Context7
Up-to-date docs for AI agents
作者による説明(英語の原文)
Persistent memory for AI agents: connects MCP clients to your Kemory memory vault
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。
KEMORY_API_KEY「秘密」と表示された値は、あなたのアカウントの鍵です。絶対に人に教えたり、チャットに貼り付けたりしないでください。
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": {
"kemory": {
"command": "npx",
"args": [
"-y",
"kemory",
"mcp",
"serve"
],
"env": {
"KEMORY_API_KEY": "your-value"
}
}
}
}ターミナルでこれを実行します
claude mcp add kemory --env KEMORY_API_KEY=your-value -- npx -y kemory mcp serve動かす前に、空欄の値を入力してください。
プロジェクトの .cursor/mcp.json、または ~/.cursor/mcp.json に貼り付けます
{
"mcpServers": {
"kemory": {
"command": "npx",
"args": [
"-y",
"kemory",
"mcp",
"serve"
],
"env": {
"KEMORY_API_KEY": "your-value"
}
}
}
}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": {
"kemory": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"kemory",
"mcp",
"serve"
],
"env": {
"KEMORY_API_KEY": "your-value"
}
}
}
}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 SeKondBrainAILabs 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。
入力が必要なもの:KEMORY_API_KEY
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(0.19.0)がレジストリに届いたのは12 日前です。
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Node.js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。
The command-line client for Kemory, a persistent memory vault for AI agents. It signs you in, connects MCP clients such as Claude Code, Codex, Cursor and VS Code to your vault, and runs the MCP bridge they use.
You need a Kemory account; sign up at kemory.sekondbrain.ai.
npx -y kemory connect # Node.js 18+
uvx kemory connect # or with uv
Your browser opens to sign in. kemory then lists the AI clients on this machine, [ready] or [connected], and asks once: connect every ready client, choose some, or cancel. Claude Code and Grok Build get the Kemory plugin; Codex, Copilot CLI, Cursor, Gemini CLI, OpenCode and VS Code an MCP entry plus automatic memory; the others an MCP entry. Then the connection is checked. A summary lists what is left to do, such as which clients to restart.
kemory doctor.--dry-run shows what would change without changing anything. In scripts, name the clients instead: --host all, or --host claude-code, --host codex and so on (MCP clients lists them); kemory then asks nothing.
brew install sekondbrainailabs/s9n/kemory
npm install -g kemory uv tool install kemory
Builds exist for macOS (Apple silicon and Intel), Linux (arm64 and x64) and Windows (x64). They are attached to each GitHub release with checksums and build provenance (gh attestation verify --repo SeKondBrainAILabs/kemory-cli). kemory upgrade tells you whether a newer release exists and how to update the copy you installed.
| Command | What it does |
|---|---|
kemory login | Sign in through your browser (OAuth device flow), or --local with an API key |
kemory logout | Remove the cached sign-in for the selected environment |
kemory whoami | Show your account, active organisation and teams |
kemory mcp serve | The stdio MCP bridge an MCP client launches |
kemory hook session-start, hook capture | What a coding agent's hooks run: load your Kemory context when a session starts, save the session when it ends (Hooks) |
kemory connect | Sign in if needed, wire an MCP client and check the connection |
kemory connect copilot-cloud | Give GitHub Copilot's cloud agent automatic memory in the current repository (Copilot cloud agent) |
kemory mcp install | Write the kemory entry into MCP clients (--host all for every installed one) |
kemory doctor | Check sign-in, network, API and MCP clients; --fix wires or cleans them |
kemory orgs, kemory use | List your organisations and switch the active one |
kemory remember, recall, ls, show, forget | Store, search, read and delete memories |
kemory ask | Ask your vault a question and get an answer with its evidence |
kemory namespaces, kemory export | List namespaces, export the whole vault as JSON |
kemory stats | Recall usage and its token cost; stats memories for what is never recalled or rated down |
kemory keys | Create, rotate, approve, revoke, delete and list API keys for agents |
kemory upgrade, telemetry, completion | Check for a newer CLI, set your analytics preference, shell completion |
Every command accepts --output json for scripts and agents (stdout then carries only the JSON payload), --quiet, --no-color and --env .
kemory connect --host and kemory mcp install --host connect one client, and --host all connects every client installed on this machine.
For Claude Code and Grok Build they install the Kemory plugin through the client's own claude or grok command. Its hooks save each session to Kemory, and in Claude Code also load your memory when a session starts. Without that command, or for an environment other than prod, they write the MCP entry instead.
For Codex they also add hooks to ~/.codex/hooks.json that load your memory when a session starts and save the session as it goes (Hooks). Codex runs a new hook only after you approve it, so open Codex once and approve them with /hooks. Your other hooks in that file are left as they are.
For Cursor they add the same hooks to ~/.cursor/hooks.json, and for Gemini CLI to the hooks in ~/.gemini/settings.json. Both run them without asking, and your other hooks are left as they are.
For VS Code and the Copilot CLI they write ~/.copilot/hooks/kemory.json, which both run (in VS Code through the chat.useHooks setting, on by default). kemory owns that file and rewrites it on every connect.
For OpenCode they add the opencode-kemory plugin to the plugin list in opencode.json, which OpenCode installs from npm. It does the same: it adds your memory to the system prompt when a session starts and saves your prompts as the session goes. Connected to an environment other than the default, they write the plugin as ~/.config/opencode/plugins/kemory.js instead, which connecting again replaces, so keep your own plugins in other files.
For every other client they write an MCP entry. The entry only starts kemory mcp serve; no token or key is written into the client's config, and everything else in the file is left as it was.
--host | Client | Config file (macOS and Linux) |
|---|---|---|
claude-code | Claude Code | ~/.claude.json |
claude-desktop | Claude Desktop | ~/Library/Application Support/Claude/claude_desktop_config.json |
codex | OpenAI Codex | ~/.codex/config.toml, plus memory hooks in ~/.codex/hooks.json (or under $CODEX_HOME) |
cursor | Cursor | ~/.cursor/mcp.json, plus memory hooks in ~/.cursor/hooks.json |
vscode | VS Code (Copilot agent mode) | ~/Library/Application Support/Code/User/mcp.json, ~/.config/Code/User/mcp.json, plus memory hooks in ~/.copilot/hooks/kemory.json |
copilot-cli | GitHub Copilot CLI | ~/.copilot/mcp-config.json (or under $COPILOT_HOME), plus memory hooks in ~/.copilot/hooks/kemory.json |
copilot-jetbrains | GitHub Copilot in JetBrains IDEs | ~/.config/github-copilot/intellij/mcp.json (%LOCALAPPDATA%\github-copilot\intellij\mcp.json on Windows) |
junie | Junie, in JetBrains IDEs and the Junie CLI | ~/.junie/mcp/mcp.json |
gemini-cli | Gemini CLI | ~/.gemini/settings.json, with the memory hooks in the same file |
antigravity | Google Antigravity | ~/.gemini/config/mcp_config.json |
windsurf | Windsurf / Devin Desktop | ~/.config/devin/mcp_config.json, or ~/.codeium/windsurf/mcp_config.json for older installs |
cline | Cline | the VS Code extension's cline_mcp_settings.json, or ~/.cline/data/settings/cline_mcp_settings.json |
kiro | Kiro | ~/.kiro/settings/mcp.json |
grok | Grok CLI | ~/.grok/config.toml |
continue | Continue (discontinued in 2026; kept working where it is still installed) | ~/.continue/mcpServers/kemory.json |
droid | Factory Droid | ~/.factory/mcp.json, plus memory hooks in ~/.factory/hooks.json (or the hooks in ~/.factory/settings.json when you keep yours there) |
zed | Zed | ~/.config/zed/settings.json (%APPDATA%\Zed\settings.json on Windows), under context_servers; your comments in the file are kept |
warp | Warp | ~/.warp/.mcp.json |
opencode | OpenCode | ~/.config/opencode/opencode.json, plus opencode-kemory in its plugin list |
On Windows the files under Library/Application Support and .config live in %APPDATA% instead, except OpenCode's, which stay in ~\.config\opencode. Grok also reads ~/.claude.json, so the claude-code entry reaches it too.
Each client should reach Kemory one way. Two ways give it every Kemory tool twice, which costs context in every session.
| Client | Connect it with |
|---|---|
| claude.ai, Claude Desktop and Claude mobile | The claude.ai connector, added from the Kemory dashboard |
| Claude Code and Grok Build | The Kemory plugin, which kemory connect installs |
| Everything else in the table above | kemory connect --host |
connect and mcp install write nothing for a client that already has Kemory: Claude Code or Grok Build with the Kemory plugin enabled, or Claude Desktop when your account has a claude.ai connector in use. kemory doctor reports a kemory entry that duplicates either one, and kemory doctor --fix removes it.
Claude Desktop rewrites its config file from memory while it runs, which drops an entry added or removed in the meantime. When its config has to change while it is open, connect, mcp install and doctor --fix offer to quit it, make the change and open it again (doctor --fix --yes does so without asking). Run from the terminal inside the Claude app, which would close with it, they offer to open Terminal and continue there instead (macOS).
GitHub Copilot's cloud agent works in a sandbox where no one signs in, so it reaches Kemory with an API key. Run kemory connect copilot-cloud in the repository it works on, with gh signed in. It:
.github/hooks/kemory.json, the hooks that load your memory when a session starts and save the session (commit and push it);KEMORY_API_KEY (for the hooks) and COPILOT_MCP_KEMORY_API_KEY (for the MCP server);Without gh it prints the key once, to add as both secrets yourself. The hooks also take KEMORY_API_KEY anywhere else no one signs in.
Scripts and agents can act on why a command failed:
| Code | Meaning |
|---|---|
| 0 | Success |
| 1 | Failure that fits no category below |
| 2 | Invalid invocation |
| 3 | Not signed in, or the sign-in was rejected — run kemory login |
| 4 | Kemory could not be reached; nothing ran on the server |
| 5 | Signed in but not allowed (403) |
| 6 | Not found (404) |
| 7 | Conflict with existing state (409) |
| 8 | Rate limited (429) |
| 9 | Kemory is up but temporarily unavailable (503) |
| Variable | Effect |
|---|---|
KEMORY_ENV | Environment to use: prod (default), india, local, or one from the environments file |
KEMORY_URL | Use this Kemory API host instead of the environment's |
KEMORY_OIDC_ISSUER, KEMORY_CLI_CLIENT_ID | Identity provider and client for self-hosted Kemory |
KEMORY_API_KEY | mcp serve authenticates with this key instead of your sign-in |
KEMORY_HTTP_TIMEOUT | Seconds mcp serve waits for Kemory (default 120) |
KEMORY_OUTPUT | text or json, like --output |
NO_COLOR | Disable colour |
| KEMORY_ACCESSIBLE=1 | Plain numbered p
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