Pieces is an AI assistant with long-term memory that operates at the operating system level for developers. It automatically captures your work context — code, tabs, messages, meetings — without any manual action, and makes it naturally queryable at any time. Its LTM-2 (Long-Term Memory) engine builds a private second brain accessible through a contextual AI copilot, plugins for VS Code, Chrome, JetBrains, Obsidian and other tools. Pieces is on-device by default: no data is sent to the cloud without explicit authorization. The free plan gives access to all basic features, and the Pro plan at $18.99/month unlocks premium LLMs like Claude and Gemini.
What is Pieces?
Pieces is a desktop AI application for developers that functions as a persistent and contextual second brain. Its LTM-2 (Long-Term Memory) engine silently and continuously captures what you do on your machine — open code, visited tabs, conversations, meetings, snippets — and makes it queryable in natural language. The tool includes a contextual AI copilot (Pieces Copilot), an AI-enriched snippet management system (Pieces Drive), and integrates into tools you already use through native plugins and the MCP protocol.
Main Features
Pieces groups several key features around memory and context. The Long-Term Memory module (LTM-2) automatically captures work activity at the OS level over a rolling 9-month period, allowing precise temporal queries like “What was I working on last night on this project?”. The Pieces Copilot is an AI assistant that has access to all your captured memory, in addition to the capabilities of the selected LLM, enabling truly contextualized responses to your work. Pieces Drive is an AI-enhanced snippet manager: save, automatic enrichment (tags, description, language), transformation (refactoring, language change) and sharing. Native plugins cover VS Code, JetBrains, Chrome, Obsidian and other tools, avoiding context switching. MCP support allows you to expose Pieces memory to any MCP client (GitHub Copilot, Cursor, Claude, Goose). Finally, privacy is guaranteed by on-device operation by default, with cloud as optional and under your total control.
Use Cases
Pieces adapts to several concrete situations experienced by developers. For technical research, Pieces automatically remembers every page, link and excerpt you consult without having to create a bookmark. For resuming after interruption, a developer can query Pieces to find exactly where they were after a meeting or over the weekend. For snippet management, developers save and quickly retrieve useful pieces of code from any tool. For code review and debugging, session context is preserved and queryable. For collaboration, snippets can be shared with enrichments via personalized links or GitHub Gists.
Advantages
The main advantage of Pieces is drastically reducing the cognitive load of managing context, a problem all developers know but few tools truly address. By automatically capturing all work context, Pieces frees up mental energy for what really matters: code, thinking, problem-solving. The on-device approach by default addresses legitimate privacy concerns of teams working on sensitive projects. MCP compatibility transforms the memory accumulated in Pieces into a resource shareable with all LLMs in the developer ecosystem, multiplying its value.
Pricing
Pieces offers two plans. The Free plan is permanent and includes the AI copilot, Pieces Drive, access to local memory history and unlimited conversations. The Pro plan is $18.99/month and unlocks access to premium LLMs like Claude Sonnet 4, Claude Opus 4, Gemini 2.5 and early access to new models upon release. The desktop application is available on Windows, macOS and Linux, as well as via a browser extension.
Conclusion
Pieces occupies a very specific but extremely useful niche in the AI tools ecosystem for developers: persistent and contextual long-term memory at the operating system level. Its on-device approach by default and ability to integrate via MCP into all developer LLMs and tools make it a unique solution. The free plan is generous and sufficient for the majority of uses. A reference for any developer wanting to stop losing their context.