memex-mvp 0.6.0 → 0.6.1

package/README.md

@@ -100,6 +100,23 @@ For a fully-automated install across all detected MCP clients, see [the AI-drive
 
 ---
 
+## Save URLs into memex (v0.6+)
+
+Once memex is installed, any MCP-aware agent can also save **web pages, AI chat shares, and pasted text** into your memex memory — searchable from any other AI chat later. In Claude Code, Cursor, Cline, …:
+
+```
+Save https://www.perplexity.ai/share/<id> to memex
+Add this article to my memex: https://example.com/long-post
+```
+
+The agent fetches the page via its own WebFetch (auto-falling back to `r.jina.ai` for Cloudflare-protected sites — memex teaches the trick) and calls `memex_store_document`. Memex stores the content verbatim as a `web` source conversation, indistinguishable from AI chats at search time.
+
+Perplexity threads need to be made **Public** in the Share dialog first — memex detects private threads and tells the user how to fix it. Full guide: [HELP.md §8](HELP.md).
+
+**Memex stays 100% local** — the agent fetches, memex only stores. Zero outbound calls from memex itself.
+
+---
+
 ## What it captures
 
 | Source                | How it gets in                                                 |
@@ -111,6 +128,7 @@ For a fully-automated install across all detected MCP clients, see [the AI-drive
 | Obsidian notes        | Auto: per-vault markdown watcher                               |
 | Telegram exports      | Manual: drop `result.json` (Telegram Desktop) into `~/.memex/inbox/` |
 | Telegram (live)       | Run [`memex-bot`](bot/README.md) — captures messages you send/forward to your private bot |
+| **Web pages, AI chat shares, pasted text** | From any MCP agent: *"save https://... to memex"*. Agent fetches; memex stores verbatim. Cloudflare-protected pages (Perplexity, npm.com, Twitter, Medium, …) handled via the agent's r.jina.ai fallback. See [HELP.md §8](HELP.md) |
 
 All sources land in the same FTS5 corpus, searchable by one `memex_search` call.
 
@@ -128,6 +146,7 @@ All sources land in the same FTS5 corpus, searchable by one `memex_search` call.
 | `memex_list_projects`         | Distinct project paths captured (for the `project` filter)               |
 | `memex_archive_conversation`  | Hide a chat from default listings (data preserved)                       |
 | `memex_export_markdown`       | Export one conversation as Markdown (for Obsidian round-trip)            |
+| `memex_store_document`        | Save a web page, AI chat share, or pasted text. Agent fetches; memex stores verbatim. Teaches the Jina r.jina.ai trick for Cloudflare-blocked pages |
 | `memex_list_sources`          | Per-source enabled/disabled + counts                                     |
 | `memex_status`                | Daemon health: PID, last capture, watched files                          |
 | `memex_sources_status`        | Which sources are captured + the exact CLI to opt out                    |

package/README.ru.md

@@ -121,6 +121,21 @@ curl -fsSL https://raw.githubusercontent.com/parallelclaw/memex-mvp/main/skills/
 
 …или `/install-memex`. Агент сам сделает `npm install`, пропишет MCP-config, поднимет daemon и проверит что всё работает — ~2 минуты.
 
+### Сохранение URL'ов в memex (v0.6+)
+
+После установки в любом MCP-агенте (Claude Code, Cursor, Cline, Continue, Zed) можно сохранять **web-страницы, AI-chat share'ы и pasted-тексты** прямо в memex-память:
+
+```
+Сохрани https://www.perplexity.ai/share/<id> в memex
+Добавь эту статью в memex: https://example.com/article
+```
+
+Агент сам fetch'ит страницу через свой WebFetch — для Cloudflare-защищённых сайтов (Perplexity, npm.com, Twitter, Medium) автоматически falls back на `r.jina.ai` proxy (memex учит агента этому трюку через tool description). Затем агент вызывает `memex_store_document`, который хранит контент verbatim как conversation с `source: "web"`.
+
+**Memex остаётся 100% локальным** — fetch делает агент, memex только хранит. Никаких outbound network calls со стороны memex.
+
+Полное руководство и edge cases (private Perplexity, paywall, login-walls): [HELP.md §8](HELP.md).
+
 ### Подключение к Claude Code
 
 Сначала возьми **два абсолютных пути** в терминале:
@@ -162,9 +177,11 @@ which node  # → путь до бинарника node (например /Users
 | **Cursor IDE** (Composer + Chat) | SQLite `state.vscdb` в `~/Library/Application Support/Cursor/` | ✅ работает (poll каждые 5 мин) |
 | **Obsidian** vault notes | `.md` файлы + YAML frontmatter | ✅ работает (FSEvents, hash-based dedupe) |
 | **Telegram** | `result.json` из Desktop export | ✅ работает |
-| Claude.ai web export | будет в v0.3 | — |
-| ChatGPT export | будет в v0.3 | — |
-| Apple Notes | будет в v0.3 | — |
+| **Telegram (live)** | бот `memex-bot` ловит твои сообщения / форварды | ✅ работает |
+| **Web-страницы, AI-share'ы, paste'ы** | `memex_store_document` — агент fetch'ит, memex хранит verbatim (v0.6+) | ✅ работает |
+| Claude.ai web export | будет в v0.7 | — |
+| ChatGPT export | будет в v0.7 | — |
+| Apple Notes | будет в v0.7 | — |
 
 ### Filename convention для inbox-файлов
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "memex-mvp",
-  "version": "0.6.0",
+  "version": "0.6.1",
   "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

@@ -17,9 +17,9 @@ End-to-end: **~2 minutes**, fully observable (agent shows each command before ru
 
 ## What is memex?
 
-Memex is a **local-first MCP server** that captures every conversation you have with an AI — across **Claude Code, Cowork (including subagent transcripts), Cursor, Cline, Continue, Zed**, plus **Obsidian notes** and **Telegram chats** — into one searchable SQLite + FTS5 corpus.
+Memex is a **local-first MCP server** that captures every conversation you have with an AI — across **Claude Code, Cowork (including subagent transcripts), Cursor, Cline, Continue, Zed**, plus **Obsidian notes**, **Telegram chats**, and **web pages / AI chat shares** (v0.6+ via `memex_store_document` — agent fetches, memex stores verbatim) — into one searchable SQLite + FTS5 corpus.
 
-Any MCP-compatible agent can then query that corpus through 11 standard tools (`memex_search`, `memex_recent`, `memex_overview`, …).
+Any MCP-compatible agent can then query that corpus through 12 standard tools (`memex_search`, `memex_recent`, `memex_overview`, `memex_store_document`, …).
 
 | Pain                                            | Memex                                |
 |-------------------------------------------------|--------------------------------------|

package/skills/install-memex/SKILL.md

@@ -1,6 +1,6 @@
 ---
 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 and Telegram chats. Use when the user says "install memex", "set up memex", "add memory to my AI", "make my agent remember across sessions", or similar.
+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
 metadata:
   openclaw:
@@ -160,6 +160,7 @@ After restart, suggest they try any of:
 - "show me what memex has in memory" → triggers `memex_overview`
 - "what projects has memex captured" → triggers `memex_list_projects`
 - "search memex for [recent topic]" → triggers `memex_search`
+- "save https://en.wikipedia.org/wiki/As_We_May_Think to memex" → triggers `memex_store_document` and teaches the user that URL-saving exists (v0.6+)
 
 These confirm everything works end-to-end.
 

package/skills/install-memex/examples.md

@@ -179,6 +179,34 @@ Sample interactions when the user invokes this skill. These show typical happy p
 
 ---
 
+---
+
+## Example 6 · Right after install — testing URL save (v0.6+)
+
+> **User:** save https://en.wikipedia.org/wiki/As_We_May_Think to memex
+>
+> **Agent:** Fetching the page with WebFetch...
+>
+> ```
+> ✓ Got 12,847 chars from en.wikipedia.org
+> ```
+>
+> Calling `memex_store_document(content, url=https://en.wikipedia.org/wiki/As_We_May_Think, title=auto)`...
+>
+> ```
+> ✓ stored
+>   conversation_id: web-d3b07a384d1b
+>   title: "As We May Think"
+>   length: 12,847 chars
+>   warnings: []
+> ```
+>
+> Saved. Try searching it now: *"search memex for memex Bush 1945"* — the article will show up alongside any AI chats where you discussed it.
+>
+> 💡 By the way, you can save any URL this way — Perplexity threads, blog posts, ChatGPT shares, Twitter threads, GitHub discussions. For Perplexity specifically, the thread must be made Public first (Share → Public link). For Cloudflare-protected sites, memex auto-falls back through `r.jina.ai` proxy.
+
+---
+
 ## What these examples illustrate about the skill's behavior
 
 - **Always discover first**, then ask for confirmation before any write action