agent reads these files at the start of a task. Learnings from previous tasks are available immediately, with no extra configuration needed.

## What Gets Remembered

You decide what's worth saving. Typical examples:

* Build and test commands
* Framework and language conventions
* File layout and architecture patterns
* Past mistakes and what fixed them

Only non-obvious learnings that aren't already documented are saved.

## Availability

| Agent       | Memory support |
| ----------- | -------------- |
| Claude Code | Supported      |
| Codex       | Supported      |
| OpenCode    | Supported      |

Memory is portable across agents: knowledge written by one CLI is readable by the others, so switching agents on the same workspace doesn't lose context.