Context7
Up-to-date docs for AI agents
作者による説明(英語の原文)
One searchable memory of your Claude.ai chats and Claude Code sessions, served over MCP.
この3つを1つのスコアにまとめることはしません。意見、測定、人気はそれぞれ別のものだからです。
このサーバーのやさしい解説はまだ書いていません。以下はレジストリから読み取った事実です。
使っているAIアプリを選んで、設定をコピーしてください。
必要なもの
どのアプリを使っていますか?
上でアプリを選んでください。選んだアプリを覚えておくので、次からはボタンに「…にインストール」と表示されます。
Claude Desktop → Settings → Developer → Edit Config を開き、claude_desktop_config.json にこれを貼り付けます
{
"mcpServers": {
"memex": {
"command": "uvx",
"args": [
"memex-chats"
]
}
}
}ターミナルでこれを実行します
claude mcp add memex -- uvx memex-chatsプロジェクトの .cursor/mcp.json、または ~/.cursor/mcp.json に貼り付けます
{
"mcpServers": {
"memex": {
"command": "uvx",
"args": [
"memex-chats"
]
}
}
}ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。
プロジェクトの .vscode/mcp.json に貼り付けます
{
"servers": {
"memex": {
"type": "stdio",
"command": "uvx",
"args": [
"memex-chats"
]
}
}
}ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。
これはパソコンで動くサーバーですが、ChatGPTがつなげるのはインターネット上のサーバーだけです。ほかのアプリを選んでください。
選んだアプリは、この端末のCookieに保存されます。アカウントは不要です。
この設定は、作者のレジストリ登録情報から作成しています。READMEと違う場合は、READMEに従ってください。
パソコンで動くサーバーです。インストールすると、ツール一覧がAIアプリに表示されます。
誰でも見られる情報をチェックしており、コードは読んでいません。当てはまらない項目は数に入れていません。 · 2026年11月7日にチェック
レジストリ名は、リポジトリを所有するGitHubアカウント dioniipereyraa で確認済みです
このリポジトリはまだGitHubから読み取っていません
このリポジトリはまだGitHubから読み取っていません
これはパソコンで動くため、インターネット上のエンドポイントはありません
パソコンで動き、代わりにローカルの設定を使います
パソコンで動くサーバーです。ツール一覧を読み取れるのは、インターネット上のエンドポイントがある場合だけです
レジストリでこのカテゴリにある有効なすべてのサーバーと比較しています。スターは、公開者がリポジトリの所有者である場合だけ数えます。
当てはまる基本チェック1項目のうち1項目に合格しました。コードは読んでいません。キーやトークンを追加する前に、サーバーがどんなアクセスを求めているかを確認し、必要な権限だけを持つキーを使ってください。
レジストリには必須のキーは載っていません。ただし、最初に使うときにサインインを求めるサーバーもあります。
あなたのパソコンで動きます。必要なときにAIアプリが起動し、データは作者のサーバーを通りません(サーバー自体がオンラインサービスを呼び出す場合を除きます)。
GitHubリポジトリの最終更新は–、最新バージョン(0.2.3)がレジストリに届いたのは5 か月前です。
Claude Desktop、Claude Code、Cursor、VS CodeなどのMCP対応アプリで使えます。パソコンにPython (uv)も必要です。
同じカテゴリには:Context7, Codebase Memory, Exa
同じカテゴリで、ほかの作者が作ったサーバー。スターの多い順。
カードの見方:★ GitHubスターi3つの柱:レビュー · チェック · 利用状況i更新=最新バージョンをレジストリに公開した日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.
作者のリポジトリから書かれたとおりにコピーしたものです。PopNx MCPは内容を確認・推奨していません。HTML、画像、スクリプトは取り除いています。リンクはこのサイトの外へ移動します。
Your Claude.ai chats and your Claude Code sessions live in two worlds that never talk. Memex makes them one memory you can search from both.
Local-first MCP server that indexes your Claude.ai chat history and your local Claude Code / terminal sessions, and exposes them to Claude Code (stdio) and Claude.ai (remote MCP connector).
Status: alpha, 0.3.1 on PyPI. Phases 0 to 7 closed, security-audited (plus four adversarial red-team rounds). Shipped: hybrid search, live capture, auto-summaries, chat ↔ repo association, the Claude.ai remote connector (GitHub OAuth), Claude Code / terminal ingestion with secret redaction, one-command setup, cross-platform autostart, and one-click claude.ai history backfill.
*End-to-end demo: from Claude Code, you ask about something you discussed on claude.ai. Memex searches your chat history (search_chats) and Claude answers from the real conversation. No copy-paste, no manual context handoff.*
One command installs uv + Memex and runs memex setup (registers the MCP server, installs the always-on capture service, indexes your local sessions, prints the pairing token):
# macOS / Linux
curl -LsSf https://raw.githubusercontent.com/dioniipereyraa/memex/main/scripts/install-pypi.sh | sh
# Windows (PowerShell)
powershell -ExecutionPolicy ByPass -c "irm https://raw.githubusercontent.com/dioniipereyraa/memex/main/scripts/install-pypi.ps1 | iex"
Then the one browser step a terminal cannot do: install the Chrome extension, paste the token it printed, and click "Backfill claude.ai history". Other paths (pipx, uv tool install, from source) are under Installation.
Brainstorming and planning happen in Claude.ai. Execution happens in Claude Code. The two worlds do not talk to each other: Claude Code cannot read a chat of yours from Claude.ai, not even the one that originated the task it is currently working on. The memory Anthropic shipped on Claude.ai (March 2026) is curated, not full history, and lives isolated inside Claude.ai.
Memex fills that gap: runs locally, indexes the entire corpus of your chats, and exposes them as MCP tools so Claude can search and pull past context whenever it needs to.
[Claude.ai]
↓ (official JSON export / Chrome ext) [Ingestor] → [SQLite + sqlite-vec] → [local embeddings (fastembed / Ollama)] ↓ [core: storage + retrieval] ↓ [MCP stdio] ───→ Claude Code, Claude Desktop [MCP Streamable HTTP] ─→ Claude.ai connector
Design: pure core (storage, ingest, embeddings, retrieval) decoupled from transport. The same engine serves both stdio and remote MCP without a rewrite.
Installs uv if needed (it brings the right Python), installs Memex from PyPI, and runs memex setup to wire it into Claude Code (MCP server + always-on capture service + local session indexing + the pairing token). No git clone required.
# macOS / Linux
curl -LsSf https://raw.githubusercontent.com/dioniipereyraa/memex/main/scripts/install-pypi.sh | sh
# Windows (PowerShell)
powershell -ExecutionPolicy ByPass -c "irm https://raw.githubusercontent.com/dioniipereyraa/memex/main/scripts/install-pypi.ps1 | iex"
The only step a terminal cannot do is the browser one: install the Chrome extension, paste the token the installer prints, and click "Backfill claude.ai history" to import your history. Embeddings work out of the box (a quantized 130 MB fastembed model downloads on first ingest; no Ollama, no API key).
A plain
pipx install memex-chats(oruv tool install memex-chats) followed
by
memex setupdoes the same thing in two steps. The autostart service is
generated for the wheel install too (launchd / systemd / a logon Scheduled
Task), so no clone is needed for it.
Clone the repo to get an editable install plus the extension source and service templates. You need git; the script installs uv and the pinned Python for you.
git clone https://github.com/dioniipereyraa/memex
cd memex ./scripts/install.sh
install.sh installs uv if you do not have it, runs uv sync, and verifies the install with memex doctor. That is the whole setup.
git clone https://github.com/dioniipereyraa/memex
cd memex powershell -ExecutionPolicy Bypass -File .\scripts\install.ps1
Same three steps as the macOS script (install uv, sync, verify). If git is not installed, get it from git-scm.com first.
# 1. Install uv (skip if you already have it):
git clone https://github.com/dioniipereyraa/memex cd memex uv sync # installs Python 3.13 + dependencies into .venv uv run memex doctor # verify
Upgrade with the same tool that installed it, or the new version will not land on your PATH. A previous install owns the memex executable, so installing again with a different manager fails with "Executables already exist" and memex keeps running the old version. (This is the usual reason memex sync seems to "not exist" after an upgrade: an old pipx-owned memex shadowed a newer uv tool install.)
# 1. Find which tool owns it:
which memex # macOS / Linux Get-Command memex # Windows (PowerShell)
pipx upgrade memex-chats # if pipx owns it uv tool upgrade memex-chats # if uv owns it
If you want to switch managers, uninstall the old one first (pipx uninstall memex-chats or uv tool uninstall memex-chats), then reinstall. After upgrading, memex --version shows the new version and memex doctor should pass.
To make Claude one memory across several machines, install Tailscale first (so each device has a stable private address), then opt in once per device:
memex setup --sync # opt-in, persisted: the always-on service is sync-reachable
It prints the single memex sync connect ... line to run on your other devices. The choice is saved, so the service stays sync-reachable across reboots without re-running anything. Full flow, security model, and the manual one-shot alternative are in Syncing across your devices.
For a dual-boot machine (Linux and Windows that are never on at the same time), use file-based sync instead: memex setup --sync-dir on each OS, pointed at the same folder. No Tailscale, no two devices online at once. See Dual-boot or never-online-together.
The fast path is one command:
uv run memex setup
memex setup wires everything end to end and is safe to re-run: it registers the MCP server with Claude Code (claude mcp add), installs the always-on live-capture service (launchd on macOS, systemd on Linux, a Scheduled Task on Windows), indexes your local Claude Code sessions, and prints the access token to paste into the Chrome extension. Each step degrades to a warning instead of aborting the rest. Flags: --no-mcp, --no-autostart, --no-ingest, --remote (also install the claude.ai connector agent), -y (no prompt).
After that, the only manual step left is installing the Chrome extension and pasting the token, so new chats are captured as you go.
# 1. Request your official Claude.ai export (Settings → Privacy → Export data),
uv run memex ingest /path/to/your-export.zip
uv run memex ingest-claude-code
uv run memex search "your query" -n 5 uv run memex stats
(If you installed with a script, the commands above work as written. If you installed the published PyPI package instead, drop the uv run prefix.)
Where your data lives. From a cloned repo, the database and exports stay
in
/data. From auvx/pipinstall, they go to your OS data
directory (
~/Library/Application Support/memexon macOS,
%LOCALAPPDATA%\memexon Windows,~/.local/share/memexelsewhere). Override
with
MEMEX_DB_PATH/MEMEX_EXPORTS_DIR.memex doctorprints the resolved
path.
Once memex setup finishes, nothing else needs launching: the capture server and the indexers run in the background. You use Memex three ways.
1. From Claude Code (the main way). Setup registers the MCP server, so Claude Code can search your whole history and keep it fresh through these tools:
| Tool | What it does |
|---|---|
search_chats | Semantic + keyword search across your claude.ai chats AND Claude Code sessions |
get_chat | Fetch a full conversation by id |
list_recent_chats | Your most recent conversations |
find_related | Conversations related to a topic or snippet |
index_terminal_sessions | Index your local Claude Code sessions now (so the current one becomes searchable) |
sync_now | Sync with your other devices now (paired peers + the dual-boot shared folder) |
Just ask Claude Code naturally ("what did we decide about X in my claude.ai chats?", "index this session", "sync this to my other devices") and it calls these. index_terminal_sessions and sync_now are local-only (never exposed to the remote claude.ai connector). Note sync_now sends what is already indexed, so to include the session you are in, ask Claude to index_terminal_sessions first. To have context injected automatically at the start of a session, add the optional SessionStart hook.
2. From the terminal. memex search "...", memex stats, memex doctor, memex token (re-print the extension pairing token), memex --version.
3. Capture (automatic, you run nothing). The Chrome extension indexes a claude.ai chat as you open or reload it (and its "Backfill" button imports your old history once); your Claude Code sessions are indexed when a session ends, plus a 15-minute backstop.
| Path | Latency |
|---|---|
| A claude.ai chat into your local index | Near-instant: captured as you open/reload the chat (embedded in seconds) |
| A Claude Code session into your local index | At session end, plus a 15-minute backstop |
| Available to Claude Code on the same machine | Immediate (it reads the same local DB the capture writes) |
| Across devices | Not live. Periodic + overlap: see below |
Same-machine is essentially real-time. Cross-device is not a live relay (it is peer-to-peer with no cloud): paired devices auto-reconcile every 15 minutes while
冒頭だけを表示しています。続きはリポジトリで読めます