Pieces · Indexed content

How to apply a discount code at checkoutApply your discount code before you pay — Add discount sits above the card fields and is easy to miss.Where it isOn the payment step, the Add discount button sits above the payment methods. Click it to reveal the code field.Before you startYou’ll need a valid discount code and a signed-in Pieces account.How to apply itIn Pieces Desktop, click Upgrade. Checkout opens in your browser.Fill in your details on the first screen, then continue to payment.Click Add discount above the card fields.Enter your code and apply it. The order total should update immediately — confirm the new amount before you continue.Enter your payment details and finish checkout.TroubleshootingCode rejected?Double-check the spelling and capitalization — most codes are case-sensitive — and confirm it hasn’t expired.Total didn’t change?Make sure you clicked to apply the code after typing it; it won’t apply on its own. Refresh and try once more, or contact support if it still fails.Already on a paid plan?Contact support to apply the code to your existing subscription.SupportStill need a hand?Browse FAQs or submit a request — we’ll help you get the code applied.Contact support…

Back to Updates Agentic Long-Term Memory and Meeting PrepProduct|May 1, 2026The agentic era begins — multi-turn agentic Long-Term Memory, Meeting Prep, Reflection Mode, and Google Calendar.6.0.0 changes the architecture. Agentic Long-Term Memory Engine replaces the single-shot Q&A engine with a multi-turn reasoning agent that follows threads, cross-references context, and builds toward complete answers. That foundation powers the first summary that takes action — Meeting Prep reads your calendar, assembles structured pre-reads, and can schedule prep time for you.What you can do now that you couldn't beforeHave real conversations with your memoryAgentic Long-Term Memory enables multi-turn reasoning across your summaries, events, people, and beyond. The agent follows threads, cross-references context, and builds toward complete answers instead of guessing in one shot. A full toolbox — memory search, web search, calendar, filesystem, and browser history — lets the agent actively gather evidence during any chat or summary.Walk into every meeting preparedMeeting Prep connects to your Google Calendar, looks ahead at upcoming meetings, cross-references each with your Long-Term Memories, a…

Back to Blog How to Set Up OpenClaw With Your Pieces Long-Term MemoryA step-by-step guide to setting up OpenClaw with Pieces Long-Term Memory - so your AI agent has full context of your work from day one.Jack RossAI & LLMsMarch 27, 2026If you're using AI agents, one of the biggest limitations is memory. In this guide, I'll show you how to connect OpenClaw to Pieces Long-Term Memory so your agent instantly knows everything about you and your work, and can operate 24/7 while building context from everything it does.What You'll Need:A computer with Node.js installedPieces Desktop AppngrokAn OpenClaw-compatible API keySetup Time: 3-5 minutesStep 1: Download Pieces and Enable Long-Term MemoryDownload Pieces from pieces.app and install the desktop app.Once installed, open Pieces and go to Settings → Long-Term Memory and make sure it's enabled.This allows Pieces to capture your real work — your screen, clipboard, and activity — and turn it into structured memory over time.The more you use your computer, the richer your memory gets.Step 2: Start the TunnelTo make your local Pieces instance accessible to OpenClaw, you'll need to expose it using ngrok. In your terminal, run:ngrok http 39300Y…

Back to Updates Scheduled Summaries and a rebuilt local LLM engineProduct|March 1, 2026The friction-removal release — Scheduled Summaries, Modality Focus, a rebuilt local LLM engine, and expanded BYOK.5.1.0 removes friction. It puts summaries on autopilot with Scheduled Summaries, adds Modality Focus for capture-aware querying, rebuilds the local LLM engine from the ground up — no more Ollama — and expands BYOK to OpenAI, Google AI Studio, and Anthropic.What you can do now that you couldn't beforePut summaries on autopilotSchedule any summary to run automatically — daily, weekly, or on a custom cadence. Morning briefs generate before you open Pieces, and weekly recaps arrive every Friday afternoon.Query by how you captured itModality Focus lets you filter chat prompts by clipboard, audio, or vision — narrowing results to the right capture type when you remember how you encountered something but not the exact content.Run local models without OllamaA completely rebuilt local LLM engine removes the Ollama dependency, with fewer setup issues, better stability, and access to newer models.Bring your own API keysFull BYOK support for OpenAI, Google AI Studio, and Anthropic joins existing …

Back to Updates Audio capture for Long-Term MemoryProduct|February 1, 2026The biggest capture and integration release yet — LTM Audio, custom templates, and a 39-tool MCP server.5.0.3 adds audio to Long-Term Memory Engine, puts full template control in your hands, and gives AI agents their deepest access to your work history.What you can do now that you couldn't beforeCapture your meetings and callsLTM Audio (preview) records microphone input and system audio simultaneously, extracts context, and folds it into your Long-Term Memory. Pair programming sessions, stand-ups, client calls, and webinars become searchable alongside everything else you've worked on. Pieces processes audio locally; no raw audio is stored.Build your own one-click summariesCustom summary templates let you define exactly what you want: choose a time range, scope by website, project, or application, set your preferred prompt, and save it. Next time, one click generates the same structured output — no reconfiguring parameters.Give your AI agent your full work historyThe Pieces MCP Server now exposes 39 tools — full-text search, vector search, temporal queries, batch retrieval, and annotation access. Cursor agents…

Back to Updates Time Breakdown for billable hoursProduct|January 27, 2026The professional productivity release — Time Breakdown, Timeline Search, and model management.5.0.1 introduces Time Breakdown — the first tool to reconstruct your billable hours from captured context — alongside a searchable timeline, a richer model picker, enterprise model governance, and one-tap entry from any summary into a deeper conversation.What you can do now that you couldn't beforeStop losing billable hours to poor recallTime Breakdown analyzes your captured workstream and reconstructs your day into approximate time blocks grouped by project and client. It gives you a structured starting point to review, refine, and submit, instead of starting from a blank page.Find anything in your work historyThe timeline is now searchable by keyword and filterable by time range, source application, and summary type. Combine filters to scope to a specific afternoon, or to everything related to one module from VS Code this week.Pick the right model without the frictionA redesigned model picker shows inline descriptions and a quick-search field. Switching from Claude to Gemini mid-conversation takes two clicks. Full m…

Back to Updates A new Home Base and single-click summariesProduct|December 23, 2025The foundation release — a new Home Base, personalization, and single-click summaries.5.0.0 consolidates Pieces into a single, calm entry point, makes filtering and browsing fluid and in-place, teaches Pieces to understand who you are versus who you collaborate with, and introduces single-click summaries for Morning Brief, Day Recap, Standup, and Week Recap.What you can do now that you couldn't beforeStart from one place, every timeHome Base replaces the multi-entry-point design that left users hunting for features. Now you arrive somewhere consistent: start a new chat, pick up a recent conversation, or generate a summary, without navigating to a different screen first.Filter, browse, and act without losing contextIn-place filtering lets you narrow your view by date, chat type, summary type, source, or material category, then immediately ask a question or generate something new in the same view. As your library grows into the thousands, this replaces the "find the right screen" problem with a simpler loop: browse, filter, act.Get summaries that are actually about youThe personification and disambigua…

Back to Blog A comprehensive review of the best AI Memory systemsIn-depth 2025 review of the best AI memory systems for developers. Compare architectures, features, use cases, and performanceThe Pieces TeamAI & LLMsDecember 15, 2025This guide is a tour of today’s AI “memory” tool – the stuff you need to move beyond quick demos and build production-ready LLM/chat apps that actually remember users over time.We’ll compare cloud options (like OpenAI, and IBM), open-source frameworks (such as Zep and Fabric), local-first tools (including Pieces and NativeMind), and hybrid setups that mix the best of both.Understanding AI Memory Systems (and how AI memory actually works)If you’re building an AI chat app or an agent, “memory” isn’t one thing – it’s a set of layers that solve different problems. Most AI memory tools are basically opinionated ways to store, organize, and retrieve information across these layers so your app can stay coherent in the moment and still remember useful things later.The main memory layers you’ll run intoWorking memory: What the model is thinking about right now – the current prompt, the current context window, and the latest tool outputs. It’s extremely temporary …

Back to Blog Not a standup tool: the AI memory that makes standups greatDitch standup bots. Use Pieces, an on-device artificial memory that captures your work to generate accurate, detailed standup reports with a simple prompt.The Pieces TeamAI & LLMsDecember 12, 2025Product status: This post describes Pieces as it worked when published. Pieces Drive is not available in current Pieces releases.The morning standup. It’s a cornerstone of agile development, but for many developers, it’s a source of daily friction. The scramble begins minutes before the meeting: frantically digging through git logs, scrolling through Slack channels, and trying to piece together yesterday’s chaotic trail of activity. You know you were productive, but articulating what you actually did, the research, the debugging, the quick pivots, is a frustrating exercise in reverse-engineering your own workflow. What if you didn't have to remember? What if you had an AI that remembered for you?Many teams have turned to AI tools that record and summarize team standups, but these solutions often miss the mark. They’re reactive, capturing only what’s said in a meeting, not the deep work that happens between them. They a…

Back to Blog Building a daily productivity app with Pieces — Part 4: polish & production readyBuild a daily productivity app with Pieces in Part 4 of the series: polish the UX, tighten performance, fix edge cases, and make your app production-ready with deployment best practices.Bishoy HanyProductivityDecember 9, 2025Welcome to Part 4! We've come a long way:Part 1: We built a real-time sync with Pieces OSPart 2: Then we added AI insights with GeminiPart 3: Lastly, we created a beautiful Flutter UIThe problems we're solvingAfter Part 3, we had a working app, but:Every restart regenerates recaps - Wastes API calls and timeErrors just fail silently - Bad UXCan't regenerate a recap - Stuck with what you gotNo tests - Can't confidently make changesNo CI/CD - Manual testing every timeLet's fix all of these!Feature 1: persistent caching with HiveThe problemWhen you close the app, all those AI-generated recaps? Gone. Next time you open it, we regenerate everything. That's:Slow (3+ seconds per day)Expensive (API calls cost money)Wasteful (Same data, different day)Solution: persistent caching with HiveHive is a lightweight, fast NoSQL database for Flutter. Perfect for caching our recaps!Firs…

Back to Blog Building a daily productivity app with Pieces - Part 3: bringing it all together with Flutter UIPart 3: Flutter UI to bring your Pieces daily productivity app together.Bishoy HanySoftware DevelopmentDecember 4, 2025Welcome to Part 3! In Part 1, we built real-time sync with Pieces OS. In Part 2, we added Gemini AI to extract insights. Now it's time to make it beautiful with a Flutter UI! 🎨What we're buildingA clean Flutter app that shows:📅 Daily recap cards💼 Projects with status indicators👥 People you collaborated with (with avatars!)⏰ Reminders📝 Notes and learnings🔄 "Load More" paginationThe challengeWe have two services working perfectly:PiecesOSService - Real-time data syncDailyRecapService - AI-powered insightsNow we need to:Initialize both services when the app startsLoad recaps for recent daysDisplay them in beautiful cardsHandle loading statesAllow pagination ("Load More")Setting upFirst, add the avatar package to pubspec.yaml:dependencies:flutter_initicon: ^2.0.0 # For generating avatars from namesThis package creates beautiful avatars from initials - perfect for showing collaborators!Integrating the servicesStart by removing anything that may be in your m…

Back to Blog Building a daily productivity app with Pieces — Part 2: Adding AI Intelligence with GeminiBuild a daily productivity app with Pieces (Part 2) by adding AI intelligence with Google Gemini, covering architecture, prompts, integrations, and practical tips to ship smarter workflows.Bishoy HanyAI & LLMsDecember 4, 2025Welcome back! In Part 1, we built a complete PiecesOS service that:Connects to PiecesOS and maintains a WebSocket connectionFetches and caches workstream summaries grouped by dayExtracts the summary content from annotationsNow we have all of the infrastructure in place. But here's the thing: having raw summaries with their content is cool, but it's not exactly... useful. I mean, I have all this text about what I did, but what did I actually accomplish today?That's where Part 2 comes in. We're going to use Google's Gemini AI to transform those raw summaries into actual insights. Think:What did I work on?Which projects did I touch?Who did I collaborate with?What should I remember for tomorrow?The challengeThanks to Part 1, we now have access to rich summary data using SummaryWithContent:// lib/models/daily_recap_models.dart // Don't forget the imports! import 'd…

Back to Blog Building daily stand-up generator using Pieces API — Part 1: The SDK overviewLearn how to build a daily stand-up generator using the Pieces API. This first part of the series covers the SDK overview, key capabilities, and how developers can streamline workflow automation with Pieces.Bishoy HanySoftware DevelopmentDecember 1, 2025Imagine the following scenario: Monday, 9 AM. You grab your coffee, join the stand-up call, and suddenly realise: you have absolutely no idea what you did last week. The weekend wiped your mental cache clean. Was it the React component refactor? Or was that two weeks ago? You vaguely remember fighting with TypeScript errors on Thursday, but what was the actual solution? Your Git commits say 'fix: update logic' — thanks, past you, very helpful.Here's the thing: your brain isn't built to be a perfect activity log. But your computer? It remembers everything. That's where PiecesOS comes in.The goalCreate an app that tracks what work is done every day.For Part 1, we will work on:Connecting to PiecesOSGetting our workstream summariesGrouping the summaries by dayKeeping everything updated in real-timeWe’ll hit a UI later on. Let’s take this one step a…

Back to Blog How we stopped watching our engineers struggle through stand-upsTired of awkward standup meetings where great engineers sound like they did nothing? I automated our team's standups with AI and got 3 people promoted. Here's exactly how we changed standups and made real work visible to managers.The Pieces TeamProductivityNovember 27, 2025Every Monday, we used to watch our team go through the same painful ritual: stand-up time. That dreaded meeting when everyone goes around sharing where they left off last week, and what’s top of mind this week. Week after week, our best team members, people at the core of what we build, consistently struggled to recall and articulate their highlights.We knew they’d been busy, context-switching between technical challenges, neck-deep in research, fielding customer support, and unblocking other team members across the org. When it was their turn to give an update, you could see them struggle to remember what they’d accomplished and explain what’s next.Something had to changeDuring one particular stand-up where everyone seemed to be reading from the same script of vague progress updates, Ali, our Senior Developer Advocate, finally said what…

Back to Blog Top 3 ways to improve your work performance (that I wish I’d learned sooner)Discover the top 3 ways to improve work performance, based on real experience, not just theory. Learn how to gain clarity through context tracking, reduce mental load by automating reporting, and turn daily updates into actionable personal insights.Hanna StechenkoPerspectivesNovember 25, 2025If you’d asked me a year ago how to improve work performance, I probably would have rattled off the usual suspects: work harder, attend more meetings, try to multitask better. But the reality, as I’ve learned through experience (and a few hard lessons), is that real improvement comes from working smarter, not just harder.Here are the top 3 ways to improve work performance that truly made a difference for me.Gaining clarity through context trackingIf there’s one universal truth about modern work, it’s this: we’re all drowning in information. Between emails, meetings, chat threads, and endless to-do lists, it’s easy to lose sight of what actually matters.Most people don’t realize how much time they spend just trying to remember what happened yesterday, why a decision was made, or where that critical piece of …

Back to Blog We fixed every other meeting problem. Why not stand-ups?Most teams hate standup meetings but keep doing them anyway. We used AI to capture our work automatically and skip the meeting entirely. Here's how it works.Nolan TaftProductivityNovember 21, 2025It's wild how we can collectively complain about the same broken process and still show up to it every single day.Think about it, five years of daily stand-ups, recycling the same complaints, just packaged in different words. We’ve reinvented every other broken meeting: we have Slack for async conversations, Asana for visual progress tracking, and tools like Granola that turn discussions into actionable summaries.And yet… the stand-up survives.Despite the workshops, retros, tons of research, and "10 Ways to Fix Your Stand-ups" – nothing really changes.Maybe we're asking the wrong question. Maybe the problem isn't the format. Maybe it's that we're performing productivity instead of capturing it.The performative burnout we're all livingLet’s start with something every major study mentions, since understanding how we got here might reveal a deeper layer of the problem. I call it performative burnout.It's the tired feeling th…

Back to Blog How to have a better stand-up meeting than 99% of peopleStop treating standups like boring task reports. Learn how 1% of teams actually take advantage of that. Real example with team quotes and results.The Pieces TeamProductivityNovember 17, 2025Most teams treat daily stand-ups like a necessary evil, "daily task updates that everyone sits through but no one likes."But here's what the 1% of high-performing teams understand: the problem isn't stand-ups themselves. It's that 99% of teams completely miss the real opportunity – creating clarity, building trust with your manager, and turning scattered work into coherent progress. The teams that get this right don't just have better meetings, they have better relationships, clearer expectations, and more meaningful career growth.Yes, that’s right, "meaningful".Stop performing, start capturingThe irony is that while promoting Pieces' AI memory everywhere, we were stuck in the same broken stand-up cycle. Our ML engineers got pulled from deep work for timezone-mismatched meetings. Our marketing team struggled to translate complex technical developments into 15-minute verbal summaries that lost all context.And like most teams, we…

Back to Blog Why stand-ups feel harder than they shouldStruggle to remember what you did before stand-ups? Here’s why daily updates feel harder than they should, and how to make them effortless.Mack MyersProductivityNovember 17, 2025It's Monday morning. You're planning the week ahead, trying to remember where you left things on Friday. You skim a few emails. Scroll through Slack. Open a few tabs. Check your calendar.Somewhere in the middle of piecing it all together, you realize your first stand-up is about to start. You take a breath. What did I even do last week? What should I say?You're not unprepared, but you feel buried under information.The stand-up spiralStand-ups have a way of sneaking up on you. One minute you’re catching up, the next you’re on the spot, expected to sound crisp and confident about everything you’ve done and everything you’re about to do.Most of the time, it’s not that you don’t know, you just can’t recall it all fast enough. You’re juggling too many details spread across too many places.So you wing it. You give a quick summary. You hope you didn’t forget anything important.Then, two minutes after the meeting ends, it all comes rushing back. Ah, I should’ve…

Back to Blog How we automated stand-up meetings (and why you should too)Stop scrambling to remember what you worked on yesterday. Learn how one developer automated daily standup updates with AI, transformed "no updates from me" into career-advancing insights, and why this simple hack is changing how teams communicate their real impact.The Pieces TeamProductivityNovember 14, 2025Stand-up meetings. Love 'em, hate 'em, they're on your calendar every week.If you've ever been in a stand-up meeting, it goes one of two ways. Either you mumble "no updates from me" and pray nobody asks questions... or you spend 20 minutes writing an update from scratch, trying to remember what the hell you actually accomplished.If you're a developer, product manager, or anyone doing daily or weekly stand-ups, you know exactly what I'm talking about.We’re gonna save you some time, and share one thing that took a long time to learn — this meeting is NOT just a status update. Your manager is listening. Your team is forming opinions about your work. And whether you realize it or not, your stand-up updates are massively shaping your career.Today, we’re going to show you how we automated the entire stand-up proce…

Back to Blog 11 Best IDEs for Python developers in 2025Explore 11 top Python IDEs to boost productivity, streamline coding, and enhance your development workflow.Emmanuel IsenahSoftware DevelopmentNovember 14, 2025I’ve spent more late nights than I’d like to admit hopping between editors these past few months in search of the perfect IDE. What began as a one-time upgrade turned into a long exploratory journey.I tried everything from the classic VS Code to the latest AI‑powered tools like Windsurf and Cursor. There are just so many IDEs out there today that it's hard to know which one to commit to.In this article, I'll share my first‑hand findings and discuss some of the cool features and downsides each IDE possesses.My methodologyWhile writing this piece, I took into account the following five key factors:Plugin & Ecosystem: How much support is there for third‑party plugins and does it integrate well with other tools and libraries?Pricing: Is it free, or subscription-based?Performance: Startup time, memory footprint, and general snappiness under load. - Configurability: What is the depth of customization available? Can I tailor every minute detail to my heart’s content?AI Integrati…

Back to Blog Your go-to daily standup agenda and how to actually make it workDiscover how to run daily stand-up meetings that actually drive results. Learn the meaning of a stand-up meeting, see classic and modern agenda examples, and explore best practices for team stand-ups.The Pieces TeamProductivityNovember 12, 2025If you’ve ever wondered what a stand-up meeting is or found yourself zoning out during a daily check-in, you’re not alone. At Pieces, we’ve seen firsthand how a well-run daily stand-up meeting agenda can transform a team’s energy, alignment, and output. But we’ve also seen how easily these meetings can slip into routine, losing their impact and becoming just another calendar item.This guide is for anyone who wants to run stand-ups that actually help, whether you’re new to agile, leading a remote team, or just looking for ways to make your work stand-up meetings more effective.What is a stand-up meeting? (and why do we still do them?)Let’s start with the basics: stand-up meeting meaning. A stand-up is a short, focused daily meeting where team members quickly share what they’re working on, what’s next, and what’s blocking them. The idea is to keep everyone aligned, sur…

Back to Blog How to use AI Memory in Claude desktop (and why It changes everything)Explore how prototypes lay the foundation for long-term memory in AI. Learn why early experiments, iteration, and design “blueprints” are critical for building durable, context-rich intelligence.The Pieces TeamAI & LLMsSeptember 18, 2025Most AI tools are brilliant at answering questions in the moment. They can brainstorm, write drafts, or help you debug. But the second you close the chat, everything disappears. No memory. No continuity. No context carried over.If you’ve ever felt frustrated re-explaining the same details to Claude over and over, you’re not alone. It’s not your fault, Claude, like most AI assistants, wasn’t designed with long-term memory built in.But what if you could change that? What if Claude could remember your projects, your workflows, and your past conversations and help you pick up exactly where you left off?That’s now possible. By connecting Claude Desktop with an AI memory system, you can give it the power to create and access long-term memories. In this guide, we’ll explain how to set it up, how to use it, and why it’s a game-changer for productivity.Why memory matters in AI…

Back to Blog Prototypes: the glue of Long-Term MemoryExplore how prototypes lay the foundation for long-term memory in AI. Learn why early experiments, iteration, and design “blueprints” are critical for building durable, context-rich intelligence.The Pieces TeamAI & LLMsSeptember 17, 2025This isn’t a new idea. Prototypical networks, the machine learning trick that powers systems like Google Photos work the same way. Embed a bunch of images of the same person, average them, and you get a prototype vector. That prototype becomes the stable representation, even as the raw inputs vary.It’s a simple idea with massive implications:Multimodality strengthens identity. Store text and images and voice, and you get a far more resilient anchor.Prototypes scale. As your model backbone improves, the prototypes get stronger too.Hard facts matter. Anchoring memory in prototypes creates “ground truth” for the system to lean on when generating.We’ve been exploring similar patterns at Pieces. In some of our OCR cleanup experiments, we’ve paired extraction with narrative generation loops to make reasoning more robust. The parallel here is obvious: if you want reliable long-term context, you need more…

Back to Blog Why developers need AI that actually gets Their contextTired of re-explaining your codebase to AI every week? Discover why developers need context-aware AI that remembers your workflow. Learn how Workstream Activity, Sources, and Time Ranges in Pieces give you control, continuity, and a searchable memory for your entire dev process.The Pieces TeamPerspectivesSeptember 15, 2025You know the drill.It's Monday morning. You fire up your IDE, stare at the screen, and... what was I working on again?You waste 20 minutes hunting through commit messages, trying to remember why you left that TODO comment. Or you find yourself re-explaining your entire codebase to ChatGPT for the third time this week because it has zero memory of your previous conversations.Sound familiar? You're not alone. Most AI tools treat every interaction like you're meeting for the first time. They don't understand your project, your patterns, or the context that makes you productive.What you really need isn't another generic AI assistant. You need one that actually gets your workflow and remembers it.Meet Workstream Activity: Your Development Context, CapturedThis is exactly why we built Workstream Activit…

Back to Blog AI memory explained: what Perplexity, ChatGPT, Pieces, and Claude remember (and forget)Discover the different types of AI memory, how they work, key use cases, and the best prompting approaches to get accurate, context-aware responsesAntreas AntoniouAI & LLMsSeptember 11, 2025Think about how you use your own memory. Some things live in your short-term recall, like the phone number you just looked up or what you had for lunch yesterday. Other things live deeper: like your favorite lunch menu, the name of your first teacher, the stories you tell at family dinners.Now imagine if you only had the Post-it note version of memory. You'd remember fleeting details, but the moment you left the room, it would all be gone.That's how most AI assistants worked until recently: stateless. Each chat was a blank slate. Helpful in the moment, but forgetful the next.Now engineers start noticing something is missing in their AI assistants. These systems could impress with their intelligence, drafting essays, writing code, summarizing research, but they couldn't remember who you were or what you cared about. In the excitement of generative AI's breakthrough moment in 2023, few questioned wh…