diff --git a/public/content/core-dependencies/pieces-os.md b/public/content/core-dependencies/pieces-os.md index d84c726..4a5175c 100644 --- a/public/content/core-dependencies/pieces-os.md +++ b/public/content/core-dependencies/pieces-os.md @@ -46,7 +46,7 @@ The Long-Term Memory (LTM-2.7) Engine is a powerful evolution of the original LT By automatically capturing workflow context and providing flexible memory browsing, LTM-2.7 ensures you don't lose track of code, discussions, or references—even if you return to a project weeks or months later. These workflow events and summaries can be found within the [Timeline](/products/desktop/timeline) view in the [Pieces Desktop App](/products/desktop). - Here's a quick read on some of the nano-models we develop that layer into the data retrieval pipeline for LTM-2.7. + Here's a [quick read on some of the nano-models](https://tsavo.hashnode.dev/temporal-nano-model-breakthrough) we develop that layer into the data retrieval pipeline for LTM-2.7. ### Deep Study @@ -84,8 +84,8 @@ Under the hood, LTM monitors your workflow at the operating system level, captur LTM (through PiecesOS) extends your ability to [enable or disable specific sources](/products/core-dependencies/pieces-os/quick-menu#quick-menu-actions) for data capture—this way, you can decide exactly what gets tracked and stored, providing flexibility if you have sensitive or personal workflows. - - The data captured by LTM is processed and stored entirely on your device, so you don't need to worry about privacy and security—[which you can read more about here.](/products/privacy-security-your-data) + + LTM data is stored on your device. Processing depends on your [processing mode](/products/desktop/configuration/models) and model choice: **Local** does most processing on-device but can still use an external cloud model. **Blended** and **Cloud** send context to cloud providers. [Learn more about privacy and security.](/products/privacy-security-your-data) ### Less Context Switching @@ -152,8 +152,8 @@ LTM applies on-device machine learning algorithms to filter out sensitive inform ## Pieces Drive -Pieces Drive is a legacy material manager that allows you to save, manage, and share developer resources. This feature will be merged with Timeline in a future update. +[Pieces Drive](/products/desktop/drive) is a legacy material manager that allows you to save, manage, and share developer resources. This feature will be merged with Timeline in a future update. *** -If PiecesOS isn't what you're looking for, check out the [Pieces Desktop App](/products/desktop) to see how these components work together, or explore [Conversational Search](/products/desktop/conversational-search) to learn how to talk with your memories. +Check out the [Pieces Desktop App](/products/desktop) to see how these components work together, or explore [Conversational Search](/products/desktop/conversational-search) to learn how to talk with your memories. diff --git a/public/content/core-dependencies/pieces-os/quick-menu.md b/public/content/core-dependencies/pieces-os/quick-menu.md index 58d82dd..625bf43 100644 --- a/public/content/core-dependencies/pieces-os/quick-menu.md +++ b/public/content/core-dependencies/pieces-os/quick-menu.md @@ -85,6 +85,14 @@ To do so, click the `Pieces` logo in your taskbar or toolbar, and click `Enable Conversely, you can click the green `On` button to display a drop-down menu that lets you disable the LTM temporarily in minute increments or altogether. +### LTM Audio (Audio Ingestion) + +LTM Audio enables the Long-Term Memory Engine to capture system audio and microphone input. From the Quick Menu, scroll to *LTM Audio* and toggle it on or off. + + + On macOS, LTM Audio requires [System Audio Capture and Microphone Access permissions](/products/desktop/configuration/long-term-memory#ltm-audio) before it can be enabled. First-time users may see a yellow warning indicator on their User Profile—click it to grant the required permissions. + + ### Long-Term Memory Access Control This section allows you to manage which applications and sources LTM captures data from through two menus: diff --git a/public/content/desktop/configuration/long-term-memory.md b/public/content/desktop/configuration/long-term-memory.md index d11b60e..5cd5a8c 100644 --- a/public/content/desktop/configuration/long-term-memory.md +++ b/public/content/desktop/configuration/long-term-memory.md @@ -88,6 +88,101 @@ Manage accessibility and screen permissions for the Long-Term Memory Engine. If +### LTM Audio + +LTM Audio, also known as Audio Ingestion, enables the Long-Term Memory Engine to capture system audio and microphone input to enhance your workflow context. This feature is currently in *Preview* and requires platform-specific permissions. + + + + + + + + > LTM Audio setup on macOS + + First-time users will see a yellow warning indicator on the `Enable LTM Audio` option when they open their `User Profile` in the top left. Click the `warning indicator` to open the permissions dialog and grant the required access. + + + + Click your `User Profile` in the top left. If you see a yellow warning indicator, click it to open the "Some Permissions Are Missing" dialog. Otherwise, go to *Settings* → *Long-Term Memory* → *Long-Term Memory Permissions*. + + + + In the permissions dialog, locate "System Audio Capture" and click the `Allow` button. This opens the macOS *Privacy & Security* → *Screen & System Audio Recording* settings. + + + + In the *System Audio Recording Only* section at the bottom, click the `+` button. Navigate to *Applications* in Finder and select `Pieces OS`. The system will prompt you to restart Pieces OS—choose `Quit & Reopen`. + + + + After restarting, the permissions dialog will prompt you to grant Microphone Access. Click the `Allow` button for "Microphone Access" to open the macOS *Privacy & Security* → *Microphone* settings. + + + + In the Microphone settings, find `Pieces OS` and turn the toggle on. Choose `Quit & Reopen` when prompted to restart Pieces OS. + + + + Once permissions are granted, click your `User Profile` in the top left and click `Enable LTM Audio` to turn the feature on. Alternatively, click the `PiecesOS` icon in your menu bar to open the dropdown, scroll to *LTM Audio*, and enable it there. + + + + + LTM Audio is a *Preview* feature. You must grant both System Audio Capture and Microphone Access, then restart Pieces OS after each permission change, before the feature can be enabled. + + + + + + + > LTM Audio setup on Windows + + On Windows, LTM Audio prompts for microphone permission only. Accept the prompt and the feature is enabled—no system audio capture or restart required. + + Enable LTM Audio from your `User Profile` in the top left, or from the PiecesOS icon in your system tray—click it to open the dropdown, scroll to *LTM Audio*, and toggle it on. + + **If you skipped the initial permission prompt** + + You can grant microphone access through Windows Settings: + + + + Press `Win + I` or click the `Start` button and select `Settings`. + + + + Go to `Privacy & Security` (Windows 11) or `Privacy` (Windows 10), then select `Microphone`. + + + + Turn on *Microphone access* if it is off. Find `Pieces OS` in the list of apps and enable the toggle next to it. + + + + Restart Pieces if it was open, then enable *LTM Audio* from your `User Profile` or the `PiecesOS` system tray dropdown. + + + + + LTM Audio is a *Preview* feature. Accept the microphone permission when prompted to enable the feature. + + + + + On Linux (Snap installation), run `pieces-os.doctor` after installation. The script outputs a command you can copy and paste into your terminal to connect all interfaces with the system. + + Once the interfaces are connected, enable LTM Audio from your `User Profile` in the top left, or from the PiecesOS icon in your application tray—click it to open the dropdown, scroll to *LTM Audio*, and toggle it on. + + + LTM Audio is a *Preview* feature. Run `pieces-os.doctor` to connect system interfaces before enabling the feature. + + + + ## Performance Optimize system resources and manage memory usage for the Long-Term Memory Engine. diff --git a/public/content/desktop/configuration/models.md b/public/content/desktop/configuration/models.md index b32e42c..f84110d 100644 --- a/public/content/desktop/configuration/models.md +++ b/public/content/desktop/configuration/models.md @@ -225,6 +225,33 @@ Each provider can be expanded to see individual models, and you can enable or di For a complete list of all compatible models and their capabilities, see the [Compatible LLMs](/products/large-language-models) documentation. This page provides detailed information about cloud models, local models, and which models work best for different use cases. +### Free vs Pro Model Access + +Model access depends on your plan. Free users get full access to local models and limited usage of cloud models. Pieces Pro subscribers get unlimited access to premium cloud LLMs. + +#### Free Plan — Models + +The free plan includes: + +* **Local models (Ollama)**: Full access with no usage limits. Download and run models like Llama, Gemma, Phi, and others entirely on-device. +* **Cloud models**: Limited usage. Access to select cloud models with usage caps—ideal for getting started and trying AI-assisted development. +* **Basic AI features**: Snippet management, local storage, and community support. + + + Model availability and usage limits may vary. See the [Cloud Models](/products/large-language-models/cloud-models) page for the latest list and plan-specific availability. + + +#### Plan Comparison + +| **Feature** | **Free** | **Pieces Pro** | +|-------------|----------|----------------| +| Local models (Ollama) | Full access, no limits | Full access, no limits | +| Cloud / premium models | Limited usage | Unlimited access | +| Long-term memory | Standard | Infinite | +| Deep Study reports | — | ✓ | + +For pricing and upgrade options, see [Pieces Pro](/products/paid-plans). + *** ## Next Steps diff --git a/public/content/desktop/conversational-search/context-integration.md b/public/content/desktop/conversational-search/context-integration.md index 8a98f9d..b6f57ea 100644 --- a/public/content/desktop/conversational-search/context-integration.md +++ b/public/content/desktop/conversational-search/context-integration.md @@ -12,6 +12,10 @@ metaDescription: Enable or disable Long-Term Memory context in Conversational Se Control whether Conversational Search includes Long-Term Memory context in your conversations. When enabled, Conversational Search has access to 9 months of captured workflow context from your [Long-Term Memory (LTM-2.7)](/products/core-dependencies/pieces-os#ltm-27) Engine, including code you've written, conversations you've had, and decisions you've made. + + LTM must be enabled to access the chat feature in Pieces Desktop. If LTM is off, chat does not work. LTM is enabled by default in conversations. + + ## LTM Context Toggle Enable or disable Long-Term Memory context for Conversational Search. When enabled, your chats automatically include workflow history context. When disabled, conversations use only the current context without historical data. diff --git a/public/content/meet-pieces/linux-installation-guide.md b/public/content/meet-pieces/linux-installation-guide.md index 3a26c91..9796aeb 100644 --- a/public/content/meet-pieces/linux-installation-guide.md +++ b/public/content/meet-pieces/linux-installation-guide.md @@ -45,8 +45,12 @@ There are several requirements that your Linux device must meet to download and 2. `sudo snap connect pieces-os:process-control :process-control` 3. `sudo snap install pieces-for-developers` + + Run `pieces-os.doctor`. The script outputs a command; copy and paste it into your terminal to connect all interfaces with the system. Then, type `pieces-for-developers` to launch the application directly from your terminal. + + Your Linux device must be running a supported distribution of Ubuntu—**Ubuntu 22+.** @@ -61,6 +65,10 @@ Installation of PiecesOS and the Pieces Desktop App on supported Linux systems i Read the documentation below for tips and information to ensure you’re up and running with the latest versions of PiecesOS and the Pieces Desktop App, as well as steps to uninstall Pieces software from your Linux device. +### Connect System Interfaces + +After installing via snap, run `pieces-os.doctor` in your terminal. The script outputs a command you can copy and paste to connect all interfaces with the system. This step is required for full functionality, including features like [LTM Audio](/products/desktop/configuration/long-term-memory#ltm-audio). + ### Updating The Pieces Desktop App automatically downloads and installs new updates. diff --git a/public/content/meet-pieces/macos-installation-guide.md b/public/content/meet-pieces/macos-installation-guide.md index 064ed00..b9d988f 100644 --- a/public/content/meet-pieces/macos-installation-guide.md +++ b/public/content/meet-pieces/macos-installation-guide.md @@ -9,7 +9,12 @@ metaDescription: Get started with Pieces on macOS – install, configure, troubl ogImage: "https://storage.googleapis.com/hashnode_product_documentation_assets/og_images/meet_pieces/meet_pieces_macos_install.webp" --- - + + + *** diff --git a/public/content/paid-plans.md b/public/content/paid-plans.md index ec10d25..859b4b3 100644 --- a/public/content/paid-plans.md +++ b/public/content/paid-plans.md @@ -87,6 +87,46 @@ Choose the plan that works best for you: +## Plan Comparison + +Compare Free and Pieces Pro to see which plan fits your workflow. + +### Free Plan — Model Access + +The free plan includes full access to local models (Ollama) with no usage limits, plus limited usage of select cloud models. You can use on-device models like Llama, Gemma, and Phi for private, offline use. Cloud model usage is capped—upgrade to Pro for unlimited access to premium LLMs. + +| **Feature** | **Free** | **Pieces Pro** | +|-------------|----------|----------------| +| Cloud / premium AI models | Limited usage | Unlimited access | +| Local models (Ollama) | Full access, no limits | Full access, no limits | +| Long-term memory | Rolling window (time-bound) | Unlimited (up to 9 months) | +| Deep Study reports | — | ✓ | +| AI-powered code generation | Basic | Advanced | +| Support | Community | Priority | +| Cloud backup | Limited | Full | + +For details on which models are available on each plan, see [Models](/products/desktop/configuration/models#free-vs-pro-model-access). + +## Frequently Asked Questions + + + + Both. Pro gives you longer memory retention *and* access to more powerful models for searching and reasoning over your stored context. The Long-Term Memory engine that captures and organizes your workflow data is the same on both plans—the main differences are *duration* and *retrieval quality*. + + + + The free plan is time-bound: you have access to a rolling window of recent history. Pieces Pro offers unlimited long-term memory with up to 9 months of context. + + + + The free plan includes limited usage of select cloud models to get started. Pro offers unlimited access to premium LLMs including GPT-5, Claude, Gemini, and thinking models. [See the full model list](/products/large-language-models/cloud-models) for details on which models are Free vs Pro. + + + + No. The engine that captures and organizes your data is the same. Pro users get *longer* retention (up to 9 months vs a rolling window) and can use more powerful models to *search and query* those memories, yielding deeper insights—but the underlying memory formation is identical. + + + ## Benefits Unlimited access to *premium LLMs, infinite long-term memory,* and *priority support* are a combination that empowers your team to code smarter, faster, and with greater confidence.