Prototype · Preview: every server in the official registry, synced every 30 minutes. Reviews and accounts come in a later step.
PopNx MCPMCP servers for people who use AI · explained in plain words

Ariadne

by mclautversion 0.8.25i★ –iRuns on your computer
Registry nameio.github.mclaut/ariadne

Install

Overview

Description from the maker (original English)

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

PopNx MCP’s three pillars

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

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: Runs on your computer
  • Transport: stdio
  • Category: Search & AI memory

Install

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

Before you install

  • Basic checks: 1 of 1 passed
  • Runs on your computer with your user’s permissions (files, network, apps).
  • You fill in yourself: ARIADNE_QDRANT_HOST, ARIADNE_QDRANT_PORT, ARIADNE_OLLAMA, ARIADNE_MODEL, ARIADNE_COLLECTION

Which app do you use?

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

Download the maker’s .mcpb file

The link goes to the maker’s own file; we do not host or repackage it. Open the file and Claude Desktop installs it.

Run this in your terminal

Fill in the empty values before running it.

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.

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 one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.

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

Values you fill in

  • 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

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

What it can do

Runs on your computer; the tool list appears in your AI app after you install it.

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 mclaut, 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 applicable

    Endpoint responds

    This one runs on your computer; there is no internet endpoint

  • – Not applicable

    Sign-in with OAuth

    Runs on your computer and uses local settings instead

  • … Not checked yet

    No hidden instructions in tool descriptions

    Runs on your computer; we can only read tool lists from internet endpoints

Compared with others in Search & AI memoryi

  • More stars than 0% of the other 7275 servers in this category
  • Published to the registry more recently than 83% of the other 7275 servers in this category
  • Basic checks equal to or better than 100% of the other 7275 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 Ariadne 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?

The registry does not list a required key, though some servers ask you to sign in on first use.

Does it run on my computer or in the cloud?

It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).

Is it still maintained?

The GitHub repo last changed –, and the latest version (0.8.25) reached the registry 7 days ago.

Which apps can use it?

Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need MCPB on your computer.

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 last month
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.

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

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

Ask PopNx