Nautilus Compass Memory

Name: Nautilus Compass Memory
Author: chunxiaoxx

by chunxiaoxxversion 3.2.0i★ –iComputer or cloud

Registry nameio.github.chunxiaoxx/nautilus-compass

Install

Overview

Description from the maker (original English)

Local-first long-term memory for AI agents, with byte-recomputable signed verification receipts.

PopNx MCP’s three pillars

These three are never merged into one score: opinions, measurements and popularity are different things.

User voiceiNo reviews yetReviews open together with accounts in a later step
Our basic checksi1 of 1 passedChecked from public information; code not scanned yet
UsageiNot measured yet★ –

What you can do with it

We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.

Connection: Computer or cloud
Transport: stdio, Streamable HTTP
Category: Search & AI memory
You need to fill in: Authorization

Install

Pick the AI app you use, then copy the settings.

Before you install

Basic checks: 1 of 1 passed
Runs on the maker’s server: what you ask it goes through their server.
You fill in yourself: Authorization

Values marked secret are keys to your account. Never share them or paste them into a chat.

You need

Runs in the cloudNothing to install; it connects over the internet
PyPIPython’s uv installed (for the uvx command)

Which app do you use?

ClaudeClaude CodeCursorVS CodeChatGPT

Pick your app above. We remember it, so next time the button says “Install in …”.

This address needs a key in a request header, which the add-connector menu cannot set. Use Claude Code, Cursor or VS Code instead.

Or run it on your computer

Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json

{
  "mcpServers": {
    "nautilus-compass": {
      "command": "uvx",
      "args": [
        "nautilus-compass"
      ]
    }
  }
}

Run this in your terminal

claude mcp add --transport http nautilus-compass https://compass.nautilus.social/mcp/ --header 'Authorization: your-value'

Or run it on your computer

claude mcp add nautilus-compass -- uvx nautilus-compass

Fill in the empty values before running it.

Open in Cursor

Or copy the settings yourself

Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "nautilus-compass": {
      "url": "https://compass.nautilus.social/mcp/",
      "headers": {
        "Authorization": "your-value"
      }
    }
  }
}

Or run it on your computer

Open in Cursor

Or copy the settings yourself

Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "nautilus-compass": {
      "command": "uvx",
      "args": [
        "nautilus-compass"
      ]
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

Open in VS Code

Or copy the settings yourself

Paste into .vscode/mcp.json in your project

{
  "servers": {
    "nautilus-compass": {
      "type": "http",
      "url": "https://compass.nautilus.social/mcp/",
      "headers": {
        "Authorization": "your-value"
      }
    }
  }
}

Or run it on your computer

Open in VS Code

Or copy the settings yourself

Paste into .vscode/mcp.json in your project

{
  "servers": {
    "nautilus-compass": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "nautilus-compass"
      ]
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

This address needs a key in a request header, which the add-connector menu cannot set. Use Claude Code, Cursor or VS Code instead.

Your choice stays on this device in a cookie; no account needed.

Values you fill in

Authorization secret required HTTP header
Bearer token — create a free account at https://compass.nautilus.social/signup, then generate a token in the console. Each token is user-scoped.

These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.

What it can do

We have not read this server’s tool list yet; we check endpoints in rotation.

Basic checksi

We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026

✓ Pass
Maker matches the repo
The registry name was verified with the GitHub account chunxiaoxx, which owns the repo
… Not checked yet
Still maintained
We have not read this repo from GitHub yet
… Not checked yet
Has a licence
We have not read this repo from GitHub yet
… Not checked yet
Endpoint responds
Not checked yet; we check endpoints in rotation
… Not checked yet
Sign-in with OAuth
Not checked yet; we check endpoints in rotation
… Not checked yet
No hidden instructions in tool descriptions
Not checked yet; we read the tool list when we check the endpoint

Compared with others in Search & AI memoryi

More stars than 0% of the other 5653 servers in this category
Published to the registry more recently than 44% of the other 5653 servers in this category
Basic checks equal to or better than 100% of the other 5653 servers in this category

Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.

Common questions

Is Nautilus Compass Memory safe?

It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.

What keys or codes does it need?

You need to fill in: Authorization

Does it run on my computer or in the cloud?

Either way works: install it on your computer or connect to the cloud version.

Is it still maintained?

The GitHub repo last changed –, and the latest version (3.2.0) reached the registry 2 months ago.

Which apps can use it?

Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.

What can I use instead?

In the same category: Context7, Codebase Memory, Exa

Alternatives

Servers in the same category from other makers, sorted by stars.

Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi

Context7

by upstash

Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.

Computer or cloud★ 64,224MITUpdated yesterday

Install

Codebase Memory

by DeusData

Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.

Runs on your computer★ 48,148MITUpdated 21 days ago

Install

Exa

by exa-labs

Connect AI agents to Exa for web search, content fetching, and multi-step research.

Runs in the cloud★ 5,213MITUpdated 2 months ago

Install

README from the maker

Open the README

Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.

nautilus-compass

Open-source memory & reliability layer for AI agents.

Long-term memory that now beats mem0 on all three LongMemEval-S metrics

while staying fully local & 14× cheaper — plus drift detection and

cross-agent contracts that no other memory layer ships.

Plugin for Claude Code / Desktop · Cline · Cursor · Continue.dev · Zed ·

any MCP client.

Built by [Nautilus Platform](https://nautilus.social) · open agent ecosystem · join as agent →

🇬🇧 English (this file) · 🇨🇳 中文

October 2026 — Independent Judging & Verification (new pillar)

This project now also powers the independent judging layer of the Nautilus platform — preregistered criteria, three-state verdicts, negative results published as-is:

NACRE judge v1 — judging knowledge compressed into a 1.7B LoRA (88.5% three-state, ECE 0.072). Model card + weights: nautilus-compass/nacre-judge-v1
Deployment-precision discipline (preregistered, 291 cases): fp16 = 100% label agreement with bf16 anchor (safe) · int8 = 98.28% (fail) · int4 = 94.16% (forbidden). Full verdict table in-repo (docs/metering/PRECOR_BC_VERDICT_20261007.md).
caliber-bench — a meta-benchmark that scores *benchmarks themselves* (criteria drift / contamination / judge stability). Open sample pack: nautilus-compass/caliber-bench-v0
Harness leaderboard, Round 1 — same model, two harnesses: v5-harness 26.7% vs mini-swe-agent 16.7% (+10.0pp), every artifact sha16-addressable. Live at nautilus.social/leaderboard.html; free L1 intake at nautilus.social/intake.html.
Casebook v1.4 (shipping 10/12) — 16 precedented judgment cases + 6 self-errata, every case independently recomputable (docs/cases/CASEBOOK_V1.md); the paid binding line's first artifact.
Judgment-fuel corpus — 2,257 qid-deduplicated precedent cases across four sources (verdict splits / delta registry ratchet / org-fuel pipeline / outreach), live counter at nautilus.social/corpus_stats.json.
E-NACRE-1, a published negative result — domain-routed LoRA shards regressed −36.6pp; dynamic-weight routing suspended until corpus ≥3,000. Negative results ship as first-class findings (docs/metering/PRECOR_ENACRE1_VERDICT_20261007.md).
Full customer journey, externally verified — intake → criteria → leaderboard → status query → registry → programmatic status API (/api/judge_status), all reachable from the public internet with three-tier checks (HTTP / content anchors / live data).
Format-regression set v1 — 26 patch-format failure cases (harness A 15 + agent B 11) from Round 1, each with defect labels and reapply expectations (runtime/outreach/rsi_regression_set_v1.jsonl), built for rsi-bench replay certification.

Memory layer (below) remains fully local & open; judging artifacts carry the same evidence discipline (measured / inferred / unverifiable — labeled).

What this is (memory layer, 2026-08 state)

Three pillars, one plugin:

1 · Black-box long-term memory — now with SOTA retrieval. Raw text embedded locally with BGE-m3. No extraction LLM at ingest, no graph, no data leaving your machine. In Aug 2026 we added utterance-routed chunk retrieval: single-session and knowledge-update questions route to turn-window chunks (the answer usually lives in ONE user turn; whole-session embedding dilutes it), everything else uses session-level hybrid (BM25 + dense RRF). Result on LongMemEval-S full 500 questions, same-question head-to-head vs mem0 2.0.19 (both sides infer=False, each on its own default embedder — bge-m3 vs vertexai text-embedding-005 — our reproduction):

LongMemEval-S · n=500	P@1	P@5	MRR
compass	0.890	0.978	0.929
mem0 2.0.19	0.774	0.916	0.834

One-command reproduction (retrieval-only, no LLM calls, CPU works / GPU recommended for the full 500):

bash scripts/reproduce_lmes_retrieval.sh            # full 500

SUBSET=12 bash scripts/reproduce_lmes_retrieval.sh # smoke

The same utterance ammo overtakes mem0 on its own home benchmark (LOCOMO-10, n=1986: 0.644 / 0.890 vs 0.592 / 0.802) and fixes the single-session collapse on LongMemEval-M (0.20 → 1.00). Full evidence chain with per-type breakdowns and every config flag: docs/evidence/headhead_mem0_full500_20260826.json — including the experiments that failed (cross-encoder reranking *hurts* on this corpus; candidate-pool K is a no-op; Qwen3-0.6B swap is a wash).

2 · Drift detection — the half nobody else solves. Memory recalled doesn't stop the AI from breaking the rule *this time*. compass scores every prompt against an anchor set of real failure patterns (25 positive + 35 negative) before the agent acts. AUC 0.83 held-out, p95 latency <50 ms, fire rate 0.5% in production traffic. White-box layers abstract prompts into facts before drift becomes checkable — structurally out of their reach.

3 · Cross-agent contracts + governance. When you run multiple agents (or multiple Claude dialogs) on shared files, compass derives implicit contracts from handoff files, tracks closure, and audits for fake-closure / red drift. A 4-dialog 28-hour field study lives in docs/case_study_4dialog_compass.md.

The trade that flipped: earlier versions traded −30 points on LongMemEval-S for local deployment and cost. As of 2026-08 there is no trade — full sweep at 1/14 the reproduction cost (~$3.50 per 500 questions vs $50+ for GPT-4o-judged stacks). Full argument: paper/BLACKBOX_VS_WHITEBOX.md.

Quickstart

Packages on PyPI

Package	What it is
`nautilus-compass`	this repo — CLI, MCP server, A2A adapter, assay judge toolkit (3.3.0)
`assay-verify`	ed25519 signed receipts for AI outputs — attest-at-generation, verify-on-consume (Let's Encrypt for AI claims)
`jev-trust`	trust middleware for the Jev decision API — logs every call, measures calibration in your domain, signs the evidence
BC1 benchmark	30-item organizational-memory exam — honest scoring (U never counts), machine-scored, our own 11/18 first self-test published in full — LAUNCHED 9/27

Python package (PyPI · 3.3.0)

pip install nautilus-compass

ships the CLI, the MCP server, the A2A adapter and session tools:

nautilus-compass · compass-mcp · compass-a2a

compass-drift-history · compass-session-search · compass-session-writer

30 seconds (Claude Code / Desktop · local daemon)

git clone https://github.com/chunxiaoxx/nautilus-compass ~/.claude/plugins/nautilus-compass

bash ~/.claude/plugins/nautilus-compass/install.sh

start the BGE-m3 daemon (one-time per boot)

bash ~/.claude/plugins/nautilus-compass/daemon_start.sh

Deploy notes (field-verified pitfalls, 2026-08-28):

- COMPASS_USE_INOTIFY=0 disables new-file discovery — recalls won't see

fresh writes, silently. Only set it if you know why; the daemon logs a

WARNING when it's off.

- drift fails loudly now: if anchors.json is missing from the plugin dir,

responses carry drift.anchors_error + should_alert: true (it used to

silently return "no risk" — that was a security hole).

- Token changes to tokens.json hot-reload via mtime check (no systemd

restart needed since v3.1.0).

- First recall after daemon idle may take up to 90 s (model cold-load); the

MCP client auto-retries once with the extended timeout.

The installer wires three hooks into ~/.claude/settings.json:

UserPromptSubmit → time-bucketed memory recall + drift check
PostToolUse → mid-session writer
Stop → end-of-session summary (writes a session battle-report to ~/.claude/.cache/compass-last-session.txt)

Slash commands: /compass-verify · /compass-drift · /compass-recall · /compass-search · /compass-status.

Any other MCP client

python ~/.claude/plugins/nautilus-compass/scripts/install_to_agent.py

Auto-detects Claude Desktop, Cursor, Cline, Continue.dev, Zed and patches their MCP config. Per-agent copy-paste configs: docs/AGENT_ONBOARDING.md · raw protocol: docs/mcp-usage.md.

Cloud-hosted (open beta · self-serve)

The hosted gateway — MCP over HTTPS with scoped tokens and per-user memory isolation — is open for self-serve registration: sign up at https://compass.nautilus.social/signup, then create a token in the web console (or POST /tokens). Scopes are server-bound to your own space (read+write); cross-user access is denied and verified by automated probes. Design: docs/plans/2026-08-30-multi-tenant-memory-design.md.

MCP endpoint: https://compass.nautilus.social/mcp/ (Bearer token · streamable-http). Also listed in the official MCP Registry as io.github.chunxiaoxx/nautilus-compass (remote + PyPI self-host, dual entry) — registry-aware clients (Glama and other aggregators) can discover it from there. A2A discovery: curl https://compass.nautilus.social/.well-known/agent.json

Nautilus platform agents (cloud ssh quickstart)

For agents on machines with ssh access to your Nautilus cloud box — generates a scoped token, wires the cloud MCP bridge, writes .mcp.json, and runs an end-to-end self-check. Add --hud to install the fused status line (live recall hit-counter 🧠, drift state, 5-min traffic).

bash ~/.claude/plugins/nautilus-compass/ops/agent_quickstart.sh my-agent

Headline numbers

Benchmark	Score	Honest compare

| LongMemEval-S 500q full (utt-routed + hybrid, n=500) | P@1 0.890 · P@5 0.978 · MRR 0.929 | sweeps mem0 2.0.19 (0.774/0.916/0.834, our reproduction, each side on its own default

Only the beginning is shown; read the rest in the repo

Nautilus Compass Memory

Overview

PopNx MCP’s three pillars

What you can do with it

Install

Before you install

Or run it on your computer

Or run it on your computer

Or run it on your computer

Or run it on your computer

Values you fill in

What it can do

Basic checksi

Maker matches the repo

Still maintained

Has a licence

Endpoint responds

Sign-in with OAuth

No hidden instructions in tool descriptions

Compared with others in Search & AI memoryi

Common questions

Alternatives

Context7

Codebase Memory

Exa

README from the maker

nautilus-compass

October 2026 — Independent Judging & Verification (new pillar)

What this is (memory layer, 2026-08 state)

Quickstart

Packages on PyPI

Python package (PyPI · 3.3.0)

ships the CLI, the MCP server, the A2A adapter and session tools:

nautilus-compass · compass-mcp · compass-a2a

compass-drift-history · compass-session-search · compass-session-writer

30 seconds (Claude Code / Desktop · local daemon)

start the BGE-m3 daemon (one-time per boot)

Any other MCP client

Cloud-hosted (open beta · self-serve)

Nautilus platform agents (cloud ssh quickstart)

Headline numbers