Agent skill

Memory Palace

Hierarchical memory organization for multi-session context retention.

Install Memory Palace

skills CLI

$ npx skills add vibeeval/vibecosystem --skill memory-palace -a claude-code

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

GitHub CLI

$ gh skill install vibeeval/vibecosystem memory-palace --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/vibeeval/vibecosystem.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/memory-palace .claude/skills/memory-palace && 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/

Paste into Claude Code

Install the "memory-palace" agent skill from https://github.com/vibeeval/vibecosystem/tree/main/skills/memory-palace into .claude/skills/memory-palace/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "memory-palace", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/vibeeval/vibecosystem/tree/main/skills/memory-palace

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add vibeeval/vibecosystem --skill memory-palace -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install vibeeval/vibecosystem memory-palace --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/vibeeval/vibecosystem.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/memory-palace .agents/skills/memory-palace && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "memory-palace" agent skill from https://github.com/vibeeval/vibecosystem/tree/main/skills/memory-palace into .agents/skills/memory-palace/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "memory-palace", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add vibeeval/vibecosystem --skill memory-palace -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install vibeeval/vibecosystem memory-palace --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/vibeeval/vibecosystem.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/memory-palace .cursor/skills/memory-palace && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "memory-palace" agent skill from https://github.com/vibeeval/vibecosystem/tree/main/skills/memory-palace into .cursor/skills/memory-palace/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "memory-palace", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/vibeeval/vibecosystem.git --path skills/memory-palace

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add vibeeval/vibecosystem --skill memory-palace -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install vibeeval/vibecosystem memory-palace --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/vibeeval/vibecosystem.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/memory-palace .gemini/skills/memory-palace && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "memory-palace" agent skill from https://github.com/vibeeval/vibecosystem/tree/main/skills/memory-palace into .gemini/skills/memory-palace/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "memory-palace", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install vibeeval/vibecosystem memory-palace

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add vibeeval/vibecosystem --skill memory-palace -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/vibeeval/vibecosystem.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/memory-palace .github/skills/memory-palace && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "memory-palace" agent skill from https://github.com/vibeeval/vibecosystem/tree/main/skills/memory-palace into .github/skills/memory-palace/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "memory-palace", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add vibeeval/vibecosystem --skill memory-palace -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install vibeeval/vibecosystem memory-palace --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/vibeeval/vibecosystem.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/memory-palace .opencode/skills/memory-palace && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "memory-palace" agent skill from https://github.com/vibeeval/vibecosystem/tree/main/skills/memory-palace into .opencode/skills/memory-palace/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "memory-palace", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: memory-palace
GitHub stars: 531
Token cost: ~1.1k tokens
SKILL.md length: 290 words
Files: 1
Skills in repo: 144
Repo updated: Aug 8, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Hierarchical memory organization for multi-session context retention.

Backend & APIs work in your project
SKILL.md covers Architecture, Storage Format, Operations and Integration Points, plus 2 more sections
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Memory Palace is an agent skill from vibeeval/vibecosystem. Hierarchical memory organization for multi-session context retention. Wings (projects) Rooms (domains) Drawers (decisions). Semantic search across all memories with zero cloud dependency.

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.

It sits in Backend & APIs. The repository describes itself as: AI software team for Claude Code - 138 agents, 295 skills, 73 hooks. Self-learning, multi-agent swarm, autonomous skill evolution. The licence is MIT.

When your agent uses it

Backend & APIs work in your project

Example prompts

“/memory-palace”

Requirements

Docker

What it can do on your machine

Read from SKILL.md and the folder at commit 3b763b1. 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 json).
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 Palace loads about 1.1k tokens when it runs. Until then it costs about 51 tokens; SKILL.md has 290 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~51
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 vibeeval/vibecosystem at commit 3b763b1, republished under its MIT licence (© vibeeval). 290 words, ~1,059 tokens.

Download SKILL.mdSave it as .claude/skills/memory-palace/SKILL.md (or your agent's skills folder).

name: memory-palace
description: Hierarchical memory organization for multi-session context retention. Wings (projects) > Rooms (domains) > Drawers (decisions). Semantic search across all memories with zero cloud dependency.

Memory Palace

Hierarchical, persistent memory system for Claude Code sessions. Organizes knowledge so agents never lose context across sessions.

Architecture

Palace (global)
  Wing: project-name
    Room: authentication
      Drawer: "chose JWT over sessions" (2026-04-07)
      Drawer: "rate limiting at 100 req/min" (2026-04-06)
    Room: database
      Drawer: "PostgreSQL with pgvector" (2026-04-05)
      Drawer: "migration strategy: blue-green" (2026-04-04)
    Room: deployment
      Drawer: "Vercel + GitHub Actions" (2026-04-03)
  Wing: another-project
    Room: ...

Storage Format

All memories stored in ~/.claude/palace/ as flat JSONL files per wing:

~/.claude/palace/
  index.json          # Wing registry
  my-project.jsonl    # All drawers for this wing
  other-project.jsonl # All drawers for this wing

Drawer Entry Format

json

{
  "id": "d-abc123",
  "wing": "my-project",
  "room": "authentication",
  "content": "Chose JWT with refresh tokens over session-based auth. Reason: stateless, mobile-friendly, scalable.",
  "tags": ["auth", "jwt", "architecture"],
  "timestamp": "2026-04-07T14:30:00Z",
  "session_id": "s-xyz789",
  "agent": "architect",
  "type": "decision"
}

Entry Types

decision - Architectural or design choice with reasoning
discovery - Something learned about the codebase
error - Error encountered and how it was resolved
constraint - External limitation or requirement
pattern - Recurring code or workflow pattern

Operations

Store a Memory

When an important decision, discovery, or constraint is identified:

Wing: detect from CLAUDE_PROJECT_DIR or package.json name
Room: infer from topic (auth, db, deploy, frontend, api, etc.)
Content: what was decided/discovered and WHY
Tags: relevant keywords for search

Recall Memories

Before starting work on a topic, query relevant rooms:

1. Get wing from current project
2. List rooms with recent activity
3. Load drawers matching current task keywords
4. Inject as context: "Previous decisions in this area: ..."

Search Across Wings

For cross-project pattern detection:

Search all wings for entries matching query
Return sorted by relevance (keyword match + recency)
Useful for: "Have I solved this before in another project?"

Integration Points

With Agents

architect: Store architectural decisions automatically
self-learner: Store error resolutions as discoveries
planner: Load relevant rooms before planning
compass: Use palace for session recovery context

With Hooks

palace-auto-save hook: Captures decisions from conversation
palace-recall hook: Injects relevant memories at session start
pre-compact-continuity: Saves WIP state to palace before compaction

With Existing Memory System

Palace complements (does not replace) the existing PostgreSQL memory:

PostgreSQL: raw embeddings, vector search, learning store
Palace: structured, human-readable, hierarchical organization
Both can be queried; palace is faster for targeted recall

Room Detection Heuristics

Keywords in Context	Room
auth, login, session, JWT, OAuth	authentication
database, SQL, migration, schema	database
deploy, CI/CD, Docker, K8s	deployment
React, CSS, component, UI	frontend
API, endpoint, REST, GraphQL	api
test, TDD, coverage, mock	testing
security, XSS, injection, CORS	security
performance, cache, optimize	performance
config, env, settings	configuration

When to Store

ALWAYS store:

Architectural decisions with reasoning
External constraints (client requirements, hosting limits)
Error resolutions that took > 5 minutes to solve
Chosen patterns and why alternatives were rejected

NEVER store:

Code snippets (they're in git)
Temporary debugging notes
Information already in CLAUDE.md
Ephemeral task progress (use tasks for that)

Files

Just SKILL.md in skills/memory-palace of vibeeval/vibecosystem.

Open the folder on GitHubat commit 3b763b1

Compare with similar skills

Memory Palace 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 Palace compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Memory Palace this skillvibeeval/vibecosystem	531	—	~1.1k	Automated safety check: Pass	MIT	2 mo ago
Sub2API AdminWei-Shaw/sub2api	43k	1 repos	~717	Automated safety check: Pass	LGPL-3.0	yesterday
OpenAPI to MCP Servermcp-use/mcp-use	11k	—	~5.2k	Automated safety check: Pass	Apache-2.0	yesterday
Gemini Live API Devgoogle-gemini/gemini-skills	4.3k	—	~4.6k	Automated safety check: Pass	Apache-2.0	yesterday
OmniRoute LLM Cachediegosouzapw/OmniRoute	74k	1 repos	~529	Automated safety check: Pass	MIT	yesterday
Projectsamchon/nestia	2.2k	—	~3k	Automated safety check: Pass	MIT	today

Similar skills

Sub2API Admin
Wei-Shaw/sub2api
Manages a Sub2API deployment from the command line: accounts, redeem and invitation codes, groups, proxies, imports, exports and raw admin API calls.
43k GitHub starsUsed in 1 repo~717 tokens
Backend & APIsAuto-check passed
OpenAPI to MCP Server
mcp-use/mcp-use
Turns an OpenAPI or Swagger spec into an MCP server with the mcp-use TypeScript SDK, mapping each operation to a tool, wiring auth, testing and deploying.
11k GitHub stars~5.2k tokensUpdated yesterday
Backend & APIsAuto-check passed
Gemini Live API Dev
google-gemini/gemini-skills
Official
A skill your agent uses when building real-time, bidirectional streaming applications with the Gemini Live API, or migrating legacy Live models (2.0/2.5/3.1) to Gemini 3.8 Live.
4.3k GitHub stars~4.6k tokensUpdated yesterday
Backend & APIsAuto-check passed
OmniRoute LLM Cache
diegosouzapw/OmniRoute
Documents OmniRoute's cache endpoints for reading cache statistics and clearing entries, statistics or the reasoning cache, with notes on TTL and similarity settings.
74k GitHub starsUsed in 1 repo~529 tokens
Backend & APIsAuto-check passed
Project
samchon/nestia
Defines the nestia product contract, workspace layout, package boundaries, the Go plugin composition model, and canonical commands.
2.2k GitHub stars~3k tokensUpdated today
Backend & APIsAuto-check passed
Databuddy
databuddy-analytics/Databuddy
Integrate Databuddy analytics using the SDK, REST API, or MCP.
1.2k GitHub stars~2.1k tokensUpdated today
Backend & APIsAuto-check passed

Questions about Memory Palace

What does Memory Palace do?

Hierarchical memory organization for multi-session context retention. Memory Palace is an agent skill from vibeeval/vibecosystem. Hierarchical memory organization for multi-session context retention.

When should I use Memory Palace?

Memory Palace fits situations like: backend & APIs work in your project.

How do I install Memory Palace in Claude Code?

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

How do I install Memory Palace in Codex?

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

Can I use Memory Palace 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 vibeeval/vibecosystem --skill memory-palace -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-palace, .gemini/skills/memory-palace, .github/skills/memory-palace and .opencode/skills/memory-palace in your project.

What does Memory Palace need to run?

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

Does Memory Palace 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 Palace 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 Palace use?

Memory Palace 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 Palace use?

About 1.1k tokens (SKILL.md is roughly 4.2k 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 Palace?

Skills that share tags, products or a category with Memory Palace: Sub2API Admin (Wei-Shaw/sub2api, 43k stars), OpenAPI to MCP Server (mcp-use/mcp-use, 11k stars), Gemini Live API Dev (google-gemini/gemini-skills, 4.3k stars) and OmniRoute LLM Cache (diegosouzapw/OmniRoute, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Memory Palace?

vibeeval (a GitHub user) maintains it in vibeeval/vibecosystem, which has 531 GitHub stars. The repository holds 144 skills in this directory. The repository was last updated on August 8, 2026.

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

Install Memory Palace

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Memory Palace

Architecture

Storage Format

Drawer Entry Format

Entry Types

Operations

Store a Memory

Recall Memories

Search Across Wings

Integration Points

With Agents

With Hooks

With Existing Memory System

Room Detection Heuristics

When to Store

Files

Compare with similar skills

Similar skills

More from vibeeval/vibecosystem

Related

Questions about Memory Palace