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.
Smart retrieval from Ogham shared memory. An agent skill from ogham-mcp/ogham-mcp.
Install Ogham Recall
$ npx skills add ogham-mcp/ogham-mcp --skill ogham-recall -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ogham-mcp/ogham-mcp ogham-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/ogham-mcp/ogham-mcp.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/ogham-recall .claude/skills/ogham-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 "ogham-recall" agent skill from https://github.com/ogham-mcp/ogham-mcp/tree/main/skills/ogham-recall into .claude/skills/ogham-recall/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ogham-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/ogham-mcp/ogham-mcp/tree/main/skills/ogham-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 ogham-mcp/ogham-mcp --skill ogham-recall -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ogham-mcp/ogham-mcp ogham-recall --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ogham-mcp/ogham-mcp.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/ogham-recall .agents/skills/ogham-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 "ogham-recall" agent skill from https://github.com/ogham-mcp/ogham-mcp/tree/main/skills/ogham-recall into .agents/skills/ogham-recall/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ogham-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 ogham-mcp/ogham-mcp --skill ogham-recall -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ogham-mcp/ogham-mcp ogham-recall --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ogham-mcp/ogham-mcp.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/ogham-recall .cursor/skills/ogham-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 "ogham-recall" agent skill from https://github.com/ogham-mcp/ogham-mcp/tree/main/skills/ogham-recall into .cursor/skills/ogham-recall/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ogham-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/ogham-mcp/ogham-mcp.git --path skills/ogham-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 ogham-mcp/ogham-mcp --skill ogham-recall -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ogham-mcp/ogham-mcp ogham-recall --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ogham-mcp/ogham-mcp.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/ogham-recall .gemini/skills/ogham-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 "ogham-recall" agent skill from https://github.com/ogham-mcp/ogham-mcp/tree/main/skills/ogham-recall into .gemini/skills/ogham-recall/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ogham-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 ogham-mcp/ogham-mcp ogham-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 ogham-mcp/ogham-mcp --skill ogham-recall -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/ogham-mcp/ogham-mcp.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/ogham-recall .github/skills/ogham-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 "ogham-recall" agent skill from https://github.com/ogham-mcp/ogham-mcp/tree/main/skills/ogham-recall into .github/skills/ogham-recall/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ogham-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 ogham-mcp/ogham-mcp --skill ogham-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 ogham-mcp/ogham-mcp ogham-recall --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ogham-mcp/ogham-mcp.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/ogham-recall .opencode/skills/ogham-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 "ogham-recall" agent skill from https://github.com/ogham-mcp/ogham-mcp/tree/main/skills/ogham-recall into .opencode/skills/ogham-recall/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ogham-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
ogham-recall- GitHub stars
- 115
- Token cost
- ~1k tokens
- SKILL.md length
- 531 words
- Files
- 1
- Skills in repo
- 3
- Repo updated
- First seen
- Licence
- MIT
At a glance
Smart retrieval from Ogham shared memory. An agent skill from ogham-mcp/ogham-mcp.
- Works in 3 steps: Search broadly → Follow the graph → Check for decisions
- The user wants to recall what they know
- SKILL.md covers Retrieval strategy, Context bootstrapping, Presenting results and When nothing is found
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Ogham Recall is an agent skill from ogham-mcp/ogham-mcp. Smart retrieval from Ogham shared memory. Use when the user wants to recall what they know, find related context, bootstrap session context, or explore their knowledge graph. Triggers on "what do I know about", "find related", "search ogham", "search memory", "recall", "context for this project", "what did we decide about", "any notes on", "check ogham for", or any request to retrieve or explore stored knowledge. Also use at session start when the user is about to work on something and could benefit from prior…
Its SKILL.md is about 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 Agent Workflows, covering Knowledge graphs, MCP servers and Vector databases. It works with Model Context Protocol, PostgreSQL and pgvector. The repository describes itself as: Shared memory MCP server — persistent, searchable, cross-client Claude, Opencode. The licence is MIT.
When your agent uses it
- The user wants to recall what they know
- Find related context
- Bootstrap session context
- Explore their knowledge graph
Example prompts
- “what do I know about”
- “find related”
- “search ogham”
- “/ogham-recall”
Workflow steps
3 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 7184b6b. 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.
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
Ogham Recall loads about 1k tokens when it runs. Until then it costs about 146 tokens; SKILL.md has 531 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 ogham-mcp/ogham-mcp at commit 7184b6b, republished under its MIT licence (© ogham-mcp). 531 words, ~1,023 tokens.
Download SKILL.mdSave it as
.claude/skills/ogham-recall/SKILL.md (or your agent's skills folder).- name
- ogham-recall
- description
- Smart retrieval from Ogham shared memory. Use when the user wants to recall what they know, find related context, bootstrap session context, or explore their knowledge graph. Triggers on "what do I know about", "find related", "search ogham", "search memory", "recall", "context for this project", "what did we decide about", "any notes on", "check ogham for", or any request to retrieve or explore stored knowledge. Also use at session start when the user is about to work on something and could benefit from prior context. Requires the Ogham MCP server to be connected.
Ogham recall
You retrieve knowledge from Ogham shared memory. Your job is to find relevant memories and surface connections the user might not know exist.
Retrieval strategy
Don't just run one search and call it done. Different queries surface different results, and the knowledge graph often has useful connections that keyword search misses.
Step 1: Search broadly
Start with hybrid_search using the user's query. This combines semantic similarity with keyword matching, so "us-east-1" and "which AWS region do we use" both work.
For queries that need connections between memories, use graph_depth=1 to automatically follow relationship edges from the top results. This surfaces related memories that didn't match the query directly but are linked to matches.
If the results look thin, try rephrasing. A query about "database setup" might miss memories tagged with "postgres" or "supabase" -- try both angles.
Step 2: Follow the graph
When search returns useful results, pick the most relevant memory IDs and run find_related on them. This walks the knowledge graph outward -- a memory about a database decision might link to memories about the schema, migration gotchas, or performance benchmarks.
For broader exploration, use explore_knowledge with a query. It searches first, then traverses relationship edges from the results. Set depth=2 to go two hops out if the first level doesn't surface enough.
Step 3: Check for decisions
If the user is asking about a past choice ("what did we decide about X", "why did we go with Y"), filter by decision-type memories. Decisions stored via store_decision have structured rationale and alternatives that give context regular memories don't.
Try: hybrid_search(query="decision about X", tags=["type:decision"])
Show full SKILL.md (266 more words)Show less
Context bootstrapping
When the user is starting work on something, proactively search for relevant context. Look at:
- The current project name (from CLAUDE.md, repo name, or working directory)
- What the user said they're about to do
- Recent git activity (what was changed recently)
Run 2-3 targeted searches to pull in useful background. Present it as a brief summary, not a wall of text. Something like:
"Found 4 relevant memories from previous sessions:
- You decided to use OpenAI embeddings at 512 dims because Mistral can't truncate (stored March 10)
- There's a gotcha with Neon PgBouncer -- ALTER TABLE silently fails on the pooler endpoint (stored March 8)
- The auto-link threshold of 0.85 produces very different results per provider (stored March 9)"
Let the user ask for more detail on any of these rather than dumping everything.
Presenting results
Keep it scannable. For each relevant memory:
- One-line summary of what it says
- When it was stored (relative time is fine -- "last week", "March 10")
- Tags if they help (especially
type:decisionortype:gotcha) - Memory ID only if the user might want to update or delete it
Group related memories together rather than listing them in search-rank order. If you found a decision and its supporting context via graph traversal, present them as a cluster.
When nothing is found
If searches come back empty, say so directly. Don't make up context or hedge with "I didn't find anything but...". The user needs to know their knowledge base doesn't cover this topic yet.
Suggest storing what they learn: "Nothing in Ogham about X yet. Want me to store what we figure out?"
© ogham-mcp, 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/ogham-recall of ogham-mcp/ogham-mcp.
Open the folder on GitHubat commit 7184b6b
Compare with similar skills
Ogham Recall 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 |
|---|---|---|---|---|---|---|
| Ogham Recall this skillogham-mcp/ogham-mcp | 115 | — | ~1k | Automated safety check: Pass | MIT | |
| MemPalace MemoryMemPalace/mempalace | 60k | — | ~2.7k | Automated safety check: Pass | MIT | |
| Agent RecallGoldentrii/AgentRecall-X | 371 | — | ~5.2k | Automated safety check: Notes | MIT | |
| Cortex Mem MCPsopaco/cortex-mem | 313 | — | ~2.8k | Automated safety check: Pass | MIT | |
| Session Ingestdnotitia/akb | 162 | — | ~8.1k | Automated safety check: Pass | Custom licence | |
| Mesh Memorysickn33/agentic-awesome-skills | 47k | 1 repos | ~1.9k | Automated safety check: Pass | MIT |
Similar skills
Agent Recall
Goldentrii/AgentRecall-X
Persistent compounding memory for AI agents. An agent skill from Goldentrii/AgentRecall-X.
Cortex Mem MCP
sopaco/cortex-mem
Persistent memory enhancement for AI agents. An agent skill from sopaco/cortex-mem.
Session Ingest
dnotitia/akb
Ingest a coding session JSONL into AKB as structured notes — session report + parallel-drafted TIL / task / idea / decision sub-notes.
Mesh Memory
sickn33/agentic-awesome-skills
Self-hosted semantic memory for AI agents via MCP. An agent skill from sickn33/agentic-awesome-skills.
Cognee Docker Setup
topoteretes/cognee
Runs the Cognee AI memory platform in Docker, from a one-file prebuilt image to a full compose stack with UI, MCP server, Postgres and Neo4j.
More from ogham-mcp/ogham-mcp
Ogham Research
ogham-mcp/ogham-mcp
Structured memory capture for Ogham shared memory. An agent skill from ogham-mcp/ogham-mcp.
Ogham Maintain
ogham-mcp/ogham-mcp
Admin and maintenance workflows for Ogham shared memory. An agent skill from ogham-mcp/ogham-mcp.
Related
Works with
Questions about Ogham Recall
What does Ogham Recall do?
Smart retrieval from Ogham shared memory. An agent skill from ogham-mcp/ogham-mcp. Ogham Recall is an agent skill from ogham-mcp/ogham-mcp. Smart retrieval from Ogham shared memory.
When should I use Ogham Recall?
Ogham Recall fits situations like: the user wants to recall what they know; find related context; bootstrap session context; explore their knowledge graph.
How do I install Ogham Recall in Claude Code?
Run `npx skills add ogham-mcp/ogham-mcp --skill ogham-recall -a claude-code`. Or copy the skill folder (skills/ogham-recall in ogham-mcp/ogham-mcp) into .claude/skills/ogham-recall in your project. Claude Code loads it when a task matches its description.
How do I install Ogham Recall in Codex?
Run `npx skills add ogham-mcp/ogham-mcp --skill ogham-recall -a codex`. Or copy the skill folder (skills/ogham-recall in ogham-mcp/ogham-mcp) into .agents/skills/ogham-recall in your project. Codex loads it when a task matches its description.
Can I use Ogham Recall 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 ogham-mcp/ogham-mcp --skill ogham-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/ogham-recall, .gemini/skills/ogham-recall, .github/skills/ogham-recall and .opencode/skills/ogham-recall in your project.
What does Ogham Recall need to run?
SKILL.md names no scripts, command-line tools or credentials: Ogham Recall is instructions for the agent only.
Does Ogham Recall 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 Ogham Recall 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 Ogham Recall use?
Ogham Recall 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 Ogham Recall use?
About 1k tokens (SKILL.md is roughly 4.1k 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 Ogham Recall?
Skills that share tags, products or a category with Ogham Recall: MemPalace Memory (MemPalace/mempalace, 60k stars), Agent Recall (Goldentrii/AgentRecall-X, 371 stars), Cortex Mem MCP (sopaco/cortex-mem, 313 stars) and Session Ingest (dnotitia/akb, 162 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Ogham Recall?
ogham-mcp (a GitHub organization) maintains it in ogham-mcp/ogham-mcp, which has 115 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on September 30, 2026.
Source: ogham-mcp/ogham-mcp on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.