Auto Memory logo

Auto Memory

CommunityPopular
tractorjuice
auto-memory

This skill should be used when the user asks to 'set up memory', 'create memory files', 'create MEMORY.md', 'set up topic files', 'improve memory organization', 'what should I remember', 'how to structure memory files', 'MEMORY.md is too long', 'what goes in memory vs topic files', 'memory best practices', or wants to establish a persistent knowledge base across Claude Code sessions. Triggers on: memory setup, MEMORY.md, topic files, cross-session knowledge, persistent notes, memory maintenance, memory pruning.

Overview

Publishertractorjuice
Repositoryarc-kit
Skill nameauto-memory
Stars
2.3K
Forks
282
Bundled files
3
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by tractorjuice on GitHub. Read the source before you install it.

Installation

Install the Auto Memory AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/tractorjuice/arc-kit/tree/main/.claude/skills/auto-memory
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/tractorjuice/arc-kit.git /tmp/arc-kit
mkdir -p .claude/skills
cp -r /tmp/arc-kit/.claude/skills/auto-memory .claude/skills/auto-memory
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Auto Memory in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Auto Memory on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Auto Memory is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Auto Memory Management

Use persistent auto memory to retain project knowledge across Claude Code sessions. The memory directory (~/.claude/projects/<path>/memory/) stores a concise index file (MEMORY.md) and detailed topic files, creating a structured knowledge base that grows with the project.

Core Architecture

text
~/.claude/projects/<project-path>/memory/
├── MEMORY.md          # Always loaded into system prompt (~200 lines max)
├── architecture.md    # Topic file: system architecture decisions
├── patterns.md        # Topic file: code patterns and conventions
├── debugging.md       # Topic file: debugging insights
├── workflows.md       # Topic file: development workflows
└── known-issues.md    # Topic file: bug tracking

Two-Tier Design

  1. MEMORY.md (always in context): Concise index with key facts, quick reference tables, and links to topic files. Lines after 200 are truncated — keep it tight.
  2. Topic files (consulted as needed): Detailed reference organized by domain. No size limit, but keep each file focused on one topic.

What to Save

Save These

  • Stable patterns confirmed across multiple interactions (naming conventions, file organization, coding style)
  • Architectural decisions and their rationale
  • Important file paths and project structure
  • User preferences for workflow, tools, and communication style
  • Solutions to recurring problems and debugging insights
  • Critical gotchas that cause repeated mistakes
  • Explicit user requests ("always use bun", "never auto-commit") — save immediately, no need to wait for confirmation across sessions

Do NOT Save

  • Session-specific context (current task details, in-progress work, temporary state)
  • Unverified information — verify against project docs before writing
  • Duplicates of CLAUDE.md — memory supplements project instructions, never contradicts them
  • Speculative conclusions from reading a single file
  • Rapidly changing values (exact line numbers, temporary feature flags)

Setting Up Auto Memory

Step 1: Create the Memory Directory

The directory is created automatically by Claude Code, but to initialize manually:

bash
mkdir -p ~/.claude/projects/<project-path>/memory/

The <project-path> typically mirrors the working directory with slashes replaced by dashes (e.g., /workspaces/my-app becomes -workspaces-my-app).

Step 2: Create MEMORY.md

Start with a minimal index and expand as patterns emerge. Include:

  • Project overview: Key architectural facts (2-3 bullet points)
  • Quick reference: Counts, paths, conventions that come up repeatedly
  • Critical gotchas: Hard-won lessons that prevent repeated mistakes
  • Topic file index: Table linking to detailed files with "when to consult" guidance

See examples/MEMORY.md for a starter template.

Step 3: Create Topic Files as Needed

Create topic files only when a domain accumulates enough detail to warrant its own file. Common topic files:

FilePurpose
architecture.mdSystem design decisions, component relationships
patterns.mdCode conventions, naming, file organization
debugging.mdSolutions to recurring problems
workflows.mdBuild, test, deploy procedures
known-issues.mdBug tracking, open/fixed issues
release-process.mdVersion management, release checklists
dependencies.mdPackage versions, compatibility notes

See examples/topic-file.md for the recommended structure.

Organization Principles

Semantic Over Chronological

Organize by topic, not by date. "Architecture decisions" is better than "Session notes 2026-02-15". When new information arrives, integrate it into the appropriate topic rather than appending chronologically.

Concise Index, Detailed Topics

MEMORY.md answers "what do I need to know right now?" Topic files answer "what are all the details about X?" Keep the index scannable — use bullet points, tables, and bold for key terms.

Topic File Index Table

Always include a table in MEMORY.md linking to topic files with guidance on when to consult each:

markdown
## Topic Files

| File | When to consult |
|------|----------------|
| `architecture.md` | Working on system design, component changes |
| `patterns.md` | Writing new code, reviewing conventions |
| `debugging.md` | Investigating bugs, error messages |

One Topic Per File

Each file covers one domain. If a file grows beyond ~5,000 words or covers multiple unrelated topics, split it. A file named misc.md or notes.md is a sign of poor organization.

Maintenance

When to Update

  • After discovering a mistake that could recur
  • When a pattern is confirmed across 2+ interactions
  • When the user explicitly asks to remember something
  • After resolving a tricky bug worth documenting
  • When project structure changes significantly

When to Remove or Edit

  • When stored information becomes outdated (version bumps, removed features)
  • When a gotcha is fixed and no longer relevant
  • When the user asks to forget something
  • When MEMORY.md exceeds ~200 lines — prune or move detail to topic files

Avoiding Drift

Periodically review memory files against the actual project state. Stale entries (wrong counts, outdated paths, fixed bugs still listed as open) erode trust in the memory system. Mark fixed issues as fixed rather than deleting them — the history of what went wrong is itself valuable.

Additional Resources

Reference Files

For detailed patterns, anti-patterns, and advanced techniques:

  • references/patterns.md — Writing style guide, MEMORY.md structure patterns, topic file patterns, common anti-patterns

Example Files

Working examples ready to adapt:

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Auto Memory AI skill do?

This skill should be used when the user asks to 'set up memory', 'create memory files', 'create MEMORY.md', 'set up topic files', 'improve memory organization', 'what should I remember', 'how to structure memory files', 'MEMORY.md is too long', 'what goes in memory vs topic files', 'memory best practices', or wants to establish a persistent knowledge base across Claude Code sessions. Triggers on: memory setup, MEMORY.md, topic files, cross-session knowledge, persistent notes, memory maintenance, memory pruning.

Why use Auto Memory on TypingMind?

Because you install it once and use it with any model. Auto Memory is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Auto Memory in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/tractorjuice/arc-kit/tree/main/.claude/skills/auto-memory. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Auto Memory?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Auto Memory?

As many as you like. As long as a model supports skills, you can use Auto Memory with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Auto Memory AI skill free?

It is published on GitHub by tractorjuice. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇