原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。评价和账户功能将在后续阶段推出。
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚

Ariadne

作者:mclaut版本 0.8.25i★ –i在你的电脑上运行
注册名称io.github.mclaut/ariadne

安装

概览

作者提供的说明(英文原文)

Local-first agent memory with verified backup rotation and explicit project isolation.

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。

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: 在你的电脑上运行
  • 传输方式: stdio
  • 分类: 搜索与 AI 记忆

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
  • 在你的电脑上运行,拥有你的用户账户的权限(文件、网络、应用)。
  • 需要你自己填写: ARIADNE_QDRANT_HOST, ARIADNE_QDRANT_PORT, ARIADNE_OLLAMA, ARIADNE_MODEL, ARIADNE_COLLECTION

你用的是哪个应用?

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 …”。

下载作者的 .mcpb 文件

链接指向作者自己的文件;我们不托管也不重新打包它。打开文件后,Claude Desktop 会进行安装。

在终端中运行这条命令

运行前请先填写空着的值。

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。

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。

这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。

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

  • ARIADNE_QDRANT_HOST env
    Qdrant host
  • ARIADNE_QDRANT_PORT env
    Qdrant gRPC port
  • ARIADNE_OLLAMA env
    Ollama API URL
  • ARIADNE_MODEL env
    Embedding model
  • ARIADNE_COLLECTION env
    Qdrant collection

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

它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。

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 mclaut 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

  • – 不适用

    端点有响应

    它在你的电脑上运行,没有互联网端点

  • – 不适用

    使用 OAuth 登录

    在你的电脑上运行,改用本地设置

  • … 尚未检查

    工具描述中没有隐藏指令

    它在你的电脑上运行;我们只能读取互联网端点的工具列表

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 7275 个服务器的 0%
  • 发布到注册中心的时间比此分类中其他 7275 个服务器的 83% 更新
  • 基础检查结果等于或优于此分类中其他 7275 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

Ariadne 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?

注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。

它在我的电脑上运行还是在云端?

它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。

它还在维护吗?

GitHub 仓库最后更新于–,最新版本(0.8.25)于7天前进入注册中心。

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。你的电脑上还需要有 MCPB。

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★ 5,213MIT上个月更新
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。

ariadne

English · [Українська](README.uk.md)

A native, local-first, multilingual memory server for Codex, Claude Code, and any MCP client. Go + Qdrant + bge-m3 — no Docker, no cloud, no API keys.

Purpose-built for private coding-agent memory: a small native appliance rather than a hosted, multi-tenant memory platform. The default path is offline and cross-lingual, with observable retrieval cost and no account dependency.

[Project site](https://mclaut.github.io/ariadne/) · [Hugging Face Space](https://huggingface.co/spaces/mclaut/ariadne) · [Latest release](https://github.com/mclaut/ariadne/releases/latest)

Built as a replacement for embedded vector-DB memory backends that crash or starve under several concurrent MCP sessions. ariadne is a server: one Qdrant handles concurrent writes natively, so the whole single-writer / lock-starvation class simply doesn't exist.

What's New in v0.8.25

With a declared full-backup plan, the only retained recovery set is backups/previous/full. Collection snapshots are captured inside that set; upgrades and client integration reuse its verified recovery proof instead of creating separate runtime or configuration copies. Existing component copies require an explicit cleanup plan and are not silently removed. Audit remains outside rotation.

Previously in v0.8.24

  • Legacy runtime copies rotate too. Release-local previous-runtime copies join the canonical one-copy retention policy.
  • Restore before removal. The retained runtime is independently copied, checksum-verified and version-probed before obsolete copies expire.
  • Audit remains available. Old manifests, application metadata, sidecar history and a complete retired-file inventory are preserved separately. Active, changed, newer or unknown copies block cleanup.
  • Repeatable migration. Backup, upgrades and same-version reinstalls run the migration; an explicit retry is available through backup-retention runtime-cleanup.

Previously in v0.8.23

  • Full sets rotate too. An explicit full-backup plan retains one independently restored full recovery set. The previous full set expires only after recovery passes; its audit is preserved separately.
  • One verified copy per component. Configured Qdrant collections retain one recovery snapshot. Upgrades keep one previous runtime and one previous copy of each changed client configuration.
  • Recovery checked before rotation. Snapshot size and SHA-256 must match Qdrant; an isolated local Qdrant restores the snapshot, checks the source count and vector schema, and reads every point with its payload and vectors.
  • Bounded backup storage. After successful verification, older matching downloaded/archive snapshots and redundant native snapshots expire automatically. Older historical backup states are intentionally discarded.
  • Working state stays available. Live memory, session data, access-request history and audit logs remain outside rotation. Modified or in-use previous generations block replacement.

Previously in v0.8.18

  • Decisions first. The access section sits near the top of the tray. Only requests that need a decision appear in the active queue.
  • History in pages. Retained decisions appear newest first, ten records per page. New requests no longer hide below a long flat history.
  • Readable rows. Purpose and a short status are visible immediately; full project scope, resource, creation time, and ID are in details.
  • Exact request actions. Approve and Deny stay bound to a specific request. History rows are read-only, and every audit record is preserved.

Previously in v0.8.17

  • Every access request stays visible. The tray lists the entire retained queue and history with pending, approved, denied, expired, and consumed statuses, plus actions bound to each request ID.
  • Prompts rotate fairly. Each system dialog is bounded to 30 seconds; unanswered requests remain pending, and newer requests get a turn.
  • Continuation is explicit. Approval tells the client to retry with approval_id. Tests verify successful continuation and rejection of reused one-time grants.
  • Read-only history. ariadnectl approvals --all lists retained requests and their lifecycle without authorizing or consuming access.

Previously in v0.8.16

Fixed
  • Windows release checks include the launcher safely. The macOS behavior tests are now platform-scoped while release archives retain a Windows-safe launcher stub, so every supported target builds and tests cleanly.
Added in v0.8.15
  • Ariadne is now a real macOS application. The installer creates a signed Ariadne.app in the system Applications folder when writable, with a user-level ~/Applications fallback and a native project icon.
  • One click restores the managed tray. Finder, Spotlight, or Launchpad now starts the existing tray LaunchAgent, re-registering its canonical plist when needed without creating an unmanaged duplicate process.

Previously in v0.8.14

v0.8.14 detached the confirmed macOS update helper from tray shutdown and made the handoff observable in update.log.

Previously in v0.8.13

v0.8.13 makes a consolidation deadline safe deferred work rather than a maintenance failure, preserving every source diary with append-only deferred metadata.

Previously in v0.8.12

v0.8.12 bounded the maintenance supervisor, made schema-bound consolidation JSON deterministic for reasoning-capable Ollama models, and added exact, append-only owner-approved credential trust.

Previously in v0.8.11

v0.8.11 made the desktop tray truly single-instance, reconciled canonical and historical launchd ownership, preserved superseded plist files in an archive, and added real tray-process diagnostics.

Previously in v0.8.10

v0.8.10 made token attribution auditable with lossless Qdrant pagination, recallable-versus-history coverage, separated measured and estimated provenance, explicit gap classification, and safe opt-in attribution backfill.

Previously in v0.8.9

Fixed
  • Qdrant remains available with many concurrent agent sessions. Each MCP process now uses one persistent gRPC connection instead of the client library's implicit pool of three, while the macOS launchd service receives an explicit 8192-file descriptor limit instead of inheriting 256.
  • Startup no longer hammers payload-index creation. Ariadne inspects the existing schema and creates only missing indexes. Real storage errors now fail startup instead of being silently ignored.
  • Every short-lived client closes cleanly. Hooks, import, install, and maintenance release their Qdrant connection when they finish.
Added
  • Descriptor-pressure visibility. ariadnectl status, the tray, and the full-stack doctor report Qdrant's open descriptors and configured limit, with a visible warning before exhaustion.

Previously in v0.8.8

Added
  • Fail-closed remote Qdrant authentication. Remote gRPC requires an API key plus TLS; REST requires the same key and HTTPS. Long-running clients retain only a protected key-file path, never the key value. An explicit insecure override remains available for a user-managed SSH or equivalent tunnel.
  • Honest retrieval comparison. cmd/eval now calculates deterministic macro Recall, MRR, and nDCG for judged BM25 and learned-sparse runs instead of claiming a SPLADE improvement without corpus evidence.
Changed
  • Metrics schema v3 scales without discarding history. Every recall event remains append-only, while an indexed 30-day path and transactional daily rollups make lifetime totals bounded and fast. Existing v2 databases migrate without changing raw rows or totals.
  • Collection scans are complete. Memfile reconciliation now pages through every Qdrant point instead of relying on a fixed upper limit.
  • Maintenance has a reusable core. Bounded retry/backoff orchestration lives in internal/maintenance; ariadnectl retains its established CLI and activity semantics.
Fixed
  • Remote settings survive installation and self-update. macOS, Linux, and Windows launchers propagate the same non-secret Qdrant transport settings; explicit Windows installer arguments still take precedence.
  • Repository tooling no longer compiles dependencies from `site/node_modules`. The site is a separate Go module, and make clean archives generated assets with a recovery manifest instead of deleting them.

Previously in v0.8.7

Fixed
  • Tray restart now works under launchd's restricted environment. Ariadne resolves Homebrew from standard macOS locations when brew is absent from launchd's minimal PATH, so both Qdrant and Ollama actually restart.
  • Restart always attempts recovery. ariadnectl restart runs the start phase even when stopping one service reports an error, then returns every failure instead of leaving the stack down after a partial stop.
  • The completion message survives the tray restart. The verified result is appended before the old tray exits; its launchd replacement displays the final notification and appends a delivered marker.
Added
  • Verified service operations. The tray observes Qdrant and Ollama before and after Start, Stop, or Restart, waits for the requested state, verifies PID changes on restart, and refuses to report success while the collection is unhealthy.
  • Visible PID and operation diagnostics. Tray rows and ariadnectl status expose service PIDs; structured logs include duration, before/after state, command output, and the exact verification failure.
Changed
  • Conflicting controls are locked during service work. Start, Stop, Restart, maintenance, update, backup, and export cannot overlap while a service action is in progress.
  • Platform command errors keep their useful output. macOS, Linux, and Windows service-control failures now preserve stderr/stdout for diagnosis.

Previously in v0.8.6

Fixed
  • Tray restarts are reliable on macOS. A launchd-managed tray now asks its supervisor for one clean replacement instead of racing a second menu-bar process and occasionally leaving no icon.
  • Service failures are reported honestly. start, stop, and restart propagate platform errors to the CLI and tray instead of displaying success.
  • Claude upgrades no longer leave stale integration files. The installer validates and refreshes the shipped skill plus exact hook paths, matchers, and timeouts.
Added
  • Persistent recall across Claude context transitions. Auto-recall now runs for startup, resume, clear, compact, and fork, and injects an explicit reminder to save durable decisions, gotchas, and verified outcomes immediately.
Changed
  • Approval is always a deliberate click. System warnings contain only Approve and Deny; neither is default or focused, and Return/Enter or Escape cannot decide or dismiss the request.
  • Hook installation is update-aware. Existing Ariadne hooks are updated in place while unrelated Claude hooks are preserved.

Previously in v0.8.5

The macOS approval warning comes to the foreground. The native dialog activates before it is displayed, so an access request cannot sit unnoticed behind the active coding window. Activation changes visibility, never authority.

Hugging Face publishing is valid. Th

只显示了开头部分;其余内容请在仓库中阅读

问 PopNx