Theme
AI Resources
June
June is an open source desktop AI assistant for turning spoken work into meeting notes, dictation, and local agent sessions.
The official README describes a Tauri desktop app plus June API backend: June records local audio, generates editable meeting notes, pastes cleaned dictation into the previously focused app, groups work into projects, and runs a local Hermes-based agent runtime. The README says app state, recordings, transcripts, files, sessions, and agent memory live on the user's machine by default, while model inference goes through June API, a TEE-attested backend that keeps provider keys server-side and routes private model calls through Venice by default. 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
June brings meeting recording, editable notes, dictation cleanup, project grouping, and local agent sessions into one desktop app rather than leaving those steps in separate tools.
Why it stands out
Voice, projects, and agent work share context
Voice capture and follow-up work sit together: saved audio can be retried, notes stay editable, dictation can return to another app, and the bundled agent runtime can work around files, drafts, routines, and projects.
Availability
Public repo, release artifacts, and local run path
The public materials include the source repository, macOS and Windows release runbooks, a release-artifacts repository, local development commands, env examples, backend verification notes, and an MIT license for the source repo.
Why it matters
What makes it useful
June is practical when spoken work becomes the bottleneck: a meeting recording, a dictated note, and the follow-up file work often belong to the same project. The app shows one way to keep those steps together, with local saved audio for retry, editable notes, paste-back dictation, and agent sessions around the same work.
What to know
Where it fits
June belongs in the useful daily tools layer rather than the model layer. It overlaps with agent runtimes such as Hermes, but the public project is a desktop product for voice-to-work workflows, local app state, platform permissions, release packaging, and backend verification.
Notable points
What stands out
The official README lists meeting recording, microphone plus system audio on supported macOS versions, conversation turns, dictation, projects, model choice, local app data, June API configuration, provider-key handling, permissions, macOS and Windows support differences, development commands, and release notes.
Before using
What to review
Platform fit: macOS has the fuller path, while the Windows docs say global dictation shortcuts, dictation paste, macOS system audio capture, and Seatbelt sandbox features are not available there.
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 June 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.
Setup boundaries: review env files, provider keys, local bearer tokens, OS Accounts settings, release artifacts, and the current source before self-hosting or using production-style builds.
Reader fit
Who may find it relevant
People who want meeting audio, cleaned dictation, editable notes, and follow-up drafts to stay tied to the same project.
Builders comparing local-first desktop AI assistants that combine voice capture, notes, projects, and agent work.
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
June puts three usually separate jobs into one desktop workflow: capture spoken work, turn it into editable text, and let an agent help with the project that text belongs to. The privacy and verification design is part of the story, but the page keeps the provider and permission boundaries visible.
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.
More in Productivity
Keep browsing this category
A few more places to continue in productivity.
HTML Anything
nexu-io/html-anything
A local agentic HTML editor that uses existing coding-agent CLI sessions to turn Markdown, data, and notes into exportable HTML, PNGs, decks, social cards, data reports, and web prototypes with skill templates and sandboxed preview.
MiMo Code
XiaomiMiMo/MiMo-Code
A Xiaomi MiMo terminal-native AI coding assistant built on OpenCode, with public source, docs, install paths, build/plan/compose agents, persistent memory, task tracking, subagents, provider configuration, and release assets.
Open Design
nexu-io/open-design
A local-first AI design workspace that connects coding-agent CLIs to prototypes, decks, media outputs, design systems, sandboxed previews, and export workflows.
Related in LifeHubber
Keep the thread going
Follow the next layer with AI Resources for AI projects with original links and practical caveats, AI Guides for decision habits for messy AI choices, AI Access for free and low-cost ways to compare AI model access, AI Ballot for a clearer view of what readers are leaning toward, and AI Radar for AI stories that deserve a second look.