Nautilus Compass Memory

Name: Nautilus Compass Memory
Author: chunxiaoxx

作者：chunxiaoxx版本 3.2.0i★ –i电脑或云端

注册名称io.github.chunxiaoxx/nautilus-compass

安装

概览

作者提供的说明（英文原文）

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

PopNx MCP 的三大支柱

这三项永远不会合并成一个分数：意见、测量和人气是不同的东西。

用户评价i暂无评价评价功能将在后续阶段与账户功能一起开放
我们的基础检查i1 项中通过 1 项依据公开信息检查；尚未扫描代码
使用情况i尚未统计★ –

它能帮你做什么

我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。

连接方式: 电脑或云端
传输方式: stdio, Streamable HTTP
分类: 搜索与 AI 记忆
你需要填写：Authorization

安装

选择你使用的 AI 应用，然后复制设置。

安装之前

基础检查：1 项中通过 1 项
在作者的服务器上运行：你向它提出的内容会经过他们的服务器。
需要你自己填写： Authorization

标为机密的值是你账户的钥匙。千万不要分享给别人，也不要粘贴到聊天里。

你需要

在云端运行无需安装任何东西，通过互联网连接
PyPI已安装 Python 的 uv（用于 uvx 命令）

你用的是哪个应用？

ClaudeClaude CodeCursorVS CodeChatGPT

在上方选择你的应用。我们会记住它，下次按钮会显示“安装到 …”。

这个地址需要在请求的 header 中放入密钥，而添加连接器的菜单无法设置。请改用 Claude Code、Cursor 或 VS Code。

或者在你的电脑上运行

打开 Claude Desktop → Settings → Developer → Edit Config，把下面的内容粘贴到 claude_desktop_config.json

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

在终端中运行这条命令

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

或者在你的电脑上运行

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

运行前请先填写空着的值。

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json，或 ~/.cursor/mcp.json

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

或者在你的电脑上运行

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json，或 ~/.cursor/mcp.json

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

浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

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

或者在你的电脑上运行

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

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

浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。

这个地址需要在请求的 header 中放入密钥，而添加连接器的菜单无法设置。请改用 Claude Code、Cursor 或 VS Code。

你的选择通过 Cookie 保存在这台设备上，无需账户。

需要你填写的值

Authorization 机密必填 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.

这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同，请以 README 为准。

它能做什么

我们还没有读取这个服务器的工具列表；我们会轮流检查各个端点。

基础检查i

我们检查的是任何人都能看到的信息；我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月7日

✓ 通过
作者与仓库一致
注册名称已通过 GitHub 账户 chunxiaoxx 验证，该账户拥有此仓库
… 尚未检查
仍在维护
我们还没有从 GitHub 读取这个仓库
… 尚未检查
有许可证
我们还没有从 GitHub 读取这个仓库
… 尚未检查
端点有响应
尚未检查；我们会轮流检查各个端点
… 尚未检查
使用 OAuth 登录
尚未检查；我们会轮流检查各个端点
… 尚未检查
工具描述中没有隐藏指令
尚未检查；我们会在检查端点时读取工具列表

与“搜索与 AI 记忆”中的其他服务器比较i

星标数多于此分类中其他 5654 个服务器的 0%
发布到注册中心的时间比此分类中其他 5654 个服务器的 44% 更新
基础检查结果等于或优于此分类中其他 5654 个服务器的 100%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时，星标数才计入。

常见问题

Nautilus Compass Memory 安全吗？

它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前，请先看看这个服务器要求哪些权限，并使用只具备所需权限的密钥。

它需要哪些密钥或代码？

你需要填写：Authorization

它在我的电脑上运行还是在云端？

两种方式都可以：安装在你的电脑上，或者连接云端版本。

它还在维护吗？

GitHub 仓库最后更新于–，最新版本（3.2.0）于2个月前进入注册中心。

哪些应用可以使用它？

支持 MCP 的应用，例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接，所以接受远程 MCP 服务器的应用也可以使用，例如开启开发者模式的 ChatGPT。

有什么可以替代它？

同一分类中有：Context7, Codebase Memory, Exa

替代选择

同一分类中其他作者的服务器，按星标数排序。

如何看卡片：★ GitHub 星标i三大支柱：评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

Context7

作者：upstash

Up-to-date docs for AI agents

电脑或云端★ 64,224MIT昨天更新

安装

Codebase Memory

作者：DeusData

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

在你的电脑上运行★ 48,148MIT21天前更新

安装

Exa

作者：exa-labs

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

在云端运行★ 5,213MIT2个月前更新

安装

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

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

只显示了开头部分；其余内容请在仓库中阅读

Nautilus Compass Memory

概览

PopNx MCP 的三大支柱

它能帮你做什么

安装

安装之前

或者在你的电脑上运行

或者在你的电脑上运行

或者在你的电脑上运行

或者在你的电脑上运行

需要你填写的值

它能做什么

基础检查i

作者与仓库一致

仍在维护

有许可证

端点有响应

使用 OAuth 登录

工具描述中没有隐藏指令

与“搜索与 AI 记忆”中的其他服务器比较i

常见问题

替代选择

Context7

Codebase Memory

Exa

作者的 README

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