agentmemory Setup and Diagnostics
rohitg00/agentmemory
Sets up and troubleshoots a local agentmemory install, covering the MCP connection, environment variables, ports, authentication and optional feature flags.
Makes the agent search the user's MemPalace memory before answering about past work, people, projects or earlier decisions.
Install MemPalace Recall Protocol
$ npx skills add MemPalace/mempalace --skill mempalace-recall -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install MemPalace/mempalace mempalace-recall --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-recall .claude/skills/mempalace-recall && 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-recall" agent skill from https://github.com/MemPalace/mempalace/tree/develop/skills/mempalace-recall into .claude/skills/mempalace-recall/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mempalace-recall", 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/mempalace-recallType 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-recall -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install MemPalace/mempalace mempalace-recall --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-recall .agents/skills/mempalace-recall && 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-recall" agent skill from https://github.com/MemPalace/mempalace/tree/develop/skills/mempalace-recall into .agents/skills/mempalace-recall/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mempalace-recall", 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-recall -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install MemPalace/mempalace mempalace-recall --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-recall .cursor/skills/mempalace-recall && 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-recall" agent skill from https://github.com/MemPalace/mempalace/tree/develop/skills/mempalace-recall into .cursor/skills/mempalace-recall/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mempalace-recall", 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-recall--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-recall -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install MemPalace/mempalace mempalace-recall --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-recall .gemini/skills/mempalace-recall && 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-recall" agent skill from https://github.com/MemPalace/mempalace/tree/develop/skills/mempalace-recall into .gemini/skills/mempalace-recall/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mempalace-recall", 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 mempalace-recallInstalls 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-recall -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-recall .github/skills/mempalace-recall && 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-recall" agent skill from https://github.com/MemPalace/mempalace/tree/develop/skills/mempalace-recall into .github/skills/mempalace-recall/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mempalace-recall", 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-recall -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-recall --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-recall .opencode/skills/mempalace-recall && 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-recall" agent skill from https://github.com/MemPalace/mempalace/tree/develop/skills/mempalace-recall into .opencode/skills/mempalace-recall/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mempalace-recall", 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-recall- GitHub stars
- 59k
- Token cost
- ~1.7k tokens
- SKILL.md length
- 782 words
- Files
- 1
- Skills in repo
- 5
- Repo updated
- First seen
- Licence
- MIT
At a glance
Makes the agent search the user's MemPalace memory before answering about past work, people, projects or earlier decisions.
- Works in 6 steps: On wake-up, if a session-start hook… → Before responding about people /… → If unsure about a fact: say "let me… → …
- Answering what was decided in an earlier session
- SKILL.md covers Step 0 — Verify MemPalace is…, Identity, When to recall and Protocol, plus 4 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
This is a search-before-answer protocol: when a question may already be filed in the memory palace, the agent reads it first instead of guessing from model memory. It complements the mempalace skill, which handles install, mining and status, while this one covers recall only. Step 0 checks that MemPalace is installed, for example with mempalace --version, and that its MCP tools are connected. If they are not, the agent says the server is not connected and points to the setup skill instead of quietly answering from memory.
Recall is triggered by questions about past work or decisions, a person, project or entity, an earlier session, or a preference or fact that may have changed over time. It is skipped for pure greenfield tasks such as renaming a variable, since searching every turn would waste latency. The protocol honors any wing scoping injected at session start and picks among a knowledge-graph query for relationships and time-bound facts, a search over source text and a diary read for recent continuity, stopping once the question is answered. When unsure about a fact, the agent says it will check the palace and queries it.
When your agent uses it
- Answering what was decided in an earlier session
- Looking up who someone is or what a project involves from stored memory
- Checking a preference or fact that may have changed over time
Example prompts
- “What did we decide last time about the database migration?”
- “Who is Priya on the platform team, according to my notes?”
- “Remember when we talked about the caching approach? What was the conclusion?”
Requirements
- MemPalace installed
- The mempalace MCP server connected to your agent
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- On wake-up, if a session-start hook injected additional_context,
- Before responding about people / projects / past events / prior
- If unsure about a fact: say "let me check the palace" and query.
- Return the drawer's verbatim text. Never summarize or paraphrase
- After a substantive session, record continuity with
- When a fact changes: use mempalace_kg_supersede for
What it can do on your machine
Read from SKILL.md and the folder at commit 9404981. 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).
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):
cursor.comagentskills.io
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 Recall Protocol loads about 1.7k tokens when it runs. Until then it costs about 106 tokens; SKILL.md has 782 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 9404981, republished under its MIT licence (© MemPalace). 782 words, ~1,712 tokens.
Download SKILL.mdSave it as
.claude/skills/mempalace-recall/SKILL.md (or your agent's skills folder).- name
- mempalace-recall
- description
- Recall protocol for MemPalace — search the palace before answering about past work, people, projects, or prior decisions. Apply when the user asks what was decided, what happened before, who someone is, what was discussed last time, or anything that may already be filed in their memory palace; or when mempalace-recall is invoked. Complements the mempalace setup skill and requires the mempalace-mcp server.
MemPalace Recall
Search-before-answer protocol for MemPalace. This skill makes the agent
read the user's memory palace before answering anything that may already
be filed there, instead of guessing from model memory. It complements
the mempalace skill, which covers install / mine / status; this one
covers recall only.
Step 0 — Verify MemPalace is available
Before relying on recall, confirm MemPalace is installed and reachable:
- Official release page: https://github.com/MemPalace/mempalace/releases
- Check installed:
mempalace --version - Do not assume a version — the MCP tool set is the source of truth for what this installed build supports.
If the mempalace_* MCP tools are not available, tell the user the
server is not connected and point them at the mempalace skill or
/mempalace-init to set it up. Do not silently fall back to answering
from model memory.
Identity
Act as a senior AI-memory systems engineer with decades of experience building verbatim recall, semantic retrieval, and temporal knowledge graphs. Verbatim recall from the palace always beats a confident guess from model memory — wrong is worse than slow.
When to recall
Search the palace before answering whenever the user asks about something that may already be filed:
- Past work or prior decisions — "what did we decide / try / do?"
- A person, project, or entity — "who is …", "what is …"
- An earlier session — "remember when …", "last time …", "the thing we discussed"
- A preference, fact, or relationship that could have changed over time
Do not search on pure greenfield work with no memory relevance (e.g. "rename this variable", "fix this typo"). Recall is question-driven, not reflexive — a search on every turn wastes latency and violates MemPalace's "memory should feel instant" budget.
Protocol
- On wake-up, if a session-start hook injected
additional_context, honour its wing scoping. - Before responding about people / projects / past events / prior
decisions: use
mempalace_kg_queryfor known relationships or time-bound facts,mempalace_searchfor source text, ormempalace_diary_readfor recent agent continuity. Stop when answered; follow the canonical query guide. - If unsure about a fact: say "let me check the palace" and query.
- Return the drawer's verbatim text. Never summarize or paraphrase stored content — quoting the exact words is the point of the system.
- After a substantive session, record continuity with
mempalace_diary_write(skip if a background hook already saved). - When a fact changes: use
mempalace_kg_supersedefor single-valued replacements,mempalace_kg_invalidatefor facts that ended without replacement, andmempalace_kg_addfor independent/coexisting facts.
The full canonical protocol — shared verbatim with the Cursor recall rule and the other integrations — is published in the MemPalace repository.
Tool selection
| You need | Tool |
|---|---|
| Find any memory by meaning | mempalace_search |
| Relational / time-bound facts about an entity | mempalace_kg_query |
| Replace a single-valued fact | mempalace_kg_supersede |
| The chronological story of an entity | mempalace_kg_timeline |
| Recent session continuity | mempalace_diary_read |
| Which wings / rooms exist (scope unknown) | mempalace_list_wings, mempalace_list_rooms |
| Record this session | mempalace_diary_write |
mempalace_search takes a short natural-language query (keywords or a
question — not a system prompt or pasted conversation) plus optional
wing / room filters and limit (default 5).
Active coordination is not recall. When delegating work to another
agent on the shared hub — or waiting for its reply or patch — use the
logstream tools (mempalace_event_append, mempalace_event_wait,
mempalace_patch_submit, mempalace_artifact_get), not drawers or
search. The canonical protocol is published in the
MemPalace repository.
Show full SKILL.md (264 more words)Show less
Unhappy paths
Empty results. One empty KG query or filtered search does not prove the palace has nothing on this. Follow the query guide to check or widen the scope. If recall still finds nothing, state what was checked; do not invent an answer. Offer to file the new information.
MCP error / server down. Surface the error and suggest the user run
mempalace statusor re-run/mempalace-init. Never fall back to guessing.Palace index corrupt / compactor error. If the server reports an HNSW segment-writer error, a ChromaDB compaction failure, or stays "Not connected" after a write, the vector index is out of sync with
chroma.sqlite3while the drawer rows remain intact. Tell the user to stop the server and rebuild from SQLite — do not re-mine, which drops MCP-added drawers and diary entries (#1843):bash mempalace repair --mode from-sqlite --archive-existing --yes mempalace repair-statusDo not attempt an in-process repair from the agent. Full steps are in the shared protocol's "Recovering a corrupt index" section.
Conflicting facts. Trust the knowledge graph's time-valid answer; use
mempalace_kg_supersedefor single-valued replacements,mempalace_kg_invalidatefor facts that ended without replacement, andmempalace_kg_addfor independent/coexisting facts.
Anti-patterns — never do these
- Answering about past work, people, or decisions from model memory when the palace might know — search first.
- Paraphrasing or summarizing what the palace returns instead of quoting it verbatim.
- Searching on every turn, including greenfield tasks with no memory relevance.
- Pasting the whole conversation or a system prompt into the
queryargument — keep queries short and keyword-driven.
Official References
- MemPalace: https://github.com/MemPalace/mempalace
- MemPalace releases: https://github.com/MemPalace/mempalace/releases
- Cursor Skills documentation: https://cursor.com/docs/skills
- Agent Skills specification: https://agentskills.io/specification
© 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-recall of MemPalace/mempalace.
Open the folder on GitHubat commit 9404981
Compare with similar skills
MemPalace Recall Protocol 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 Recall Protocol this skillMemPalace/mempalace | 59k | — | ~1.7k | Automated safety check: Pass | MIT | |
| agentmemory Setup and Diagnosticsrohitg00/agentmemory | 29k | — | ~1k | Automated safety check: Notes | Apache-2.0 | |
| Qmdbreferrari/obsidian-mind | 5k | — | ~1.7k | Automated safety check: Pass | MIT | |
| Memori MCP Memory UsageMemoriLabs/Memori | 17k | — | ~3.8k | Automated safety check: Pass | MIT | |
| Shared Agent Knowledge Commonsmozilla-ai/cq | 1.3k | — | ~6.5k | Automated safety check: Pass | Apache-2.0 | |
| Save to Atlas Memorypacifio/atlas | 9.6k | — | ~347 | Automated safety check: Pass | Apache-2.0 |
Similar skills
Qmd
breferrari/obsidian-mind
Search the vault using QMD semantic search. An agent skill from breferrari/obsidian-mind.
Memori MCP Memory Usage
MemoriLabs/Memori
Teaches an MCP-connected agent when and how to call Memori's recall, summary, compaction, augmentation, feedback and quota tools to keep context across sessions.
Shared Agent Knowledge Commons
mozilla-ai/cq
Queries a shared knowledge store before acting, proposes newly discovered insights, and confirms or flags existing entries, so agents stop rediscovering the same failures.
Save to Atlas Memory
pacifio/atlas
Saves the decisions, facts, failures and architecture notes from a conversation into Atlas's shared memory so other agents and later sessions can reuse them.
Agent Recall
Goldentrii/AgentRecall-X
Persistent compounding memory for AI agents. An agent skill from Goldentrii/AgentRecall-X.
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 Setup and Operation
MemPalace/mempalace
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.
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 Recall Protocol
What does MemPalace Recall Protocol do?
Makes the agent search the user's MemPalace memory before answering about past work, people, projects or earlier decisions. This is a search-before-answer protocol: when a question may already be filed in the memory palace, the agent reads it first instead of guessing from model memory. It complements the mempalace skill, which handles install, mining and status, while this one covers recall only.
When should I use MemPalace Recall Protocol?
MemPalace Recall Protocol fits situations like: answering what was decided in an earlier session; looking up who someone is or what a project involves from stored memory; checking a preference or fact that may have changed over time.
How do I install MemPalace Recall Protocol in Claude Code?
Run `npx skills add MemPalace/mempalace --skill mempalace-recall -a claude-code`. Or copy the skill folder (skills/mempalace-recall in MemPalace/mempalace) into .claude/skills/mempalace-recall in your project. Claude Code loads it when a task matches its description.
How do I install MemPalace Recall Protocol in Codex?
Run `npx skills add MemPalace/mempalace --skill mempalace-recall -a codex`. Or copy the skill folder (skills/mempalace-recall in MemPalace/mempalace) into .agents/skills/mempalace-recall in your project. Codex loads it when a task matches its description.
Can I use MemPalace Recall Protocol 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-recall -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-recall, .gemini/skills/mempalace-recall, .github/skills/mempalace-recall and .opencode/skills/mempalace-recall in your project.
What does MemPalace Recall Protocol need to run?
SKILL.md names no scripts, command-line tools or credentials: MemPalace Recall Protocol is instructions for the agent only. Our summary lists: MemPalace installed; The mempalace MCP server connected to your agent.
Does MemPalace Recall Protocol access the network?
SKILL.md names 2 domains. As links in the text: cursor.com and agentskills.io. This is read from the text; nothing was executed.
Is MemPalace Recall Protocol 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 Recall Protocol use?
MemPalace Recall Protocol 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 Recall Protocol use?
About 1.7k tokens (SKILL.md is roughly 6.8k 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 Recall Protocol?
Skills that share tags, products or a category with MemPalace Recall Protocol: agentmemory Setup and Diagnostics (rohitg00/agentmemory, 29k stars), Qmd (breferrari/obsidian-mind, 5k stars), Memori MCP Memory Usage (MemoriLabs/Memori, 17k stars) and Shared Agent Knowledge Commons (mozilla-ai/cq, 1.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains MemPalace Recall Protocol?
MemPalace (a GitHub organization) maintains it in MemPalace/mempalace, which has 59,488 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 10, 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.