Agent skill

Nautilus Compass Memory

by chunxiaoxx in chunxiaoxx/nautilus-compass

Local-first long-term memory for AI agents via MCP — zero LLM calls at write time, typed retrieval at read time.

Custom licenceAuto-check passedAgent Workflows

Install Nautilus Compass Memory

skills CLI
$ npx skills add chunxiaoxx/nautilus-compass --skill nautilus-compass-memory -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install chunxiaoxx/nautilus-compass nautilus-compass-memory --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/chunxiaoxx/nautilus-compass.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/nautilus-compass-memory .claude/skills/nautilus-compass-memory && rm -rf skills-src

Use ~/.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/

Facts

Skill name
nautilus-compass-memory
GitHub stars
1.3k
Token cost
~1.7k tokens
SKILL.md length
467 words
Files
2
Skills in repo
2
Repo updated
First seen
Licence
Custom licence

At a glance

Local-first long-term memory for AI agents via MCP — zero LLM calls at write time, typed retrieval at read time.

  • Works in 3 steps: When to use → How to connect (~3 minutes) → How to verify (don't trust us)
  • Session decisions and pitfalls should survive across days
  • SKILL.md covers 1 · When to use, 2 · How to connect (~3 minutes), 3 · How to verify (don't trust… and 中文版
  • Calls git, python and bash; reaches compass.nautilus.social

What it does

Nautilus Compass Memory is an agent skill from chunxiaoxx/nautilus-compass. Local-first long-term memory for AI agents via MCP — zero LLM calls at write time, typed retrieval at read time. Use when session decisions and pitfalls should survive across days, when multiple agents or dialogs share facts on the same filesystem, or when you want drift detection so past mistakes don't repeat. Verified claims only — every published number ships as a byte-recomputable, ed25519-signed evidence pack.

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `SKILL.zh-CN.md`).

It sits in Agent Workflows, covering Agent memory, GitOps and MCP servers. It works with Model Context Protocol. The repository describes itself as: Open memory & reliability layer for AI agents + independent judging/verification (NACRE judge, caliber-bench meta-benchmark, preregistered criteria) — by Nautilus Platform.

When your agent uses it

  • Session decisions and pitfalls should survive across days
  • Multiple agents
  • Dialogs share facts on the same filesystem
  • You want drift detection so past mistakes dont repeat

Example prompts

  • “/nautilus-compass-memory”

Requirements

  • Python 3

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. When to use
  2. How to connect (~3 minutes)
  3. How to verify (don't trust us)

What it can do on your machine

Read from SKILL.md and the folder at commit 6891357. 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:

    • git
    • python
    • bash
    • pip

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • compass.nautilus.social

    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

Nautilus Compass Memory loads about 1.7k tokens when it runs. Until then it costs about 111 tokens; SKILL.md has 467 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~111
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 467 words (~1,721 tokens).

“Open-source memory & reliability layer for AI agents (Modified MIT). Raw text is embedded locally with BGE-m3 — no extraction LLM at ingest, no graph, no data leaving the machine. All intelligence lives at read time (semantic + keyword hybrid…”

— opening of SKILL.md by chunxiaoxx, Custom licence
name
nautilus-compass-memory

Read the full SKILL.md on GitHub

Files

SKILL.md and 1 other file in skills/nautilus-compass-memory of chunxiaoxx/nautilus-compass.

  • SKILL.md
  • SKILL.zh-CN.md

Open the folder on GitHubat commit 6891357

Compare with similar skills

Nautilus Compass 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.

Nautilus Compass Memory compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Nautilus Compass Memory this skillchunxiaoxx/nautilus-compass1.3k—~1.7kAutomated safety check: PassCustom licence
MemPalace Setup and OperationMemPalace/mempalace59k—~2.2kAutomated safety check: PassMIT
agentmemory Setup and Diagnosticsrohitg00/agentmemory29k—~1kAutomated safety check: NotesApache-2.0
Qmdbreferrari/obsidian-mind5k—~1.7kAutomated safety check: PassMIT
Memori MCP Memory UsageMemoriLabs/Memori17k—~3.8kAutomated safety check: PassMIT
Shared Agent Knowledge Commonsmozilla-ai/cq1.3k—~6.5kAutomated safety check: PassApache-2.0

Similar skills

  • 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.

    59k GitHub stars~2.2k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Sets up and troubleshoots a local agentmemory install, covering the MCP connection, environment variables, ports, authentication and optional feature flags.

    29k GitHub stars~1k tokensUpdated today
    Agent WorkflowsAuto-check: notes
  • Qmd

    breferrari/obsidian-mind

    Search the vault using QMD semantic search. An agent skill from breferrari/obsidian-mind.

    5k GitHub stars~1.7k tokensUpdated 3 days ago
    Agent WorkflowsAuto-check passed
  • 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.

    17k GitHub stars~3.8k tokensUpdated 6 days ago
    Agent WorkflowsAuto-check passed
  • Queries a shared knowledge store before acting, proposes newly discovered insights, and confirms or flags existing entries, so agents stop rediscovering the same failures.

    1.3k GitHub stars~6.5k tokensUpdated 3 days ago
    Agent WorkflowsAuto-check passed
  • 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.

    9.5k GitHub stars~347 tokensUpdated today
    Agent WorkflowsAuto-check passed

More from chunxiaoxx/nautilus-compass

  • Compass Integrity

    chunxiaoxx/nautilus-compass

    A skill your agent uses when the user is about to rely on prior session memory for a non-trivial decision, or when something feels off about a recall hit — runs the Merkle chain check, drift…

    1.3k GitHub stars~1.3k tokensUpdated today
    Auto-check passed

Categories

Questions about Nautilus Compass Memory

What does Nautilus Compass Memory do?

Local-first long-term memory for AI agents via MCP — zero LLM calls at write time, typed retrieval at read time. Nautilus Compass Memory is an agent skill from chunxiaoxx/nautilus-compass. Local-first long-term memory for AI agents via MCP — zero LLM calls at write time, typed retrieval at read time.

When should I use Nautilus Compass Memory?

Nautilus Compass Memory fits situations like: session decisions and pitfalls should survive across days; multiple agents; dialogs share facts on the same filesystem; you want drift detection so past mistakes dont repeat.

How do I install Nautilus Compass Memory in Claude Code?

Run `npx skills add chunxiaoxx/nautilus-compass --skill nautilus-compass-memory -a claude-code`. Or copy the skill folder (skills/nautilus-compass-memory in chunxiaoxx/nautilus-compass) into .claude/skills/nautilus-compass-memory in your project. Claude Code loads it when a task matches its description.

How do I install Nautilus Compass Memory in Codex?

Run `npx skills add chunxiaoxx/nautilus-compass --skill nautilus-compass-memory -a codex`. Or copy the skill folder (skills/nautilus-compass-memory in chunxiaoxx/nautilus-compass) into .agents/skills/nautilus-compass-memory in your project. Codex loads it when a task matches its description.

Can I use Nautilus Compass 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 chunxiaoxx/nautilus-compass --skill nautilus-compass-memory -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/nautilus-compass-memory, .gemini/skills/nautilus-compass-memory, .github/skills/nautilus-compass-memory and .opencode/skills/nautilus-compass-memory in your project.

What does Nautilus Compass Memory need to run?

Going by SKILL.md and its folder, Nautilus Compass Memory needs the command-line tools its instructions call (git, python, bash and pip). Our summary lists: Python 3.

Does Nautilus Compass Memory access the network?

SKILL.md names 1 domain. In commands or code: compass.nautilus.social; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Nautilus Compass 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 Nautilus Compass Memory use?

Nautilus Compass Memory has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Nautilus Compass Memory use?

About 1.7k tokens (SKILL.md is roughly 6.9k 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 Nautilus Compass Memory?

Skills that share tags, products or a category with Nautilus Compass Memory: MemPalace Setup and Operation (MemPalace/mempalace, 59k stars), agentmemory Setup and Diagnostics (rohitg00/agentmemory, 29k stars), Qmd (breferrari/obsidian-mind, 5k stars) and Memori MCP Memory Usage (MemoriLabs/Memori, 17k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Nautilus Compass Memory?

chunxiaoxx (a GitHub user) maintains it in chunxiaoxx/nautilus-compass, which has 1,258 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 9, 2026.

Source: chunxiaoxx/nautilus-compass on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.