Cherry Studio Tool Guide
CherryHQ/cherry-studio
Routes an agent inside Cherry Studio to the right first-party tool or bundled runtime for local scripts, documents, memory, schedules, knowledge bases, MCP servers and more.
Installs and configures MemPalace as a private local palace, a shared-brain hub or a client of an existing hub, including MCP registration and version-correct initialization.
Install MemPalace Setup and Operation
$ npx skills add MemPalace/mempalace --skill mempalace -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install MemPalace/mempalace mempalace --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/MemPalace/mempalace.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/mempalace .claude/skills/mempalace && rm -rf skills-srcUse ~/.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/
Install the "mempalace" agent skill from https://github.com/MemPalace/mempalace/tree/develop/skills/mempalace into .claude/skills/mempalace/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mempalace", 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 install https://github.com/MemPalace/mempalace/tree/develop/skills/mempalaceType 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.
$ npx skills add MemPalace/mempalace --skill mempalace -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install MemPalace/mempalace mempalace --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MemPalace/mempalace.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/mempalace .agents/skills/mempalace && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "mempalace" agent skill from https://github.com/MemPalace/mempalace/tree/develop/skills/mempalace into .agents/skills/mempalace/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mempalace", 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.
$ npx skills add MemPalace/mempalace --skill mempalace -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install MemPalace/mempalace mempalace --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MemPalace/mempalace.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/mempalace .cursor/skills/mempalace && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "mempalace" agent skill from https://github.com/MemPalace/mempalace/tree/develop/skills/mempalace into .cursor/skills/mempalace/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mempalace", 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 https://github.com/MemPalace/mempalace.git --path skills/mempalace--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add MemPalace/mempalace --skill mempalace -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install MemPalace/mempalace mempalace --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MemPalace/mempalace.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/mempalace .gemini/skills/mempalace && rm -rf skills-srcUse ~/.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/
Install the "mempalace" agent skill from https://github.com/MemPalace/mempalace/tree/develop/skills/mempalace into .gemini/skills/mempalace/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mempalace", 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.
$ gh skill install MemPalace/mempalace mempalaceInstalls 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).
$ npx skills add MemPalace/mempalace --skill mempalace -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/MemPalace/mempalace.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/mempalace .github/skills/mempalace && rm -rf skills-srcUse ~/.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/
Install the "mempalace" agent skill from https://github.com/MemPalace/mempalace/tree/develop/skills/mempalace into .github/skills/mempalace/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mempalace", 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.
$ npx skills add MemPalace/mempalace --skill mempalace -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install MemPalace/mempalace mempalace --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MemPalace/mempalace.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/mempalace .opencode/skills/mempalace && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "mempalace" agent skill from https://github.com/MemPalace/mempalace/tree/develop/skills/mempalace into .opencode/skills/mempalace/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mempalace", 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
mempalace- GitHub stars
- 59k
- Token cost
- ~2.2k tokens
- SKILL.md length
- 1,083 words
- Files
- 1
- Skills in repo
- 5
- Repo updated
- First seen
- Licence
- MIT
At a glance
Installs and configures MemPalace as a private local palace, a shared-brain hub or a client of an existing hub, including MCP registration and version-correct initialization.
- Works in 7 steps: Inspect before changing anything → Install the CLI when necessary → Choose the topology with the user → …
- Setting up MemPalace for the first time
- SKILL.md covers Setup protocol, Palace health: audit and…, Recalling past work and Cursor-specific notes, plus 1 more section
- Calls uv, python and claude
What it does
Setup is guided and starts with inspection: the agent detects the OS and agent harness, runs version checks for mempalace, uv and Python, and looks for an existing palace and MCP registration, never reinitializing or rebuilding one just to make setup easier. It installs the CLI when needed, preferring an isolated uv tool install and otherwise pip, then confirms the command is reachable on PATH.
You choose a topology: a private local palace on one machine with a local stdio MCP server, a shared-brain hub that owns the palace and serves a fleet, or a client that joins an existing hub using a hub URL and bearer token you supply, without creating a second copy of the owner's palace. The agent also asks which project or conversation corpus to initialize, defaulting to the current directory.
Initialization follows instructions printed by the CLI for the installed version, available for help, init, mine, search and status, and a new palace is verified with mempalace status. MCP is registered with the command that mempalace mcp prints, for example through the claude mcp add or codex mcp add commands, and hubs use mempalace serve. The skill also covers mining, audit and repair, wings, rooms and drawers.
When your agent uses it
- Setting up MemPalace for the first time
- Wiring the MemPalace MCP server into Claude Code or Codex
- Turning one machine into a shared-brain hub for other machines
- Connecting a machine as a client to an existing hub
Example prompts
- “Install MemPalace on this machine as a private palace and register its MCP server.”
- “Join the shared-brain hub at the URL I will give you and do not create a local palace.”
- “Check my MemPalace status and repair anything that looks off.”
Requirements
- Python, with uv or pip to install mempalace
Workflow steps
7 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit d439d1e. 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
Shell commands in SKILL.md call:
uvpythonclaudecodexnpx
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
mempalaceofficial.com
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
MemPalace Setup and Operation loads about 2.2k tokens when it runs. Until then it costs about 73 tokens; SKILL.md has 1,083 words of instructions outside code blocks.
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 MemPalace/mempalace at commit d439d1e, republished under its MIT licence (© MemPalace). 1,083 words, ~2,160 tokens.
Download SKILL.mdSave it as
.claude/skills/mempalace/SKILL.md (or your agent's skills folder).- name
- mempalace
- description
- Install, configure, and operate MemPalace, including a private local palace, a shared-brain hub, or a client joining an existing hub. Use for first-time setup, MCP wiring, mining, status, palace audit and repair, wings, rooms, drawers, shared-brain identity, or logstream readiness.
MemPalace Setup
A guided, skill-first setup for a searchable memory palace. The user may have
installed this skill with npx skills add before the MemPalace Python package
or MCP server exists; that is the normal bootstrap path.
Setup protocol
1. Inspect before changing anything
- Detect the OS and current agent harness.
- Run
mempalace --version,uv --version, and an appropriate Python version check. Do not assume that an installed Python package is reachable on PATH. - Check for an existing palace and MCP registration. Never reinitialize or rebuild an existing palace just to make setup simpler.
2. Install the CLI when necessary
Prefer an isolated uv tool installation:
uv tool install mempalaceIf uv is unavailable, use the PATH-visible Python installation:
python -m pip install mempalaceAfter installation, run mempalace --version. If it still is not reachable,
fix PATH or use the matching uv tool run invocation before continuing.
3. Choose the topology with the user
Ask which outcome they want unless it is already clear:
- private local palace — one machine, local stdio MCP;
- shared-brain hub — this machine owns the palace and serves the fleet;
- client joining an existing hub — this machine connects to a hub owned elsewhere.
Also ask which project or conversation corpus should be initialized, offering the current working directory as the default. A shared-brain client does not initialize a second copy of the owner's palace.
4. Run version-correct initialization
MemPalace provides dynamic, version-correct instructions via the CLI. To get instructions for any operation:
mempalace instructions <command>Where <command> is one of: help, init, mine, search, status.
Run the appropriate instructions command, then follow the returned instructions step by step.
For a new local palace or hub, follow mempalace instructions init, configure
the selected corpus, then verify with mempalace status. For a client, skip
local initialization and obtain the hub URL and bearer token from the user.
5. Configure MCP
For local stdio integrations, use the command printed by mempalace mcp.
Typical registrations are:
claude mcp add mempalace -- mempalace-mcp
codex mcp add mempalace -- mempalace-mcpFor a shared-brain hub, guide the user through mempalace serve and the
official shared-brain guide. Do not expose a non-loopback server without
authentication. For a client joining an existing hub, configure the harness's
HTTP MCP transport with the supplied bearer token; never print or store that
token in project instructions, drawers, or logstream events.
Restart or reconnect the harness when required, then verify that the live MCP tool list includes MemPalace tools. Package installation alone is not proof that MCP is connected.
6. Configure shared-brain identity and coordination
When shared-brain mode is selected:
Agree on a stable
host:harness:projectidentity: lowercase host label (machine), harness family (claude,codex,grok,antigravity, …), and the current workspace as project. Two windows in the same project are one actor.Render the canonical rules with:
bash mempalace rules --host <host> --harness <harness> --project <example>Default
--mcp fullmatches the 47-toolmempalace-mcpserver this skill registers. If the user opted intomempalace-light-mcp, re-render with--mcp lightinstead. Replace an existing<!-- mempalace-shared-brain -->block instead of appending a duplicate.Install the rendered marker-delimited block in the harness's durable agent instructions (Claude
~/.claude/CLAUDE.md, Codex~/.codex/AGENTS.md, Grok~/.grok/AGENTS.md, Antigravity~/.gemini/config/GEMINI.md).Check coordination access with a read-only
mempalace logstream listor the equivalent MCP event-list call.Interactive sessions are declared-idle: they sweep the inbox on collab / before long tasks and do not arm a watcher at session start. Arm
mempalace logstream watch --agent <host>:<harness>:<project>(the CLI defaults a sanitized--state-file) only when the user asked to listen, the agent claimed a task, or it delegated. A remote-only MCP client must instead loop onmempalace_event_wait, preserving the last event id assince_event_id; never point it at a local SQLite watcher. Explain any permission allowlisting needed. If it cannot maintain either loop, record that the agent is turn-based and must sweep its MCP inbox withmempalace_event_liston wake-up.
Do not post a test event without telling the user: logstream events are immutable. If the user approves a smoke event, address it narrowly and close the loop with an acknowledgement.
Show full SKILL.md (442 more words)Show less
7. Report readiness
Summarize the installed version, palace location or hub URL (without secrets),
MCP connection, stable agent identity, watcher mode, and the first safe next
action. For active delegation, hand off to the mempalace-task skill.
Ask whether the user wants weekly stable-release checks. The default is no.
Explain that enabling them contacts PyPI but sends no palace content, identity,
or telemetry. When enabling, record the installer actually used with
mempalace update configure --enable --installer uv-tool (or pipx / pip);
use --disable to opt out. Checks never install anything. In
mempalace_status, treat updates.server as the palace-serving runtime and
updates.client (when present) as the local proxy runtime; do not conflate
their versions or installers. For a client update, use the local mempalace update plan. A remote server update is informational on the client: surface it
naturally and ask the hub operator to prepare and authorize the plan on the
palace-serving machine. Never use a client-generated plan to upgrade the
server, and never execute any plan without explicit approval.
Palace health: audit and repair session
When the user asks how well organized the palace is, whether memory is
"messy", why a scoped search or wake-up misses things, or invokes
/mempalace:audit, run the audit and then offer a repair session:
mempalace instructions auditFollow the returned instructions. In short: run mempalace audit --json
(read-only, safe while the MCP server is running), present the five layer
scores and findings, then walk the user through repairs one structured
question at a time with a recommended option first: merging wings and
rooms spelled two ways, folding stub wings, deleting tunnels on generic
tokens and self-link hallways, agreeing a knowledge-graph predicate
vocabulary, and giving flat wings a closed room set with
mempalace rooms propose / apply. Moves over deletions, numbers before actions, verbatim content
always. Re-run the audit at the end and write a diary entry with the
before and after scores and every decision made.
Recalling past work
This skill covers setup, mining, and status. For questions about past
work, prior decisions, or people that may already be filed in the
palace, prefer the mempalace-recall skill — it enforces
search-before-answer so the agent reads the palace instead of guessing.
Cursor-specific notes
- The Cursor plugin auto-registers
mempalace-mcp; a standalonenpx skills addinstallation does not. Always verify the live tool list. - For automatic background saving every N agent turns plus session-start memory recall, also install the Cursor hooks separately by running
hooks/cursor/install.sh --scope userfrom a cloned MemPalace repo. See the Cursor hooks guide for the full walkthrough. - The recommended
agent_namewhen callingmempalace_diary_writefrom a Cursor session iscursor-ide(matches the precedent ofclaude-codeandcodex).
Canonical references
© MemPalace, 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 skills/mempalace of MemPalace/mempalace.
Open the folder on GitHubat commit d439d1e
Compare with similar skills
MemPalace Setup and Operation 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| MemPalace Setup and Operation this skillMemPalace/mempalace | 59k | — | ~2.2k | Automated safety check: Pass | MIT | |
| Cherry Studio Tool GuideCherryHQ/cherry-studio | 52k | — | ~1.9k | Automated safety check: Pass | AGPL-3.0 | |
| Qmdbreferrari/obsidian-mind | 5k | — | ~1.7k | Automated safety check: Pass | MIT | |
| Context Mode Searchmksglu/context-mode | 26k | — | ~250 | Automated safety check: Pass | Custom licence | |
| remindb Memory Writerradimsem/remindb | 129 | — | ~2k | Automated safety check: Pass | MIT | |
| Ogham Maintainogham-mcp/ogham-mcp | 115 | — | ~1.1k | Automated safety check: Pass | MIT |
Similar skills
Qmd
breferrari/obsidian-mind
Search the vault using QMD semantic search. An agent skill from breferrari/obsidian-mind.
Context Mode Search
mksglu/context-mode
Search context-mode's persistent FTS5 knowledge base for previously indexed local project content, documentation, or session memory. Trigger…
remindb Memory Writer
radimsem/remindb
Guides an agent writing to a remindb memory server: structured notes go in as files parsed into a node tree, single text facts go in through MemoryWrite.
Ogham Maintain
ogham-mcp/ogham-mcp
Admin and maintenance workflows for Ogham shared memory. An agent skill from ogham-mcp/ogham-mcp.
Ogham Recall
ogham-mcp/ogham-mcp
Smart retrieval from Ogham shared memory. An agent skill from ogham-mcp/ogham-mcp.
More from MemPalace/mempalace
MemPalace Memory Search
MemPalace/mempalace
Mines project files and conversation exports into a local, searchable memory palace and recalls past work by semantic search through the mempalace CLI.
MemPalace Recall Protocol
MemPalace/mempalace
Makes the agent search the user's MemPalace memory before answering about past work, people, projects or earlier decisions.
MemPalace Task Handoff
MemPalace/mempalace
Creates, hands off, claims, executes and closes agent tasks through the MemPalace logstream, with approval of the exact task before it is recorded.
MemPalace Memory
MemPalace/mempalace
Gives an agent a local memory palace over MCP: verbatim conversation memory, semantic search and a temporal knowledge graph, with a per-session recall protocol.
Related
Works with
Categories
Questions about MemPalace Setup and Operation
What does MemPalace Setup and Operation do?
Installs and configures MemPalace as a private local palace, a shared-brain hub or a client of an existing hub, including MCP registration and version-correct initialization. Setup is guided and starts with inspection: the agent detects the OS and agent harness, runs version checks for mempalace, uv and Python, and looks for an existing palace and MCP registration, never reinitializing or rebuilding one just to make setup easier. It installs the CLI when needed, preferring an isolated uv tool install and otherwise pip, then confirms the command is reachable on PATH.
When should I use MemPalace Setup and Operation?
MemPalace Setup and Operation fits situations like: setting up MemPalace for the first time; wiring the MemPalace MCP server into Claude Code or Codex; turning one machine into a shared-brain hub for other machines; connecting a machine as a client to an existing hub.
How do I install MemPalace Setup and Operation in Claude Code?
Run `npx skills add MemPalace/mempalace --skill mempalace -a claude-code`. Or copy the skill folder (skills/mempalace in MemPalace/mempalace) into .claude/skills/mempalace in your project. Claude Code loads it when a task matches its description.
How do I install MemPalace Setup and Operation in Codex?
Run `npx skills add MemPalace/mempalace --skill mempalace -a codex`. Or copy the skill folder (skills/mempalace in MemPalace/mempalace) into .agents/skills/mempalace in your project. Codex loads it when a task matches its description.
Can I use MemPalace Setup and Operation 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 MemPalace/mempalace --skill mempalace -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mempalace, .gemini/skills/mempalace, .github/skills/mempalace and .opencode/skills/mempalace in your project.
What does MemPalace Setup and Operation need to run?
Going by SKILL.md and its folder, MemPalace Setup and Operation needs the command-line tools its instructions call (uv, python, claude, codex and npx). Our summary lists: Python, with uv or pip to install mempalace.
Does MemPalace Setup and Operation access the network?
SKILL.md names 1 domain. As links in the text: mempalaceofficial.com. This is read from the text; nothing was executed.
Is MemPalace Setup and Operation 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 MemPalace Setup and Operation use?
MemPalace Setup and Operation 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 MemPalace Setup and Operation use?
About 2.2k tokens (SKILL.md is roughly 8.6k 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 MemPalace Setup and Operation?
Skills that share tags, products or a category with MemPalace Setup and Operation: Cherry Studio Tool Guide (CherryHQ/cherry-studio, 52k stars), Qmd (breferrari/obsidian-mind, 5k stars), Context Mode Search (mksglu/context-mode, 26k stars) and remindb Memory Writer (radimsem/remindb, 129 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains MemPalace Setup and Operation?
MemPalace (a GitHub organization) maintains it in MemPalace/mempalace, which has 59,483 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 7, 2026.
Source: MemPalace/mempalace on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.