agentleFS
Sign inStart free
JinchengGao-InftyJinchengGao-Infty/agent-loadout/skills/memory-palace/SKILL.md

memory-palace

Skill3 starsChanged 8 months agoMITView on GitHub

Manage durable cross-session memory via Memory Palace MCP server. Supports semantic search, write guards, and hierarchical memory organization. Use for saving facts, recalling context, and managing long-term knowledge. Chinese triggers: 记忆, 长期记忆, 记住, 回忆, 召回, 压缩上下文, 重建索引.

4 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions4 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 4

    1. drewOrc/Mem-Palace-skill★ 4same name
    2. luabagg/agent-skills★ 3same name
    3. loursCreatif/ours-stack★ 1same name
    4. Tino-Tian/-Memory-Palace-AI-★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository8 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read before write: Always read existing memory before creating/updating

    line 31
  2. Very specific:

    Respect guards: If guard_action=NOOP, stop and inspect the suggested target before proceeding

    line 32
  3. Very specific:

    Prefer update over create: Use update_memory when a related memory already exists

    line 33

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Memory Palace

Durable, semantically-searchable memory system for AI agents. Persists knowledge across sessions via a local MCP server.

Setup: See Memory Palace repository for installation. Requires Ollama with an embedding model (recommended: snowflake-arctic-embed2).

First Action in Any Session

Always start with:

read_memory("system://boot")

This loads core memories and recent context.

Core Workflow

  1. Boot: read_memory("system://boot")
  2. Search: search_memory(query, include_session=true) if URI is unknown
  3. Read: read_memory(uri) to inspect the exact target
  4. Mutate: create_memory or update_memory only after reading
  5. Maintain: compact_context or rebuild_index when needed

Key Rules

  • Read before write: Always read existing memory before creating/updating
  • Respect guards: If guard_action=NOOP, stop and inspect the suggested target before proceeding
  • Prefer update over create: Use update_memory when a related memory already exists
  • Fresh context: In new sessions or subagents, always reload with system://boot

Available Tools

ToolPurpose
read_memoryRead a memory by URI
search_memorySemantic search across all memories
create_memoryCreate a new memory
update_memoryUpdate an existing memory
delete_memoryDelete a memory
add_aliasAdd an alternative URI for a memory
compact_contextDistill noisy session history
rebuild_indexRebuild the semantic search index
index_statusCheck index health

Common URIs

  • system://boot — Session initialization
  • system://index — Full memory index
  • system://recent — Recently modified memories
  • core://agent — Agent identity and rules
  • core://my_user — User profile

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free