memex-mvp 0.9.0 → 0.9.1

package/HELP.md

@@ -348,7 +348,7 @@ Magic-фича. Когда ты открываешь Claude Code в проект
 
 **Технически:** SessionStart hook в `~/.claude/settings.json`. При старте каждой Claude Code сессии хук вызывает `memex context` → memex выдаёт markdown summary → Claude получает его как system message _до_ твоего первого вопроса.
 
-**Установка:** во время `memex-sync install` будет промпт `[Y/n]` — соглашайся (Y по default'у). Или установи позже:
+**Установка:** проще всего — `curl -fsSL https://memex.parallelclaw.ai/install.sh | bash` поставит memex + daemon + auto-context хук одной командой. Если ставил memex вручную — во время `memex-sync install` будет промпт `[Y/n]` (соглашайся, Y по default'у). Или установи хук позже:
 
 ```bash
 memex hook install         # добавить хук
@@ -378,7 +378,7 @@ memex context --freshness-days 30    # только последние 30 дне
 1. Вызови `memex_overview`. Внимание на статус-баннер сверху:
    - 🟢 daemon работает — всё ок, может ещё не успел проиндексировать
    - 🔴 daemon установлен но не работает — `launchctl load ~/Library/LaunchAgents/com.parallelclaw.memex.sync.plist`
-   - ⚪ daemon не установлен — `npx memex-sync install` из директории memex-mvp
+   - ⚪ daemon не установлен — самый простой способ: `curl -fsSL https://memex.parallelclaw.ai/install.sh | bash` (поставит сам всё). Или вручную: `memex-sync install`.
 
 ### Хочу проиндексировать существующие сессии (бэкфилл)
 

package/README.md

@@ -26,6 +26,23 @@ MCP server  →  Cursor · Cline · Claude Code · Continue · Zed · Codex ·
 
 ## Install in 60 seconds
 
+**One-line install (recommended):**
+
+```sh
+curl -fsSL https://memex.parallelclaw.ai/install.sh | bash
+```
+
+That single command:
+1. Verifies Node ≥ 20.
+2. Runs `npm install -g memex-mvp`, auto-fixing `EACCES` by moving npm's prefix to `~/.npm-global` (no `sudo` needed, ever).
+3. Installs the auto-capture daemon (`memex-sync install`) **with** the v0.8 Brian Chesky auto-context hook into `~/.claude/settings.json` (preserves existing hooks).
+4. Backfills history (`memex-sync scan`) so memex already knows about your past sessions.
+5. If `claude` (Claude Code CLI) is on PATH, runs `claude mcp add memex --scope user -- memex` to wire MCP automatically.
+
+Idempotent — safe to re-run. To inspect the script before piping to bash: `curl -fsSL https://memex.parallelclaw.ai/install.sh | less`.
+
+**Prefer manual install?**
+
 ```sh
 npm install -g memex-mvp
 memex-sync install      # macOS LaunchAgent for auto-capture

package/README.ru.md

@@ -83,6 +83,23 @@ MCP server (stdio JSON-RPC)
 
 ## Установка за 60 секунд
 
+**Установка в одну строку (рекомендуется):**
+
+```bash
+curl -fsSL https://memex.parallelclaw.ai/install.sh | bash
+```
+
+Эта команда сама делает:
+1. Проверяет Node ≥ 20.
+2. Запускает `npm install -g memex-mvp`, и если ловит `EACCES` — сама переносит npm prefix в `~/.npm-global` (sudo больше не нужен — никогда, ни для одного `npm install -g`).
+3. Поднимает auto-capture daemon (`memex-sync install`) **вместе с** Brian Chesky auto-context хуком (v0.8+) в `~/.claude/settings.json` (другие хуки не трогает).
+4. Бэкфиллит историю (`memex-sync scan`) — memex сразу знает о твоих прошлых сессиях.
+5. Если на машине найден Claude Code CLI (`claude`), вызывает `claude mcp add memex --scope user -- memex` — MCP прописывается автоматом.
+
+Идемпотентно — безопасно перезапускать. Хочешь сначала посмотреть скрипт: `curl -fsSL https://memex.parallelclaw.ai/install.sh | less`.
+
+**Или вручную:**
+
 ```bash
 npm install -g memex-mvp
 memex-sync install      # macOS LaunchAgent для auto-capture

package/lib/parse-telegram-html.js

@@ -133,14 +133,25 @@ function htmlToText(html) {
 
 /**
  * Parse a Telegram date title into Unix timestamp.
- * Format: "2024-01-01 14:23:45 UTC+03:00" (or "UTC-04:00", etc.)
+ * Telegram emits dates in the user's locale format, e.g.:
+ *   • "2024-01-01 14:23:45 UTC+03:00"   (ISO — English locale)
+ *   • "01.01.2024 14:23:45 UTC+03:00"   (European — Russian / German / etc.)
+ *   • "01/01/2024 14:23:45 UTC+03:00"   (US slash format — less common in exports)
  * Returns { tsUnix, isoString } or null if unparseable.
  */
 function parseTelegramDate(title) {
   if (!title) return null;
-  const m = title.match(/^(\d{4})-(\d{2})-(\d{2})\s+(\d{2}):(\d{2}):(\d{2})(?:\s+UTC([+-])(\d{2}):(\d{2}))?$/);
-  if (!m) return null;
-  const [, y, mo, d, h, mi, s, sign, oh, om] = m;
+  let y, mo, d, h, mi, s, sign, oh, om;
+  // ISO: YYYY-MM-DD HH:MM:SS [UTC±HH:MM]
+  let m = title.match(/^(\d{4})-(\d{2})-(\d{2})\s+(\d{2}):(\d{2}):(\d{2})(?:\s+UTC([+-])(\d{2}):(\d{2}))?$/);
+  if (m) {
+    [, y, mo, d, h, mi, s, sign, oh, om] = m;
+  } else {
+    // European: DD.MM.YYYY HH:MM:SS [UTC±HH:MM]  (also supports "/" or "-" as separator)
+    m = title.match(/^(\d{2})[.\/-](\d{2})[.\/-](\d{4})\s+(\d{2}):(\d{2}):(\d{2})(?:\s+UTC([+-])(\d{2}):(\d{2}))?$/);
+    if (!m) return null;
+    [, d, mo, y, h, mi, s, sign, oh, om] = m;
+  }
   // Construct an ISO 8601 string with the explicit offset (or UTC if absent)
   const offset = sign ? `${sign}${oh}:${om}` : 'Z';
   const iso = `${y}-${mo}-${d}T${h}:${mi}:${s}${offset}`;
@@ -246,19 +257,23 @@ function slugify(s) {
  * Falls back to directory name basename, then "Telegram chat".
  */
 function extractChatTitle(htmlContent, fallbackPath) {
-  // Try the <title>...</title>
+  // PREFER the page_header — it's the actual chat name as shown in Telegram.
+  // The <title> tag is often the locale-specific "Exported Data" / "Telegram"
+  // boilerplate, which we want to avoid.
+  const headerM = htmlContent.match(/<div class="page_header"[\s\S]*?<div class="text bold"[^>]*>\s*([\s\S]*?)\s*<\/div>/);
+  if (headerM) {
+    const t = htmlToText(headerM[1]).trim();
+    if (t) return t;
+  }
+  // Fallback: <title>...</title> — strip "Chat Export" / "Telegram" / "Exported Data" suffixes
   const titleM = htmlContent.match(/<title>\s*([^<]+?)\s*<\/title>/i);
   if (titleM) {
     let t = titleM[1].trim();
-    // Telegram titles often look like "Alice — Chat Export"
     t = t.replace(/\s*[—-]\s*(Chat Export|Telegram).*$/i, '').trim();
-    if (t && t !== 'Telegram') return t;
-  }
-  // Try the page_header text
-  const headerM = htmlContent.match(/<div class="text bold"[^>]*>\s*([\s\S]*?)\s*<\/div>/);
-  if (headerM) {
-    const t = htmlToText(headerM[1]).trim();
-    if (t) return t;
+    // Skip locale boilerplate that Telegram itself uses as the page <title>
+    if (t && !/^(Telegram|Exported Data|Экспорт(ированные)? данные|Эспортированные данные)$/i.test(t)) {
+      return t;
+    }
   }
   // Fallback: dirname of the parent ChatExport_xxx folder
   if (fallbackPath) {
@@ -326,6 +341,17 @@ export function parseTelegramHtmlExport(path, opts = {}) {
   // We use a simple numeric hash so the synthetic chat_id is stable across re-imports.
   const chatId = stableChatId(chatTitle || 'Telegram chat', allMessages[0]?.date_unixtime || '0');
 
+  // Detect chat type from sender diversity. A `personal_chat` has at most 2 distinct
+  // senders (you + the other person). 3+ distinct senders → group / supergroup.
+  // We can't distinguish private_group vs public_supergroup from HTML alone, so we
+  // call it `private_group` (matches the JSON export taxonomy).
+  const distinctSenders = new Set();
+  for (const m of allMessages) {
+    if (m.from && m.from !== 'Unknown') distinctSenders.add(m.from);
+    if (distinctSenders.size > 2) break;
+  }
+  const chatType = distinctSenders.size > 2 ? 'private_group' : 'personal_chat';
+
   return {
     personal_information: { user_id: '' },
     chats: {
@@ -333,7 +359,7 @@ export function parseTelegramHtmlExport(path, opts = {}) {
         {
           id: chatId,
           name: chatTitle || 'Telegram chat',
-          type: 'personal_chat',
+          type: chatType,
           messages: allMessages,
         },
       ],

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "memex-mvp",
-  "version": "0.9.0",
+  "version": "0.9.1",
   "description": "Local-first MCP server for cross-agent AI memory. One SQLite + FTS5 corpus across Claude Code, Cowork, Cursor, Continue, Zed, Obsidian, and Telegram — passively captured, verbatim, searchable from any MCP-compatible client.",
   "type": "module",
   "main": "server.js",

package/skills/install-memex/README.md

@@ -7,13 +7,12 @@
 After you drop the skill into your agent (`~/.claude/skills/` for Claude Code, or your client's equivalent), saying **"install memex"** triggers a guided installation:
 
 1. **Discovery** — read-only checks for which MCP client you're using and what AI data already exists on your machine
-2. **`npm install -g memex-mvp`** — with EACCES fallbacks (one-shot sudo OR permanent prefix-fix; the agent asks you which)
-3. **MCP config merge** — adds a single absolute-path `command` entry into your client's `mcpServers` config. Never overwrites your other servers
-4. **`memex-sync install`** — registers the macOS LaunchAgent for live auto-capture
-5. **`memex-sync scan`** — one-time backfill of every session that already exists on disk
-6. **Restart hint + verification commands** — including the v0.7+ CLI fallback (`memex overview`, `memex search "foo"`) so you can verify memex works even if MCP didn't wire up cleanly
+2. **Fast path (v1.1+)** — `curl -fsSL https://memex.parallelclaw.ai/install.sh | bash`: one hosted bash script does npm install (with EACCES auto-fix to `~/.npm-global`), daemon setup, v0.8 auto-context hook, history backfill, and `claude mcp add memex` if Claude Code CLI is on PATH. Idempotent.
+3. **Fallback: manual five-step** — if curl fails, the user declines, or the agent is inside a GUI client (Cursor/Cline/Continue/Zed) where the MCP config still needs editing: `npm install -g memex-mvp` → MCP config merge → `memex-sync install` → `memex-sync scan`.
+4. **MCP config merge** (only needed for GUI clients) — adds a single absolute-path `command` entry into your client's `mcpServers` config. Never overwrites your other servers.
+5. **Restart hint + verification commands** — including the v0.7+ CLI fallback (`memex overview`, `memex search "foo"`) so you can verify memex works even if MCP didn't wire up cleanly.
 
-End-to-end: **~2 minutes**, fully observable (agent shows each command before running).
+End-to-end: **~60 seconds** via fast path, **~2 minutes** via manual flow, fully observable (agent shows each command before running).
 
 ## What is memex?
 

package/skills/install-memex/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: install-memex
 description: Make Claude, Cursor, Cline, Continue, and Zed remember every AI conversation forever — one local SQLite corpus shared across all of them. Installs memex (local-first MCP server) in ~2 minutes — npm install, MCP config wiring, auto-capture daemon, history backfill. No cloud, no account, verbatim storage. Also indexes Obsidian notes, Telegram chats, and any URL the user wants to save (web pages, Perplexity threads, AI chat shares — memex_store_document tool, v0.6+). Use when the user says "install memex", "set up memex", "add memory to my AI", "make my agent remember across sessions", or similar.
-version: 1.0.0
+version: 1.1.0
 metadata:
   openclaw:
     emoji: "📚"
@@ -48,7 +48,32 @@ Scan the user's setup so you can tailor advice and tell them exactly what memex
    - "After install, memex will auto-index conversations from: [detected sources]"
 4. Wait for the user's "ok" before starting step 1.
 
-## Five-step install
+## Fast path — one-line installer (try this first)
+
+memex ships a hosted bash installer that does steps 1, 3, and 4 in a single run — and also wires up Claude Code's MCP entry if `claude` is on PATH. It's idempotent (safe to re-run), auto-fixes the `EACCES` case by moving npm's prefix to `~/.npm-global`, and prompts before enabling the auto-context hook.
+
+Show this command to the user, explain what it does, get their **explicit ok**, then run:
+
+```sh
+curl -fsSL https://memex.parallelclaw.ai/install.sh | bash
+```
+
+What the script does, in order:
+1. Checks Node ≥ 20.
+2. `npm install -g memex-mvp` — on EACCES, sets `npm config set prefix ~/.npm-global`, appends PATH to `~/.zshrc`, retries.
+3. `memex-sync install` with `--auto-context yes` (Brian Chesky hook into `~/.claude/settings.json` — preserves other hooks).
+4. `memex-sync scan` — backfills existing history.
+5. `claude mcp add memex --scope user -- memex` if Claude Code CLI is detected.
+
+After the script finishes:
+- If the user is in **Claude Code (CLI)** → install is complete. Skip straight to step 5 (verification + restart).
+- If the user is in **Cursor / Cline / Continue / Zed** → the npm install + daemon + auto-context + scan are done, but the GUI client's MCP config still needs the memex entry. **Skip step 1 (already installed)**, **skip step 3** (daemon already installed) and **skip step 4** (scan already ran). **Do step 2** (wire MCP into the GUI client's config) and **step 5** (verify + restart).
+
+If the script fails for any reason — non-zero exit, weird output, user uncomfortable piping curl to bash — fall back to the **Manual five-step install** below.
+
+To inspect what the script does first: `curl -fsSL https://memex.parallelclaw.ai/install.sh | less` (don't pipe to bash).
+
+## Manual five-step install (if the fast path didn't fit)
 
 Do these in order. Show each command before running it. Stop and ask if anything fails or looks wrong.
 
@@ -224,4 +249,4 @@ This is also useful for agents without native MCP support (OpenCode + Kimi, plai
 
 ## Begin
 
-Greet the user, confirm which MCP client you're running inside, and run the Discovery checks before any install actions.
+Greet the user, confirm which MCP client you're running inside, and run the Discovery checks before any install actions. After Discovery, **propose the fast path (curl one-liner) first** — it covers ~90% of cases in one shot. Only fall back to the manual five-step install if the user objects, the script fails, or you're inside a GUI client where you'll still need to do step 2 manually after the script runs.

package/skills/install-memex/examples.md

@@ -2,6 +2,52 @@
 
 Sample interactions when the user invokes this skill. These show typical happy paths and how the skill handles common edge cases.
 
+> **Note (v1.1+):** The skill now leads with the **fast-path one-liner** (`curl -fsSL https://memex.parallelclaw.ai/install.sh | bash`) after Discovery — see Example 0 below. The legacy five-step examples (1–5 below) stay as the fallback when the agent is inside a GUI client (Cursor / Cline / Continue / Zed — still need step 2 manually after the script), the user declines curl, or the script fails.
+
+---
+
+## Example 0 · Fast path on Claude Code CLI (v1.1+)
+
+> **User:** install memex
+>
+> **Agent:** 👋 You're running inside Claude Code CLI. Let me run a quick discovery first.
+>
+> ```
+> ✓ Found Claude Code data at ~/.claude/projects/ (14 sessions)
+> ✓ Found Cowork sessions (5 subagent transcripts)
+> ✗ Cursor data not found
+> ✗ Continue / Zed not found
+> ```
+>
+> After install, memex will auto-index conversations from: **Claude Code, Cowork**. You can drop Telegram exports into `~/.memex/inbox/` later if needed.
+>
+> The fast path is a single hosted bash script that does **npm install (with EACCES auto-fix), daemon setup, Brian Chesky auto-context hook, history backfill, and `claude mcp add memex`** all in one go. Idempotent. Want me to run:
+>
+> ```sh
+> curl -fsSL https://memex.parallelclaw.ai/install.sh | bash
+> ```
+>
+> **User:** ok
+>
+> **Agent:** [runs the curl command, streams output]
+>
+> ```
+> ▸ memex one-line installer
+> ▸ Node v20.11.1 — ok
+> ▸ Installing memex-mvp from npm...
+> ✓ memex 0.9.0 ready at /Users/you/.npm-global/bin/memex
+> ▸ Installing memex-sync (LaunchAgent + auto-context hook)...
+> ✓ daemon running (PID 41872)
+> ✓ Brian Chesky auto-context hook added to ~/.claude/settings.json
+> ▸ Backfilling history (memex-sync scan)...
+> ✓ 87 conversations indexed
+> ▸ Wiring MCP into Claude Code...
+> ✓ claude mcp add memex — done
+> ▸ All set. Quit Claude Code (Cmd+Q) and reopen any project. Memex will inject prior context before your first message.
+> ```
+>
+> All five steps done in ~25 seconds. Quit Claude Code (Cmd+Q) and reopen — when you open any project you've worked in, memex will inject relevant context before you even type. Try: `memex overview` from terminal to confirm.
+
 ---
 
 ## Example 1 · Happy path on a fresh Cursor install