Aftermark
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@AftermarkRecall bookmarks for fixing React state bugs in project admin-dashboard"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Aftermark
Save what works. Teach your agent when to use it.
简体中文 · Download current release · MIT
A local bookmark library for coding agents. Keep a source, why you saved it, the project it applies to, and corrections from real work. Your browser, CLI and MCP-compatible agent share one collection.
Start in three steps
Requires Python 3.11+. Download the source ZIP, extract it, then:
Platform | Install once | Open the app |
Windows | Double-click | Double-click |
macOS / Linux |
|
|
Open http://127.0.0.1:43821, save a note or import the three examples.
In Connect an agent, copy the Codex setup command or your host's MCP configuration.
Choose the exact project name, generate its instructions and add them to your agent's project rules. Try a relevant task and inspect what it actually used.
Empty project means personal/global bookmarks only. Generating instructions changes no host files. Automatic recall depends on your host and instructions.
No account or extra model API key is needed for Aftermark. Installation and fetching webpages need internet; local notes, PDFs and keyword search work offline afterward. The project is not published to PyPI: use the source ZIP or the wheel on the release page.
Related MCP server: bookmark-mcp
What you can keep
Source | Supported |
Your own knowledge | Notes, Markdown, TXT, intent and scoped corrections |
Web | Ordinary page text, or explicitly link-only bookmarks |
Papers | Upload a text PDF or import its URL; retain the original and page citations |
Videos | Links and supplied SRT/VTT subtitles with timestamp locations |
Search finds task keywords in sources and applicable corrections. Read the matching page or subtitle segment, then decide with your agent whether it fits the project. Usage records distinguish referenced, applied, verified and skipped; changed sources leave older evidence clearly marked. A usage record must include the revision actually read. If the source changes during the task, reread its content and corrections and reassess before recording.
Long sources now show a passage covering more distinct task keywords, rather than stopping at the first generic match. PDF pages, subtitle timestamps and original text offsets remain available. This improves where you start reading; applicability is still your agent's judgment.
Connect and use
In an activated environment:
aftermark --data-dir .local/library config --project my-game
aftermark --data-dir .local/library connect codex
aftermark --data-dir .local/library connect codex --applyThe first command generates project-specific instructions. The next previews Codex registration; --apply registers it through Codex's CLI and preserves conflicting entries. Other MCP hosts use the generated JSON. Tools are recall, read_bookmark, save_bookmark, import_url, add_correction and record_usage.
Ask your agent to import an article or text PDF URL into a named project. import_url fetches the source and saves it; the agent must still retrieve and read it before citing it. The local app and add --url URL --fetch use the same importer. HTML/text is limited to 5 MB, PDFs to 20 MB. Video URLs remain link-only unless you supply subtitles.
After upgrading, restart running Aftermark services and reload your agent’s MCP connection. 0.5 improves returned excerpts without changing bookmark ranking, stored sources or backups. Usage records still require expected_revision (CLI: record --revision N). If upgrading from before 0.4, regenerate project instructions for import_url.
Codex setup and real-client evidence · CLI and source reading
Does it work?
In 0.5, real Codex CLI followed project rules to retrieve/read the saved defect note, reviewed the implementation and found an uncovered excerpt boundary. After the fix, it passed 28 focused checks and recorded/read back the results. The full suite has 63 passing tests. Identical English/Chinese fixtures miss the target passage in the released 0.4 wheel and find it in 0.5. These controlled results are not a general retrieval-accuracy or productivity benchmark; current desktop excerpt behavior and other hosts remain unverified. Exact validation scope.
Your data
The launchers use .local/library inside the project. Use --data-dir .local/library from this directory to access it from the CLI. Without that flag, the default is %LOCALAPPDATA%\Aftermark on Windows, ~/Library/Application Support/Aftermark on macOS, or $XDG_DATA_HOME/aftermark on Linux. AFTERMARK_HOME can also select a directory. All clients must use the same library.
JSON export/import includes original files and history. Existing IDs are skipped on import. Back up before upgrades; schema 2 and JSON backup format 1 remain unchanged in this release. The app is for personal, local use and binds to loopback.
Limits
Keyword retrieval, not semantic search. No OCR, automatic video transcription, frame understanding or cloud sync. Web extraction does not execute JavaScript or bypass login. Usage evidence is submitted by the user or agent; Aftermark does not independently verify it. Sources remain references and cannot override higher-priority instructions.
Development
python -m pip install -e ".[dev]"
python -m pytest
python -m buildPython, SQLite, FastAPI, the official MCP SDK and plain browser JavaScript. Architecture · Short roadmap · Changelog.
MIT. Example notes are original project content. Imported sources retain their original rights.
This server cannot be deployed
Maintenance
Related MCP Connectors
Search, label, and manage your X (Twitter) bookmarks from any MCP client via Tweetsmash
Read and edit your Acorn Reply knowledge base from any MCP client.
Search, save, and set reminders in your personal MarkIt library of links, posts, and notes.
Personal knowledge MCP: capture bookmarks, notes & todos by chat; archive pages; search memory.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA VSCode extension that provides MCP tools for AI assistants to programmatically create, manage, and annotate code bookmarks. It enables AI-driven and manual organization of codebase architecture, flows, and key components through hierarchical bookmarks and groups.1MIT
- FlicenseAqualityCmaintenanceA bookmark management MCP server that enables saving, searching, and managing bookmarks with tags and read/unread status, providing tools, resources, and prompts for integration.4-
- AlicenseNot gradedqualityCmaintenanceEnables users to search, read, and query saved bookmark content via a read-only MCP interface, with full-text and optional semantic search.4MIT
- AlicenseNot gradedqualityBmaintenanceProvides authenticated bookmark management tools via MCP, including adding, deleting, listing, and searching bookmarks.990 npmMIT