auto-memory — community auto-memory, arc-kit, community, ide skills, Claude Code, Cursor, Windsurf

v1.0.0
GitHub

About this Skill

Ideal for AI Agents like Claude Code requiring persistent knowledge retention across sessions Enterprise Architecture Governance & Vendor Procurement Toolkit

tractorjuice tractorjuice
[96]
[16]
Updated: 2/28/2026

Agent Capability Analysis

The auto-memory skill by tractorjuice is an open-source community AI agent skill for Claude Code and other IDE workflows, helping agents execute tasks with better context, repeatability, and domain-specific guidance.

Ideal Agent Persona

Ideal for AI Agents like Claude Code requiring persistent knowledge retention across sessions

Core Value

Empowers agents to leverage persistent auto memory, utilizing a structured knowledge base stored in a memory directory with concise index files like MEMORY.md and detailed topic files, facilitating project knowledge retention and growth

Capabilities Granted for auto-memory

Retaining project knowledge across sessions
Creating a structured knowledge base with MEMORY.md and topic files
Automating project data storage in the memory directory

! Prerequisites & Limits

  • Requires access to the memory directory (~/.claude/projects/<path>/memory/)
  • Limited to 200 lines in the MEMORY.md file
Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

auto-memory

Install auto-memory, an AI agent skill for AI agent workflows and automation. Works with Claude Code, Cursor, and Windsurf with one-command setup.

SKILL.md
Readonly

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
1~/.claude/projects/<project-path>/memory/ 2├── MEMORY.md # Always loaded into system prompt (~200 lines max) 3├── architecture.md # Topic file: system architecture decisions 4├── patterns.md # Topic file: code patterns and conventions 5├── debugging.md # Topic file: debugging insights 6├── workflows.md # Topic file: development workflows 7└── 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
1mkdir -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
1## Topic Files 2 3| File | When to consult | 4|------|----------------| 5| `architecture.md` | Working on system design, component changes | 6| `patterns.md` | Writing new code, reviewing conventions | 7| `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:

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is auto-memory?

Ideal for AI Agents like Claude Code requiring persistent knowledge retention across sessions Enterprise Architecture Governance & Vendor Procurement Toolkit

How do I install auto-memory?

Run the command: npx killer-skills add tractorjuice/arc-kit/auto-memory. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for auto-memory?

Key use cases include: Retaining project knowledge across sessions, Creating a structured knowledge base with MEMORY.md and topic files, Automating project data storage in the memory directory.

Which IDEs are compatible with auto-memory?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for auto-memory?

Requires access to the memory directory (~/.claude/projects/<path>/memory/). Limited to 200 lines in the MEMORY.md file.

How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add tractorjuice/arc-kit/auto-memory. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use auto-memory immediately in the current project.

Related Skills

Looking for an alternative to auto-memory or another community skill for your workflow? Explore these related open-source skills.

View All

widget-generator

Logo of f
f

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

149.6k
0
AI

flags

Logo of vercel
vercel

flags is a Next.js feature management skill that enables developers to efficiently add or modify framework feature flags, streamlining React application development.

138.4k
0
Browser

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI