Developers who forget what they worked on last week may value its on-device memory, but there is no free plan after the trial.
Kenning's take
What it does
Pieces runs in the background on a computer and captures what is on screen, copied text and, if switched on, meeting audio into a timeline stored on the device. It can answer questions about past work and write standups, recaps and meeting prep. Its MCP server passes that history to tools such as Claude, Cursor and Codex.
- Timeline of research, chats, emails and meetings
- Search by time, topic, person or tool
- Standups, morning briefs and day recaps
- Pieces MCP Server for Claude, Cursor and Codex
- Memories stored on-device by default
- Choice of Claude, Gemini, ChatGPT or local models
Who it suits. Developers and knowledge workers who want their AI tools to remember what they worked on.
Key facts
- Category
- Developer tools
- Made by
- Mesh Intelligent Technologies, Inc.
- How to get it
- Download the desktop app; 7-day free trial, then a paid plan
- Works on
- macOS, Windows, Linux
- Free plan
- No free plan; 7-day free trial on any plan
Pricing
| Plan | Price | Billed |
|---|---|---|
| Pro | $18.99 | month |
| Enterprise | $22.99 | month |
FAQ
Is Pieces free?
No. New users get a 7-day free trial, then Pro costs $18.99 per user per month.
Where does Pieces store data?
Memories are saved on the user's device by default.
Which AI tools work with Pieces?
Its MCP server carries history into Claude, Cursor, Codex and other MCP-ready assistants.
Facts from the maker's own pages and the sources listed. Checked 2026-10-11.
Similar tools

Claude Keychain
A free Mac menu bar app that keeps API keys in the macOS Keychain so Claude Code can use them without seeing them.
OpenAI Agent Builder
OpenAI's visual canvas for building multi-agent workflows, being withdrawn on 30 November 2026.
ElevenLabs Agent Workflows
Visual editor in ElevenLabs' agent platform for designing branching conversation flows for voice and chat agents.

AgentOps
Monitoring and debugging platform that records what AI agents do, what they cost and where they fail.