Theme
AI Resources
Clovy (formerly June)
Clovy is an open-source Mac AI workspace for chat, dictation, meeting notes, image generation, and local agent work. It was previously named June.
The current repository describes a Tauri desktop app plus Clovy API. The project says notes, recordings, transcripts, files, sessions, and agent memory stay on the Mac by default, while model calls use Clovy API and selected upstream providers. It describes private Venice routes as the default and labels other model choices by privacy tier. Use this as a first read, not a recommendation. Open the original project before trusting details like terms, limits, privacy, cost, setup, or safety.
What it is
Desktop assistant for spoken work
Clovy brings chat, meeting recording, editable notes, dictation cleanup, image generation, and local agent sessions into one desktop app rather than leaving those steps in separate tools.
Why it stands out
Voice, notes, chat, and agent work share one app
Saved audio can be retried, notes stay editable, dictation can return to another app, and the local agent can help with files, research, and drafts. The project describes approval gates for agent actions; check exactly which actions are covered before granting access.
Availability
Public source and signed Mac releases
The public repository contains the desktop app and Clovy API source under the MIT license. The project publishes signed, notarized Mac releases and documents how its production API image and confidential-computing attestation can be checked.
Why it matters
What makes it useful
Clovy is practical when a meeting, a dictated note, a chat, and the follow-up file work belong together. It keeps saved audio for retry, editable notes, paste-back dictation, and local agent sessions in the same workspace.
What to know
Where it fits
Use Clovy when the goal is one Mac workspace for voice, notes, chat, files, and agent help. Compare it with focused meeting assistants if you only need transcription or summaries, and check its model routes before treating local app storage as fully offline use.
Notable points
What stands out
The current README lists chat, meeting recording without a call bot, microphone plus system audio, dictation, image generation, model choice, a local agent with project-described approval gates, local app data, Clovy API, provider privacy tiers, signed releases, and source-linked verification evidence.
Before using
What to review
Platform fit: macOS 14 or later is the supported download path. The README says Windows builds omit global dictation paste, system-audio capture, and the macOS sandbox.
Data flow: app state, recordings, transcripts, files, sessions, and agent memory are described as local by default, but transcription, prompts, context, and generation requests can leave through Clovy API and upstream model routes.
Verification limits: the `/verify` page and attestation chain speak to the backend code running in a confidential VM, not to what every upstream model provider does with data.
Permissions: microphone, accessibility, screen/system audio recording on macOS, and file access for agent workflows should match the task before relying on it.
Agent controls: check which file, shell, network, connected-service, and external actions require approval, and what broader-access mode changes, before granting access to sensitive work.
Setup boundaries: review model privacy tiers, account and billing records, provider terms, release signatures, and the current source before using it for sensitive work.
Reader fit
Who may find it relevant
Mac users who want chat, meeting audio, cleaned dictation, editable notes, image generation, and follow-up drafts in one app.
Builders comparing local-first desktop AI assistants that combine voice capture, notes, model choice, and project-described agent approval gates.
Readers interested in how a desktop AI app separates local state, server-side provider keys, backend attestation, and upstream model-provider behavior.
Less relevant for readers who want a fully offline assistant, a no-setup consumer recorder, or only a standalone agent runtime without voice and note workflows.
Editorial note
Why LifeHubber lists it
Clovy keeps spoken work, editable notes, chat, and agent help in one Mac workspace. Its local storage and public verification evidence are useful, but readers still need to check which model provider receives each request.
Source links
Source materials
Reader note
Before relying on this entry
LifeHubber lists entries to help readers inspect AI projects, not to endorse them or prove they are safe, suitable, accurate, maintained, or right for a specific use. We do not verify every entry in depth. Before relying on anything listed, review the original materials, terms, privacy practices, limits, and risks that matter for your situation.
What to explore next
Decide whether you need a full workspace or focused meeting notes.
Clovy combines chat, dictation, meetings, images, and agent work. Continue with a narrower meeting assistant, or compare the wider voice and meeting landscape.
More in Productivity
Keep browsing this category
Explore more productivity tools.
Penpot
penpot/penpot
An open-source collaborative design platform with an official MCP server that lets AI agents inspect and modify Penpot files, components, tokens, styles, layouts, and assets through hosted or local connection paths.
Archify
tt-a1i/archify
An agent skill and deterministic Node.js renderer for validated architecture, workflow, sequence, data-flow, and lifecycle maps, with typed JSON source, interactive tracing, and portable HTML, image, and motion exports.
TrueForge
truefoundry/trueforge
A vendor-neutral agent harness with a chat UI, HTTP API, TypeScript SDKs, model and MCP connections, reusable skills, approvals, context management, sandboxed execution, and local or hosted deployment paths.
For project maintainers
Listed here? You can use the badge.
If you maintain a project with a current LifeHubber listing, you may add the optional “Listed on LifeHubber AI Resources” badge to its README, docs, or website. No introduction or permission request is needed.
