Agent skill

Memory

by TinyAGI in TinyAGI/tinyagi

Manage your persistent hierarchical memory — save, update, search, and organize knowledge as markdown files in the memory/ folder.

MITAuto-check passed

Install Memory

skills CLI
$ npx skills add TinyAGI/tinyagi --skill memory -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install TinyAGI/tinyagi memory --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/TinyAGI/tinyagi.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/memory .claude/skills/memory && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
memory
GitHub stars
3.6k
Token cost
~1.1k tokens
SKILL.md length
317 words
Files
1
Skills in repo
6
Repo updated
First seen
Licence
MIT

At a glance

Manage your persistent hierarchical memory — save, update, search, and organize knowledge as markdown files in the memory/ folder.

  • Works in 3 steps: Decide which category folder it belongs… → Create the category folder if it doesn't… → Write the .md file with proper frontmatter
  • : you learn something worth remembering
  • SKILL.md covers Memory Structure, Memory File Format, Saving a Memory and Updating a Memory, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Memory is an agent skill from TinyAGI/tinyagi. Manage your persistent hierarchical memory — save, update, search, and organize knowledge as markdown files in the memory/ folder. Use when: you learn something worth remembering, the user asks you to remember something, you want to recall past knowledge, you need to reorganize or update existing memories, or you want to search through your memories. Triggers: 'remember this', 'save to memory', 'what do you remember about', 'update memory', 'search memory', 'forget', or when you decide something is worth…

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: TinyAGI is the agent teams orchestrator for One Person Company. (fka TinyClaw). The licence is MIT.

When your agent uses it

  • : you learn something worth remembering
  • The user asks you to remember something
  • You want to recall past knowledge
  • You need to reorganize

Example prompts

  • “remember this”
  • “save to memory”
  • “what do you remember about”
  • “/memory”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Decide which category folder it belongs in (or root memory/ if it's top-level)
  2. Create the category folder if it doesn't exist: mkdir -p memory/
  3. Write the .md file with proper frontmatter

What it can do on your machine

Read from SKILL.md and the folder at commit 2db3a03. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash and markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Memory loads about 1.1k tokens when it runs. Until then it costs about 132 tokens; SKILL.md has 317 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~132
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from TinyAGI/tinyagi at commit 2db3a03, republished under its MIT licence (© TinyAGI). 317 words, ~1,077 tokens.

Download SKILL.mdSave it as .claude/skills/memory/SKILL.md (or your agent's skills folder).
name
memory
description
Manage your persistent hierarchical memory — save, update, search, and organize knowledge as markdown files in the memory/ folder. Use when: you learn something worth remembering, the user asks you to remember something, you want to recall past knowledge, you need to reorganize or update existing memories, or you want to search through your memories. Triggers: 'remember this', 'save to memory', 'what do you remember about', 'update memory', 'search memory', 'forget', or when you decide something is worth persisting.

Memory

Manage your persistent hierarchical memory system. Memories are stored as markdown files in the memory/ folder in your workspace, organized into a folder hierarchy that acts as categories/groups.

Memory Structure

memory/
├── project-setup.md              ← root-level memory
├── preferences/                  ← category folder
│   ├── coding-style.md
│   └── communication.md
├── projects/                     ← category folder
│   ├── overview.md
│   └── webapp/                   ← nested category
│       ├── architecture.md
│       └── api-endpoints.md
└── people/
    └── team-contacts.md

Memory File Format

Every memory file MUST have YAML frontmatter with name and summary fields:

markdown
---
name: coding-style
summary: User prefers functional style, TypeScript strict mode, no semicolons
---

Detailed notes about the user's coding preferences:

- Functional programming style over OOP
- TypeScript with strict mode enabled
- No semicolons (relies on ASI)
- Prefer const over let
- Use arrow functions for callbacks
  • name: Same as the filename (without .md extension). Acts as the memory identifier.
  • summary: A short one-line summary of what this memory contains. This is what appears in the memory index — make it informative enough to decide whether to read the full file.
  • Body: The detailed memory content after the frontmatter. Can be as long as needed.

Saving a Memory

  1. Decide which category folder it belongs in (or root memory/ if it's top-level)
  2. Create the category folder if it doesn't exist: mkdir -p memory/<category>
  3. Write the .md file with proper frontmatter
bash
cat > memory/preferences/coding-style.md << 'EOF'
---
name: coding-style
summary: User prefers functional TypeScript, strict mode, no semicolons
---

Detailed preferences documented here...
EOF

Updating a Memory

Read the existing file, modify its content, and write it back. Update the summary in frontmatter if the core meaning changed.

Searching Memories

Search through memory content using grep:

bash
# Search all memories for a keyword
grep -r "keyword" memory/ --include="*.md"

# Search only summaries (frontmatter)
grep -r "summary:" memory/ --include="*.md"

# Find memories in a specific category
ls memory/projects/

Reading a Memory in Detail

The memory index in AGENTS.md only shows name + summary. To read the full content:

bash
cat memory/<path-to-file>.md

Reorganizing Memory

You can move, rename, or restructure the hierarchy at any time:

bash
# Create a new category
mkdir -p memory/new-category

# Move a memory to a different category
mv memory/old-location/file.md memory/new-category/file.md

# Rename a memory (update the name field in frontmatter too)
mv memory/old-name.md memory/new-name.md

When reorganizing, ensure the name field in frontmatter matches the new filename.

Deleting a Memory

bash
rm memory/path/to/memory.md
# Remove empty category folders
rmdir memory/empty-category/

Guidelines

  • Save proactively: When you learn user preferences, project details, important decisions, or anything that would be useful across conversations — save it.
  • Keep summaries concise: The summary appears in the index that's loaded every conversation. Make it count.
  • Use hierarchy wisely: Group related memories into folders. Don't create too many levels of nesting (2-3 levels max).
  • Update over create: If a memory already exists on the topic, update it rather than creating a duplicate.
  • Merge when appropriate: If you notice related memories scattered around, consolidate them.
  • Prune stale memories: Remove or update memories that are no longer accurate.

© TinyAGI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/memory of TinyAGI/tinyagi.

Open the folder on GitHubat commit 2db3a03

Compare with similar skills

Memory next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Memory compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Memory this skillTinyAGI/tinyagi3.6k—~1.1kAutomated safety check: PassMIT
Swift Actor Persistenceaffaan-m/ECC274k4 repos~1.2kAutomated safety check: PassMIT
Agent Hierarchical Coordinatorruvnet/ruflo74k2 repos~2.8kAutomated safety check: PassMIT
Session Persistruvnet/ruflo74k—~415Automated safety check: NotesMIT
Context Savegarrytan/gstack136k—~9.7kAutomated safety check: NotesMIT
Save As PDFasgeirtj/system_prompts_leaks69k—~2.3kAutomated safety check: PassCC0-1.0

Similar skills

  • Thread-safe data persistence in Swift using actors — in-memory cache with file-backed storage, eliminating data races by design.

    274k GitHub starsUsed in 4 repos~1.2k tokens
    MobileAuto-check passed
  • Agent skill for hierarchical-coordinator - invoke with $agent-hierarchical-coordinator

    74k GitHub starsUsed in 2 repos~2.8k tokens
    Agent WorkflowsAuto-check passed
  • Session Persist

    ruvnet/ruflo

    Persist and restore agent sessions across conversations with state snapshots

    74k GitHub stars~415 tokensUpdated today
    Auto-check: notes
  • Context Save

    garrytan/gstack

    Captures git state, decisions made and remaining work so that a later session can resume the task without losing context.

    136k GitHub stars~9.7k tokensUpdated today
    Agent WorkflowsAuto-check: notes
  • Save As PDF

    asgeirtj/system_prompts_leaks

    Print-ready PDF export

    69k GitHub stars~2.3k tokensUpdated yesterday
    Documents & OfficeAuto-check passed
  • 在 Swift 中使用 actor 实现线程安全的数据持久化——基于内存缓存与文件支持的存储,通过设计消除数据竞争. An agent skill from affaan-m/ECC.

    274k GitHub starsUsed in 3 repos~871 tokens
    MobileAuto-check passed

More from TinyAGI/tinyagi

  • Schedule

    TinyAGI/tinyagi

    Create, list, and delete scheduled tasks (recurring or one-time) that send messages to agents.

    3.6k GitHub stars~1.4k tokensUpdated 6 mo ago
    Auto-check passed
  • Send User Message

    TinyAGI/tinyagi

    Send a proactive message to a paired user via their channel (Discord, Telegram, or WhatsApp).

    3.6k GitHub stars~829 tokensUpdated 6 mo ago
    Auto-check passed
  • Skills Manager

    TinyAGI/tinyagi

    Search for and install skills from the skills registry to agent workspaces.

    3.6k GitHub stars~528 tokensUpdated 6 mo ago
    Auto-check passed
  • Tasks

    TinyAGI/tinyagi

    Manage your assigned tasks on the TinyAGI kanban board — list tasks, update task status, create new tasks, and add or view comments.

    3.6k GitHub stars~721 tokensUpdated 6 mo ago
    Auto-check passed
  • Tinyagi Admin

    TinyAGI/tinyagi

    Manage and operate the TinyAGI system itself — agents, teams, settings, queue, tasks, daemon lifecycle, and source code.

    3.6k GitHub stars~2.5k tokensUpdated 6 mo ago
    Auto-check passed

Questions about Memory

What does Memory do?

Manage your persistent hierarchical memory — save, update, search, and organize knowledge as markdown files in the memory/ folder. Memory is an agent skill from TinyAGI/tinyagi. Manage your persistent hierarchical memory — save, update, search, and organize knowledge as markdown files in the memory/ folder.

When should I use Memory?

Memory fits situations like: : you learn something worth remembering; the user asks you to remember something; you want to recall past knowledge; you need to reorganize.

How do I install Memory in Claude Code?

Run `npx skills add TinyAGI/tinyagi --skill memory -a claude-code`. Or copy the skill folder (.agents/skills/memory in TinyAGI/tinyagi) into .claude/skills/memory in your project. Claude Code loads it when a task matches its description.

How do I install Memory in Codex?

Run `npx skills add TinyAGI/tinyagi --skill memory -a codex`. Or copy the skill folder (.agents/skills/memory in TinyAGI/tinyagi) into .agents/skills/memory in your project. Codex loads it when a task matches its description.

Can I use Memory in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add TinyAGI/tinyagi --skill memory -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/memory, .gemini/skills/memory, .github/skills/memory and .opencode/skills/memory in your project.

What does Memory need to run?

SKILL.md names no scripts, command-line tools or credentials: Memory is instructions for the agent only.

Does Memory access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Memory safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Memory use?

Memory is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Memory use?

About 1.1k tokens (SKILL.md is roughly 4.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Memory?

Skills that share tags, products or a category with Memory: Swift Actor Persistence (affaan-m/ECC, 274k stars), Agent Hierarchical Coordinator (ruvnet/ruflo, 74k stars), Session Persist (ruvnet/ruflo, 74k stars) and Context Save (garrytan/gstack, 136k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Memory?

TinyAGI (a GitHub organization) maintains it in TinyAGI/tinyagi, which has 3,620 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on March 30, 2026.

Source: TinyAGI/tinyagi on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.