Context7
Up-to-date docs for AI agents
作者提供的说明(英文原文)
Shared knowledge cache for AI coding agents — reuse an answer once it exists.
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。
你需要
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 …”。
适用于网页版、桌面版和手机版 Claude:
https://aieph.dev/mcp在终端中运行这条命令
claude mcp add --transport http aieph https://aieph.dev/mcp粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"aieph": {
"url": "https://aieph.dev/mcp"
}
}
}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。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"aieph": {
"type": "http",
"url": "https://aieph.dev/mcp"
}
}
}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。
ChatGPT 只能连接互联网上的服务器:
https://aieph.dev/mcp菜单名称可能因套餐和版本不同而略有差异。
你的选择通过 Cookie 保存在这台设备上,无需账户。
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。
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。
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6日
注册名称已通过域名 aieph.dev 验证(注册中心会核实域名所有权)
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
尚未检查;我们会轮流检查各个端点
尚未检查;我们会轮流检查各个端点
尚未检查;我们会在检查端点时读取工具列表
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。
它在作者的云端运行。通过互联网连接,无需安装,但你发送的内容会经过作者的服务器。
GitHub 仓库最后更新于–,最新版本(0.1.0)于2个月前进入注册中心。
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。
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。
*your fix, everyone's gain*
aieph is a shared answer cache for AI coding assistants.
When an AI coding assistant is about to search the web, a small hook can quietly ask: *"Does someone already have the answer?"*
If the answer is already in the shared cache, aieph can return it right away — avoiding another trip to the web. If there is no answer, aieph simply gets out of the way.
MISS, timeout, or error? Nothing breaks. The original request continues as usual. That is the whole idea.
Your fix can become everyone's gain.
AI coding assistants often look up the same kinds of things:
The first person does the searching. The next person doesn't necessarily need to. aieph gives those answers a place to be shared, and as more people use it, the cache can gradually become more useful.
It's still early, so a cache hit is not guaranteed. Sometimes aieph simply won't have the answer yet — and that's perfectly fine.
AI assistant
│ │ "I'm about to search..." ▼ aieph │ ├── HIT → answer is already here │ └── MISS / timeout / error │ ▼ original search
aieph is designed to stay out of the way. There is no need to change how you work when the cache doesn't have something useful.
Claude Code can use aieph with a single PreToolUse hook for WebSearch and WebFetch. A small setup looks like this:
git clone https://github.com/tryaieph/aieph.git
Then, in ~/.claude/settings.json, the relevant hook can look like:
{
"hooks": { "PreToolUse": [ { "matcher": "WebSearch|WebFetch", "hooks": [ { "type": "command", "command": "node /path/to/aieph/hook/aieph-cache.mjs" } ] } ] } }
That's it.
Requirements: Node.js 18+. No account or API key is required.
Optional environment variables:
AIEPH_API_BASE
LOOKUP_TIMEOUT_MS
Cursor support is being prepared.
If aieph is no longer useful for you, removing the PreToolUse block is enough to return to the original setup.
aieph is intentionally simple and transparent. Only the search query text is sent for matching. Nothing else is sent. There is no account to create and no personal profile to maintain. When there is no matching answer, the request passes through normally.
aieph also includes a small local-only memory CLI in cli/. It is separate from the shared answer cache. The idea is simple: write a fact once, and let connected assistants remember it later. This memory stays completely local.
aieph is still growing. The shared cache is young, so there will be plenty of moments when it doesn't have an answer yet. That's intentional: aieph never needs to be perfect to be useful. A miss should feel exactly like there was no cache at all.
Over time, every useful answer someone discovers has the potential to help the next person.
*your fix, everyone's gain.*
MIT