Always-on listening
Captures spoken activity and turns it into searchable memories, with raw audio processed as a stream rather than retained in the cloud long-term.
Hemory
Hemory is an always-on listening and memory tool that turns conversations, meetings and voice notes into searchable source material. Individuals can use its built-in Q&A or connect MCP-compatible agents to generate follow-ups, reports, journal entries and product documents.
A searchable memory layer for spoken activity
Hemory is a listening and memory tool for turning spoken activity into searchable source material. It captures conversations, meetings and voice notes, then organizes the resulting information into memories, transcripts, activity segments, summaries and minutes.
The product can be used on its own through its search and Q&A features or connected to external AI agents through MCP. This lets an agent answer questions grounded in prior sessions or generate material such as follow-ups, reports, journal entries and product documents. Listening can be started manually or scheduled, while the service separates cloud processing from local raw-audio storage.
Core features
Voice-activity detection
Voice-activity detection excludes silence, gaps and background noise from listening-hour usage, making scheduled listening practical for longer sessions.
Activity processing
Automatically separates activity and provides type-aware summaries and minutes, with speaker recognition by voice listed among the included capabilities.
Memory search and Q&A
Ask questions through Hemory's built-in agent, or search memories for details from earlier conversations and sessions.
MCP agent connection
Connects to mainstream MCP clients, including Claude Code, Codex, Gemini, Cursor, VS Code, OpenClaw and Hermes, so external agents can use Hemory memories as context.
Flexible capture controls
Supports manual and scheduled listening, with Apple Watch listening listed as an included capability on the pricing page.
Practical use cases
Meeting follow-ups
Capture a meeting and later ask what a participant promised, identify decisions, or retrieve details from a particular session without relying on memory or handwritten notes.
Work reporting
Use a connected MCP agent to turn conversations from a work period into a monthly report page containing progress, takeaways and a plan for the next month.
Personal notes and journaling
Record voice notes during a walk or after an event, then use the searchable memory and Q&A workflow to turn them into a concise journal entry or follow-up draft.
Research and product planning
Combine customer interviews and internal brainstorms as source material for a product requirements document, allowing an agent to synthesize the sessions into a structured draft.
Pros and Cons
Pros
- Turns everyday conversations and voice notes into searchable source material rather than requiring manual transcription.
- Supports both built-in questions and MCP-connected agents for generating documents from prior sessions.
- Offers manual and scheduled listening with voice-activity metering that excludes silence and background noise.
- States that raw audio is not stored long-term in the cloud and that product audio and transcripts are not used to train AI models.
Cons
- The site lists iOS and Android access, while macOS, Windows, Linux, web and self-hosting are marked as coming soon.
- External agents require an MCP connection, and the available output quality depends on the captured speech and the connected agent's capabilities.
- The Max plan's unlimited listening is subject to a 24-hour-per-day cap and fair-use terms.
FAQ
How do I set up Hemory?
Download Hemory and start listening in manual mode or set a schedule, such as weekdays from 9:00 to 18:00. You can then connect Hemory to a supported agent through MCP; the site shows setup examples for Codex and Claude.
What can Hemory produce from recorded activity?
Hemory processes listening sessions into searchable memories, transcripts, activity segments, summaries and minutes. Its built-in Q&A agent can answer questions about those memories, while connected MCP agents can use them as source material for documents and other outputs.
How is listening time measured?
Voice-activity detection counts only periods when someone is speaking. Silence, gaps and background noise do not consume the listening allowance. On the Max plan, listening is described as unlimited with a 24-hour-per-day cap and fair-use terms.
How does Hemory handle audio and privacy?
The site states that raw audio is processed as a stream and destroyed after processing, while audio stored on the listening device remains local and is not synced across devices. It also states that audio, transcripts and voice feature data are not used to train or improve AI models.
Do the plans have different features?
All listed plans include the same capabilities; the plans differ by listening allowance rather than feature access. The site lists a one-time 10-hour free trial, followed by Starter, Pro and Max subscriptions.
Quick Facts
- Category
- AI productivity and memory tool
- Primary platforms
- iOS and Android; additional platforms listed as coming soon
- Agent connection
- MCP-compatible clients
- Listening modes
- Manual and scheduled
- Trial
- 10 listening hours, one time, with no payment method required
- Paid plans
- Starter, Pro and Max; plans differ by listening allowance
Alternativas ao Hemory
MeetStream
MeetStream is a meeting bot API for Zoom, Google Meet, Microsoft Teams, and Webex. It helps developers record, stream, and analyze meetings programmatically, with usage-based pricing and a $5 free credit to start.
Tactiq
Tactiq is an AI note taker for Google Meet, Zoom, and Microsoft Teams that transcribes meetings live and turns them into summaries, action items, and follow-up outputs. It is built around a Chrome extension and supports team workflows through sharing and integrations.
garden-md
garden-md is an open-source Node.js CLI that turns meeting transcripts into a local company wiki. It links entities across transcripts, keeps the original text intact, and renders the result as a browsable wiki.
SpeakoFlow
SpeakoFlow is a free, open-source desktop voice-to-text app for Windows, macOS, and Linux. It supports dictation into any app, voice-driven writing with Flow, cleanup, translation, and a screen-aware assistant.
Goldfish
Goldfish is an AI memory app for macOS that helps you reply, write, summarize, and continue using the context already on your Mac. It stores memory locally and writes in your tone.
Lasso
Lasso is an ecommerce product data platform for enriching catalog records, processing supplier files, generating product content, and monitoring competitors. It combines a web app with a REST API, SDK, and MCP server for teams and developers.