Skip to main content

How AI Agent Memory Works in nanoinfra

This guide explains how to use nanoinfra's long-term AI agent memory: session history, compressed archives, durable memory files, Dream consolidation, and Git-backed memory changes.

What you will build​

  • a workspace with persistent session history
  • compressed history archives for older turns
  • durable memory files such as USER.md and MEMORY.md
  • a Dream workflow for curating long-term memory

When to use this​

Use memory when an agent should remember stable preferences, project facts, decisions, and recurring context across sessions. Do not use memory as a dumping ground for every raw transcript. nanoinfra separates short-term messages from curated durable knowledge.

Install​

Quick Start ranks four install methods easiest first. This is the first of them. Use pip, Docker or a source checkout instead if you prefer, and come back here.

uv tool install nanoinfra
nanoinfra onboard --wizard
nanoinfra agent -m "Hello!"

Minimal working example​

Ask the agent to remember a stable fact in a normal session, then run Dream:

/dream

Inspect recent memory changes:

/dream-log

The exact files live in the active workspace, usually under ~/.nanoinfra/workspaces/default/.

Production notes​

  • Use one workspace per project or personal context.
  • Keep durable facts concise. Old session details belong in history.jsonl.
  • Use /dream-prompt init when a workspace needs custom memory guidance.
  • Review Git-backed memory changes when memory affects important workflows.

Security notes​

  • Memory files may contain sensitive user or project facts.
  • Avoid sharing workspaces without reviewing SOUL.md, USER.md, and memory/MEMORY.md.
  • Use separate workspaces for personal and team contexts.

Troubleshooting​

  • If memory feels stale, run /dream and inspect /dream-log.
  • If memory changed incorrectly, use /dream-restore to inspect and restore previous versions.
  • If a new session lacks context, confirm it uses the same workspace.