Is the nautilus-compass MCP server actively maintained?

The nautilus-compass MCP server was last committed 29d ago and has 2 contributors. Issue health: 0% of issues resolved. AgentRank freshness score reflects real-time maintenance activity.

nautilus-compass MCP Server

Name: chunxiaoxx/nautilus-compass
Rating: 3.3 (1 reviews)
Author: chunxiaoxx

chunxiaoxx/nautilus-compass

Score: 56.4 Rank #8294 Search & RAG

[![AgentRank](https://agentrank-ai.com/api/v1/badge/chunxiaoxx--nautilus-compass)](https://agentrank-ai.com/tool/chunxiaoxx--nautilus-compass/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)

Are you the maintainer of chunxiaoxx/nautilus-compass? Claim this listing →

Open memory & reliability layer for AI agents + independent judging/verification (NACRE judge, caliber-bench meta-benchmark, preregistered criteria) — by Nautilus Platform

Add AgentRank to Claude Code Discover and compare tools like chunxiaoxx/nautilus-compass — your AI finds the right one automatically

Get API Access →

claude mcp add agentrank -- npx -y agentrank-mcp-server

Overview

chunxiaoxx/nautilus-compass is a Python tool. Open memory & reliability layer for AI agents + independent judging/verification (NACRE judge, caliber-bench meta-benchmark, preregistered criteria) — by Nautilus Platform Topics: a2a, agent-memory, agentic-ai, claude-code, cross-agent, mcp, nautilus, llm, local-first, long-term-memory, memory-layer, rag.

Ranked #8294 out of 24846 indexed tools.

Has 1,260 GitHub stars.

Ecosystem

Python NOASSERTION 97 pypi/wk

a2aagent-memoryagentic-aiclaude-codecross-agentmcpnautilusllmlocal-firstlong-term-memorymemory-layerrag

Score Breakdown

Stars 15% 1,260

1,260 stars → well-known project

Freshness 25% 29d ago

Last commit 29d ago → recently updated

Issue Health 25% 0%

0/32 issues closed → many open issues

Contributors 10% 2

2 contributors → solo project

Dependents 25% 0

No dependents → no downstream usage

npm Downloads N/A

PyPI Downloads 13% 97/wk

97 weekly installs → early adoption

Forks 36

Description Detailed

License NOASSERTION

Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →

How to Improve

License low impact

Add an MIT or Apache-2.0 license to signal trust and enable adoption

Issue Health high impact

You have 32 open vs 0 closed issues — triaging stale issues improves health

Dependents medium impact

No downstream dependents detected yet — adoption by other projects is the strongest trust signal

Badge all embed codes →

Markdown

[![AgentRank](https://agentrank-ai.com/api/v1/badge/chunxiaoxx--nautilus-compass)](https://agentrank-ai.com/tool/chunxiaoxx--nautilus-compass/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)

HTML

<a href="https://agentrank-ai.com/tool/chunxiaoxx--nautilus-compass/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/v1/badge/chunxiaoxx--nautilus-compass" alt="AgentRank"></a>

Embed Widget docs →

HTML

<script src="https://agentrank-ai.com/embed.js" data-tool="chunxiaoxx/nautilus-compass"></script>

Details

Stars: 1,260
Forks: 36
Open Issues: 32
Closed Issues: 0
Contributors: 2
Dependents: —
Language: Python
License: NOASSERTION
Last Commit: 29d ago

Matched Queries

topic:mcp

From the README

# 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 →](https://nautilus.social)

🇬🇧 English (this file) · [🇨🇳 中文](README.zh-CN.md)

---

## What this is (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
embeddi

Read full README on GitHub →