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.
Routes continuity and recall requests to Engram, a local-first MCP memory and identity layer that saves user-approved lessons, decisions and playbooks.
Install Engram Memory
$ npx skills add Patdolitse/piia-engram --skill engram -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Patdolitse/piia-engram engram --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/Patdolitse/piia-engram.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/engram .claude/skills/engram && 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 "engram" agent skill from https://github.com/Patdolitse/piia-engram/tree/main/skills/engram into .claude/skills/engram/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "engram", 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/Patdolitse/piia-engram/tree/main/skills/engramType 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 Patdolitse/piia-engram --skill engram -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Patdolitse/piia-engram engram --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Patdolitse/piia-engram.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/engram .agents/skills/engram && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "engram" agent skill from https://github.com/Patdolitse/piia-engram/tree/main/skills/engram into .agents/skills/engram/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "engram", 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 Patdolitse/piia-engram --skill engram -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Patdolitse/piia-engram engram --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Patdolitse/piia-engram.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/engram .cursor/skills/engram && 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 "engram" agent skill from https://github.com/Patdolitse/piia-engram/tree/main/skills/engram into .cursor/skills/engram/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "engram", 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/Patdolitse/piia-engram.git --path skills/engram--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 Patdolitse/piia-engram --skill engram -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Patdolitse/piia-engram engram --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Patdolitse/piia-engram.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/engram .gemini/skills/engram && 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 "engram" agent skill from https://github.com/Patdolitse/piia-engram/tree/main/skills/engram into .gemini/skills/engram/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "engram", 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 Patdolitse/piia-engram engramInstalls 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 Patdolitse/piia-engram --skill engram -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Patdolitse/piia-engram.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/engram .github/skills/engram && 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 "engram" agent skill from https://github.com/Patdolitse/piia-engram/tree/main/skills/engram into .github/skills/engram/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "engram", 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 Patdolitse/piia-engram --skill engram -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Patdolitse/piia-engram engram --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Patdolitse/piia-engram.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/engram .opencode/skills/engram && 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 "engram" agent skill from https://github.com/Patdolitse/piia-engram/tree/main/skills/engram into .opencode/skills/engram/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "engram", 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
engram- GitHub stars
- 163
- Token cost
- ~1.3k tokens
- SKILL.md length
- 614 words
- Files
- 3 (incl. references)
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- AGPL-3.0-or-later
At a glance
Routes continuity and recall requests to Engram, a local-first MCP memory and identity layer that saves user-approved lessons, decisions and playbooks.
- Works in 4 steps: Start of a continued session — call… → During work — when the user asks what… → Capturing durable knowledge — the user,… → …
- Continuing from a previous session or picking up where you left off
- SKILL.md covers When to use this skill, How to use it (routing, not…, Honest boundaries and MCP server
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
This skill routes an agent to Engram, a local-first memory and identity layer served over MCP, when a request implies continuity, recall or durable memory rather than a one-off task. Engram stores user-approved lessons, decisions, playbooks and project context as local JSON, so several MCP-capable coding tools can start from the same understanding of the user without a cloud account or hidden memory. The AI suggests entries and the user decides what becomes permanent.
The skill maps phrasings to existing MCP tools: get_resume_brief to continue a previous session, search_knowledge and get_relevant_knowledge to recall decisions, add_lesson, add_decision and add_playbook to save things, get_user_context and get_identity_card for preferences and export, and wrap_up_session at the end of a session. Export tools are owner-gated and can write local files. For ordinary coding tasks with no memory angle it should not be used. It adds no behavior of its own, and the project is licensed AGPL-3.0-or-later.
When your agent uses it
- Continuing from a previous session or picking up where you left off
- Recalling a past decision and the reasoning behind it
- Saving a lesson, decision or playbook as durable local memory
- Exporting your identity card or context for another tool
Example prompts
- “Pick up where we left off yesterday on the billing refactor.”
- “Save a decision: we chose SQLite over Postgres because the app is single-user.”
- “Search what we know about rate limiting before I start on it.”
- “Export my identity card so I can use it in another tool.”
Requirements
- The Engram MCP server connected to your coding tool
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Start of a continued session — call get_resume_brief to recover the last
- During work — when the user asks what was decided or learned, call
- Capturing durable knowledge — the user, not the AI, owns what becomes
- End of session — call wrap_up_session to checkpoint context so the next
What it can do on your machine
Read from SKILL.md and the folder at commit 0b7ee56. 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
Engram Memory loads about 1.3k tokens when it runs, and up to ~3.1k if it reads all its reference files. Until then it costs about 211 tokens; SKILL.md has 614 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 Patdolitse/piia-engram at commit 0b7ee56, republished under its AGPL-3.0-or-later licence (© Patdolitse). 614 words, ~1,319 tokens.
Download SKILL.mdSave it as
.claude/skills/engram/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- engram
- description
- Local-first personal AI identity and memory layer for MCP-compatible coding tools (Claude Code, Codex, Cursor, and others). Use this skill when the user wants to continue from a previous session ("continue from last session", "pick up where we left off"), recall a past decision ("what did we decide", "what was our reasoning"), persist something durable ("remember this", "save a lesson", "save a decision", "save a playbook"), search prior knowledge ("search what we know about X", "have we hit this before"), export their identity or context ("export my identity card", "give me my context"), or maintain local-first cross-tool identity and memory that the user owns and approves. Engram stores user-approved lessons, decisions, playbooks, and project context as local JSON; the AI suggests, the user decides what becomes permanent.
- license
- AGPL-3.0-or-later
Engram
Engram is a local-first personal AI identity and memory layer exposed over MCP. It lets MCP-compatible coding tools (Claude Code, Codex, Cursor, and other MCP clients) start from the same user-approved understanding of who the user is, what they've decided, and what they've learned — without a cloud account and without hidden memory the user cannot inspect.
This skill tells you when to reach for Engram and which existing MCP tools to use. It does not add new behavior; it routes to the Engram MCP server.
When to use this skill
Reach for Engram when the user's request implies continuity, recall, or durable memory rather than a one-off task:
| Signal | Example phrasing | Where to start |
|---|---|---|
| Resume work | "continue from last session", "pick up where we left off" | get_resume_brief |
| Recall a decision | "what did we decide", "why did we choose X" | search_knowledge, get_relevant_knowledge |
| Save a lesson | "remember this", "save a lesson", "note this gotcha" | add_lesson |
| Save a decision | "record this decision", "we chose X because Y" | add_decision |
| Save a playbook | "save this as a playbook", "remember these steps" | add_playbook |
| Search prior knowledge | "have we seen this before", "search what we know about X" | search_knowledge |
| Identity / preferences | "who am I to you", "what are my preferences" | get_user_context, get_identity_card |
| Export identity/context | "export my identity card", "give me my context" | get_identity_card |
| End of session | wrapping up, summarizing what changed | wrap_up_session |
When the request is a normal coding task with no continuity or memory angle, do not invoke Engram — just do the task.
How to use it (routing, not magic)
- Start of a continued session — call
get_resume_briefto recover the last thread of work. For identity and preferences on a fresh project, callget_user_context. - During work — when the user asks what was decided or learned, call
search_knowledge(topic known) orget_relevant_knowledge(let Engram pick what's relevant). Normal read/search tools provide session context; export surfaces such asget_identity_cardare owner-gated and can write local files. - Capturing durable knowledge — the user, not the AI, owns what becomes
permanent. When the user says to remember something, propose it and write it
with
add_lesson/add_decision/add_playbook. These are user-approved writes, not automatic background memory. - End of session — call
wrap_up_sessionto checkpoint context so the next tool (or the next session) can resume.
Some MCP clients also run session hooks that capture context automatically; that context lands in the user-visible daily log and the staging tier, where it is inspectable and is not silently promoted to verified/trusted knowledge.
The full read/write tool map is in references/tools.md. Privacy, ownership, and storage boundaries are in references/privacy.md.
Show full SKILL.md (186 more words)Show less
Honest boundaries
- Engram suggests; the user decides. AI-suggested knowledge is staged for review, not silently promoted to verified/trusted memory; everything written lands in the user's local store where it can be inspected.
- Storage is local JSON the user owns. There is no cloud account and no
vendor lock-in. Engram sends one anonymous usage ping a day (random install
ID, version, OS, Python version, AI client name, date); turn it off with
engram telemetry off,ENGRAM_TELEMETRY=0orDO_NOT_TRACK=1. Detailed usage statistics stay off unless the user turns them on; if enabled they write a local log only, and any remote sending is a separate explicit opt-in. - Knowledge moves through a staging → verified path so unreviewed entries do not silently become trusted facts.
- Do not claim capabilities Engram does not have. Use only the tool names in references/tools.md; do not invent tools.
MCP server
Engram runs as an MCP server via the piia-engram-mcp command. Configure your
MCP client to launch it (the Cursor plugin skeleton under .cursor-plugin/
shows one such wiring). By default the server exposes a Tier-1 core tool set;
the full set is available with ENGRAM_TOOLS=all.
© Patdolitse, AGPL-3.0-or-later. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 2 other files (references) in skills/engram of Patdolitse/piia-engram.
- SKILL.md
- references/privacy.md
- references/tools.md
Open the folder on GitHubat commit 0b7ee56
Compare with similar skills
Engram Memory next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Engram Memory this skillPatdolitse/piia-engram | 163 | — | ~1.3k | Automated safety check: Pass | AGPL-3.0-or-later | |
| Memori MCP Memory UsageMemoriLabs/Memori | 17k | — | ~3.8k | Automated safety check: Pass | MIT | |
| Prism Startup Contextdcostenco/prism-coder | 158 | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | |
| Mnemosjeremylongshore/tons-of-skills-marketplace | 2.8k | — | ~3.1k | Automated safety check: Pass | MIT | |
| MemPalace Setup and OperationMemPalace/mempalace | 59k | — | ~2.2k | Automated safety check: Pass | MIT | |
| agentmemory Setup and Diagnosticsrohitg00/agentmemory | 29k | — | ~1k | Automated safety check: Notes | Apache-2.0 |
Similar skills
Prism Startup Context
dcostenco/prism-coder
Loads Prism session memory on the first user turn, greets the developer by their configured name and shows recent-session context at the configured depth.
Mnemos
jeremylongshore/tons-of-skills-marketplace
Persistent memory and learning-loop skills for AI coding agents using mnemos MCP tools.
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.
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.
Qmd
breferrari/obsidian-mind
Search the vault using QMD semantic search. An agent skill from breferrari/obsidian-mind.
Related
Works with
Categories
Questions about Engram Memory
What does Engram Memory do?
Routes continuity and recall requests to Engram, a local-first MCP memory and identity layer that saves user-approved lessons, decisions and playbooks. This skill routes an agent to Engram, a local-first memory and identity layer served over MCP, when a request implies continuity, recall or durable memory rather than a one-off task. Engram stores user-approved lessons, decisions, playbooks and project context as local JSON, so several MCP-capable coding tools can start from the same understanding of the user without a cloud account or hidden memory.
When should I use Engram Memory?
Engram Memory fits situations like: continuing from a previous session or picking up where you left off; recalling a past decision and the reasoning behind it; saving a lesson, decision or playbook as durable local memory; exporting your identity card or context for another tool.
How do I install Engram Memory in Claude Code?
Run `npx skills add Patdolitse/piia-engram --skill engram -a claude-code`. Or copy the skill folder (skills/engram in Patdolitse/piia-engram) into .claude/skills/engram in your project. Claude Code loads it when a task matches its description.
How do I install Engram Memory in Codex?
Run `npx skills add Patdolitse/piia-engram --skill engram -a codex`. Or copy the skill folder (skills/engram in Patdolitse/piia-engram) into .agents/skills/engram in your project. Codex loads it when a task matches its description.
Can I use Engram Memory in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Patdolitse/piia-engram --skill engram -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/engram, .gemini/skills/engram, .github/skills/engram and .opencode/skills/engram in your project.
What does Engram Memory need to run?
SKILL.md names no scripts, command-line tools or credentials: Engram Memory is instructions for the agent only. Our summary lists: The Engram MCP server connected to your coding tool.
Does Engram Memory access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Engram Memory safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Engram Memory use?
Engram Memory is published under the AGPL-3.0-or-later licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Engram Memory use?
About 1.3k tokens (SKILL.md is roughly 5.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.8k tokens, read only when the agent opens those files.
What are the alternatives to Engram Memory?
Skills that share tags, products or a category with Engram Memory: Memori MCP Memory Usage (MemoriLabs/Memori, 17k stars), Prism Startup Context (dcostenco/prism-coder, 158 stars), Mnemos (jeremylongshore/tons-of-skills-marketplace, 2.8k stars) and MemPalace Setup and Operation (MemPalace/mempalace, 59k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Engram Memory?
Patdolitse (a GitHub user) maintains it in Patdolitse/piia-engram, which has 163 GitHub stars. The repository was last updated on October 8, 2026.
Source: Patdolitse/piia-engram on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.