Context7
Up-to-date docs for AI agents
作者提供的说明(英文原文)
Local-first agent memory with verified backup rotation and explicit project isolation.
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。
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。
选择你使用的 AI 应用,然后复制设置。
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 …”。
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。
ARIADNE_QDRANT_HOST envARIADNE_QDRANT_PORT envARIADNE_OLLAMA envARIADNE_MODEL envARIADNE_COLLECTION env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。
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
注册名称已通过 GitHub 账户 mclaut 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
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。
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。
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)。
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。
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。
同一分类中有:Context7, Codebase Memory, Exa
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
Up-to-date docs for AI agents
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
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。
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.
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.
previous-runtime copies join the canonical one-copy retention policy.backup-retention runtime-cleanup.approval_id. Tests verify successful continuation and rejection of reused one-time grants.ariadnectl approvals --all lists retained requests and their lifecycle without authorizing or consuming access.Ariadne.app in the system Applications folder when writable, with a user-level ~/Applications fallback and a native project icon.v0.8.14 detached the confirmed macOS update helper from tray shutdown and made the handoff observable in update.log.
v0.8.13 makes a consolidation deadline safe deferred work rather than a maintenance failure, preserving every source diary with append-only deferred metadata.
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.
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.
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.
ariadnectl status, the tray, and the full-stack doctor report Qdrant's open descriptors and configured limit, with a visible warning before exhaustion.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.internal/maintenance; ariadnectl retains its established CLI and activity semantics.make clean archives generated assets with a recovery manifest instead of deleting them.brew is absent from launchd's minimal PATH, so both Qdrant and Ollama actually restart.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.ariadnectl status expose service PIDs; structured logs include duration, before/after state, command output, and the exact verification failure.start, stop, and restart propagate platform errors to the CLI and tray instead of displaying success.startup, resume, clear, compact, and fork, and injects an explicit reminder to save durable decisions, gotchas, and verified outcomes immediately.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