Chronological work timeline
Captures research, chats, emails, notes, meetings, and other work activity in a searchable timeline that can be filtered and revisited.
An on-device work memory layer that helps individuals and teams recover context across their tools.
Pieces is a work-memory application from Mesh Intelligent Technologies that captures activity from the apps and websites you use, then makes that context searchable. It is designed to help people recover decisions, resume unfinished work, and provide relevant background to AI assistants. Memories are saved on the user's device by default, with controls to pause capture or remove data from selected times, apps, websites, or capture methods.
The product organizes research, messages, email, notes, meetings, documents, design work, and development activity into a chronological timeline. Users can ask questions about past work and narrow results by time, source, or topic. Pieces also provides generated standup updates, morning briefs, meeting preparation, and day recaps based on captured context.
Pieces includes an MCP Server that carries a user's work history into supported assistants and development tools, including Claude, Cursor, Codex, Antigravity, and other MCP-ready applications. Pro is intended for individual use, while Enterprise adds organization-level controls such as approved providers, API key management, and capture policies.
Captures research, chats, emails, notes, meetings, and other work activity in a searchable timeline that can be filtered and revisited.
Lets users ask questions about past work and scope prompts by time, source, or topic to locate decisions, people, and project context.
Generates standup updates, morning briefs, meeting preparation, and day recaps from the user's captured work context.
The Pieces MCP Server makes work history available to Claude, Cursor, Codex, Antigravity, and other MCP-ready assistants.
Stores memories on-device by default and lets users pause Pieces, disable capture for selected apps and websites, or delete data by time, source, or capture method.
The Enterprise plan adds organization-level capture and feature controls, approved AI providers, and support for an organization's own API keys.
Find an article, source, tab, note, or research trail from earlier work and continue a project without reconstructing the path manually.
Use captured email, chat, document, and prior meeting context to assemble preparation material, decisions, and relevant follow-ups.
Generate standup updates, morning briefs, and end-of-day recaps from the activity recorded during a person's workday.
Bring prior prompts, code edits, terminal activity, debugging context, and implementation history into supported coding assistants.
Use organization controls to govern providers, sources, and capture features when deploying Pieces across a team.
Memories are saved on the user's device by default. Users can pause capture, disable it for specific apps or websites, and delete data by time, app, website, or capture method.
The Pieces MCP Server carries work history into Claude, Cursor, Codex, Antigravity, and other MCP-ready AI assistants.
Pieces is a paid product. New users receive a 7-day trial on any plan, and each plan includes a 14-day money-back guarantee. A card is required to start the trial.
Pro is designed for one person to capture and recall personal work context. Enterprise adds organization-level policies, approved providers, feature controls, and support for an organization's own API keys.
トラフィックデータは参考情報としてご利用ください。
luci.memories.ai
LUCI is a local desktop memory tool for Mac and Windows that captures computer activity and meetings, then makes that context available to search, chat, and connected AI coding agents. It is designed for people and teams that need persistent context across calls, screens, notes, and everyday workflows.
www.earlyn.app
A private Mac memory for searchable screen history, meeting notes, and AI-agent context.
unabyss.com
Connect work apps to one structured context layer, then let supported MCP agents retrieve, update and export the context their tasks need.