Product Thumbnail

Pieces Long-Term Memory Agent

The first AI that remembers everything you work on

Productivity
Software Engineering
Developer Tools

Ever wish you had an AI tool that remembered what you worked on, with who, and when across your entire desktop? Pieces Long-Term Memory Agent captures, preserves, and resurfaces historical workflow details, so you can pick up where you left off.

Top comment

Hey Product Hunt!

Tsavo Knott here, CEO and Co-Founder of Pieces 👋. Today, we're launching Pieces Long-Term Memory Agent (LTM-2)—the first AI that remembers everything you work on.

AI has transformed how we build software, but it's always been missing one critical component: Memory.

Developers waste hours every week searching for lost work, switching between apps, and trying to reconstruct past decisions.

Code snippets, critical insights, and problem-solving steps get buried in Slack, lost in browser tabs, or forgotten in old commits. By the time you find what you need, your flow is broken, momentum is gone, and sometimes you end up rebuilding from scratch.

AI can generate content, but it doesn’t remember your work. Every day starts from zero.

That’s why we built Pieces Long-Term Memory (LTM-2), the first AI that captures everything you work on across desktop applications, browsers, IDEs, terminals—wherever you work.

It runs directly on macOS, Windows, and Linux, continuously structuring and resurfacing your work so you can pick up right where you left off. It remembers for months, organizing everything just like your brain does.

What LTM-2 Does

  • Remembers for 9+ months – Code, notes, links, and side conversations that shaped your decisions.

  • Instant recall – Ask, “When was the last time I hit this error?” or “What was I working on before Thanksgiving?” and get answers fast.

  • Workstream Activities – A full visual timeline showing what you did, when, and why.


Private & Built for Teams

  • 90% runs offline – Keeps your data secure and private.

  • Full control – Pause memory, block apps, or delete data anytime.


Pioneering OS-Level AI Memory

We’re not just launching a tool—we’re building a new category: OS-level Artificial Memory.

LTM-2 is a massive leap forward, and LTM-2.5 and LTM-3 are already in the works.

We can’t wait for you to try it and see how AI that remembers changes the way you work.

Let us know what you think!

Cheers,
Tsavo

Comment highlights

Absolutely phenomenal feature, LTM. Not sure we've seen anything like it(or even close). Go Pieces!

I'm not a developer, but my memory is definitely running low! :) Congrats on the launch!

I really took my time to write a comment about the LTM-2 because I wanted to thoroughly test its features, and I have to say, this version is absolutely incredible. The fact that it can store my workflow history for up to nine months is mind-blowing, and even better, all the data is stored locally on my system.


Another aspect worth highlighting is the addition of new control options like 'Sources' and 'Time Range,' which weren't available in LTM-I. These features make a significant difference in how I use the tool compared to before. Speaking of performance, the speed improvement is remarkable. With LTM-I, there were instances when retrieving the most recent data failed, or when it worked, it often took an excessive amount of time to generate a response. However, those issues seem to be completely resolved in LTM-2.


On a side note, I've been reading articles and blogs about Pieces, and I'm genuinely excited to try out LTM-2.5 and LTM-3 in the near future!


PS: I tried posting this yesterday, but it didn't go through. Today, I asked Pieces, and he wrote everything exactly as I had written it before.

Very cool product. I realise you have an SDK which we can use to build on top of, but I was curious about how (if at all) you handle caching of prompts. Because for some use cases prompts might be repetitive and can significantly make a product efficient/affordable if such prompts are cached

This is such a cool product. I think it's going to completely change how I work!
Congrats on the launch !🥳

LTM-2 has been like a time machine for me (minus the chance of destroying the future). It’s been awesome

I love using Pieces! It's my go-to AI tool.


I appreciate the continuous improvements and the team's quick response to questions and feedback.


Keep up the great work!

This is great, I like having a desktop agent that can find old emails for me without me having to search forever.

Pieces for Developers is an AI-driven tool aiming to enhance developer productivity by managing code snippets and integrating seamlessly with various IDEs and collaboration platforms.Its Long-Term Memory Engine captures and resurfaces workflow details, allowing developers to pick up where they left off.
However, some users have noted that the free version offers limited functionality, with advanced features locked behind a subscription.dditionally, certain features require an internet connection, which might be a drawback for those working in offline environments.
In comparison, tools like GitHub Copilot provide AI-assisted code completion directly within the coding environment, offering real-time suggestions without the need for extensive context switching. While Pieces emphasizes code snippet management and workflow memory, Copilot focuses on in-the-moment coding assistance.

I have been using for the last 5 days and I installed the update this morning and turned on the LTM2 work stream activities and connected with GitHub and asked the pieces copilot to assist with planning on a NVIDIA Hackathon submission and it leveraged my work stream activity and included the NVIDIA AI Workbench with NIMS Anywhere project with openUSD kit application for viewing openIFC projects. This was based on different applications that I was setting up environments for and a coding project that I have been working on. Very impressive on how it uses the workstream activity for adding to the context. I also like the ability to use local only models when needed. Having the flexibility to use offline or hybrid local and cloud is very useful.

And yet another awesome drop from the @Pieces for Developers crew! Cheers

Pieces Long-Term Memory Agent is an incredibly powerful tool for managing information and long-term memory! With its intuitive ability to organize and connect information, Pieces makes it easy for me to access and share the information I need, even if it's from years ago.


I'm blown away by Pieces' seamless integration with various apps and services, making it incredibly user-friendly. With Pieces, I can save time and boost my productivity in managing information.


If you're looking for a tool that can help you manage information and long-term memory more effectively, then Pieces Long-Term Memory Agent is the perfect choice!

Now i don’t have to dig through my precious projects for important snippets

I had the pleasure of being invited by their team to try out Pieces for Developers, and the CEO and Co-founder, Tsavo, also gave me a live demonstration!


Pieces for Developers is a " game-changing " platform that takes developer productivity to a new level!


I highly recommend trying it out for yourself and seeing how it can significantly improve your workflow.

Hey Tsavo,

Congrats on launching Pieces Long-Term Memory Agent! The ability to retain and recall work across multiple apps is a game-changer—finally solving the lost momentum problem developers deal with daily. Love the focus on privacy and offline functionality too.

I am launching today and understand the huge effort! Wishing you and the team an amazing launch.

Don
Founder

I use Pieces daily as an assistant and tutor. The desktop app is wonderful, and I even use the Pieces vsCode extension to explain snippets to me as I code. Long-term memory is my BFF on desktop for sure!

A @Quadratic integration would be too good... "What was the Python code I used to generate a data visualization in my spreadsheet last week? Run that again here."