How does Pieces capture and organize memories from the apps I already use?

Pieces runs in the background on your computer and forms memories every 2 seconds from the apps you already use, turning what already happened into a searchable timeline. It captures what you see in the currently focused application by default, with copy/paste capture and meeting/conversation audio as opt-in sources. You can then search, filter, and revisit any moment by time, topic, person, or tool — without changing how you work.

What Pieces captures, and when

The core mechanism is continuous background capture tied to the app in focus. According to Pieces, memories are formed every 2 seconds, which is what makes the timeline feel like a living record of your day rather than a set of manual notes.

Capture falls into three categories:

The distinction matters if you care about scope. Screen-level context is on by default; clipboard and audio are things you choose to include.

Which apps feed the memory

Pieces lists a broad set of supported apps and sources, grouped roughly by what they contribute to your timeline:

• Email: Gmail (threads, follow-ups, decisions, account context), Outlook (email history, commitments, meeting context)
• Browsers: Chrome (research trails, tabs, sources, web activity), Arc (web research, references, active project context), Safari (visited pages, research paths, useful sources)
• Team chat: Slack (threads, handoffs, decisions, open questions), Teams (chats, shared updates, calls, team context), Google Chat (conversations, asks, updates, decisions), Discord (community threads, feedback, support context)
• Meetings: Google Meet (decisions, action items, prep), Zoom (call takeaways, customer feedback, next steps), Microsoft Teams (meeting notes, chat context, project updates)
• Docs & design: Google Docs (drafts, comments, revisions, source material), Notion (project notes, specs, wikis, planning context), Figma (design reviews, comments, rationale, assets)
• AI tools: Claude (prompts, outputs, reasoning, reused context), ChatGPT (AI chats, drafts, summaries, task context), Copilot (code suggestions, edits, implementation context), Codex (agent activity, code changes, generated work), Perplexity (research answers, citations, source trails)
• Code editors: Cursor (agent work, code edits, commands, review context), VS Code (files, terminals, debugging, implementation trails), JetBrains (code navigation, edits, project context), Xcode (build context, app changes, debugging work)

The pattern is that Pieces plugs into the tools where decisions and context already accumulate, rather than asking you to move that work somewhere new.

How memories get organized

Captured activity is arranged chronologically into a searchable timeline. That structure supports a few concrete retrieval behaviors:

• Search and filter across any moment in your history.
• Scope prompts by time, source, or topic to find or curate exactly what you need.
• Ask about any time, topic, person, or tool — for example, "what did we decide about the Q3 launch?" or "what was I working on last Tuesday?"
• Generate recaps instantly from real context: standup updates, morning briefs, meeting prep, and day recaps.

The practical effect is that retracing your steps — which normally takes hours of scrolling through tabs, threads, and docs — becomes a single query against your own history.

What this means for your workflow

You don't have to adopt a new note-taking habit or manually file anything. Pieces works from the apps you already have open, so the memory layer builds itself as a byproduct of your normal day. The trade-off to weigh is scope: default screen capture is broad, while clipboard and audio are opt-in, so you control how much of your activity enters the timeline.

For pricing, plans, and platform availability, check Pieces pricing directly, since those details aren't covered here.