Context7
Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.
Description from the maker (original English)
Shared knowledge cache for AI coding agents — reuse an answer once it exists.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Works in Claude on the web, desktop and mobile:
https://aieph.dev/mcpRun this in your terminal
claude mcp add --transport http aieph https://aieph.dev/mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"aieph": {
"url": "https://aieph.dev/mcp"
}
}
}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.
Paste into .vscode/mcp.json in your project
{
"servers": {
"aieph": {
"type": "http",
"url": "https://aieph.dev/mcp"
}
}
}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.
ChatGPT connects only to servers on the internet:
https://aieph.dev/mcpMenu names can differ slightly by plan and over time.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
We have not read this server’s tool list yet; we check endpoints in rotation.
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 6, 2026
The registry name was verified against the domain aieph.dev (the registry checks domain ownership)
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Not checked yet; we check endpoints in rotation
Not checked yet; we check endpoints in rotation
Not checked yet; we read the tool list when we check the endpoint
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
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.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
The GitHub repo last changed –, and the latest version (0.1.0) reached the registry 2 months ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.
In the same category: Context7, Codebase Memory, Exa
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
Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.
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.
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.
*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