This release adds 3 notable features for engineering teams evaluating rollout.
✓ No known CVEs patched in this version
Summary
AI summaryAdds voice intelligence analytics, private meeting memory for Zoom/Teams, and an owner‑only local CLI/MCP control socket.
Changes in this release
| Type | Severity | Summary | CVE |
|---|---|---|---|
| Feature | Medium |
Adds Voice Intelligence with analytics over time. Adds Voice Intelligence with analytics over time. Source: llm_adapter@2026-07-17 Confidence: high |
— |
| Feature | Medium |
Adds Private Meeting Memory for optional suggestions and transcript generation. Adds Private Meeting Memory for optional suggestions and transcript generation. Source: llm_adapter@2026-07-17 Confidence: high |
— |
| Feature | Medium |
Adds local CLI and MCP control socket for history, search, stats, and file transcription. Adds local CLI and MCP control socket for history, search, stats, and file transcription. Source: llm_adapter@2026-07-17 Confidence: high |
— |
| Feature | Low |
Adds configurable local retention for meeting audio with play, export, retry, or delete options in Settings. Adds configurable local retention for meeting audio with play, export, retry, or delete options in Settings. Source: llm_adapter@2026-07-17 Confidence: high |
— |
| Bugfix | Medium |
Ensures active meeting capture finalizes on graceful quit and preserves disk‑written microphone frames for retry after crashes. Ensures active meeting capture finalizes on graceful quit and preserves disk‑written microphone frames for retry after crashes. Source: llm_adapter@2026-07-17 Confidence: high |
— |
| Bugfix | Medium |
Limits repeated engine restarts to prevent poison‑file loops for permanently failed meetings. Limits repeated engine restarts to prevent poison‑file loops for permanently failed meetings. Source: llm_adapter@2026-07-17 Confidence: high |
— |
| Bugfix | Medium |
Makes meeting post‑processing chunked, resumable, and prioritizes live dictation. Makes meeting post‑processing chunked, resumable, and prioritizes live dictation. Source: llm_adapter@2026-07-17 Confidence: low |
— |
| Bugfix | Medium |
Binds long‑running CLI/MCP requests and cancels them when the client disconnects or quits. Binds long‑running CLI/MCP requests and cancels them when the client disconnects or quits. Source: llm_adapter@2026-07-17 Confidence: low |
— |
| Bugfix | Low |
Preserves existing preferences, history, modes, dictionary entries, and archived dictation audio during upgrade. Preserves existing preferences, history, modes, dictionary entries, and archived dictation audio during upgrade. Source: llm_adapter@2026-07-17 Confidence: high |
— |
| Refactor | Low |
Restricts history/search responses to final visible text and bounded metadata only. Restricts history/search responses to final visible text and bounded metadata only. Source: llm_adapter@2026-07-17 Confidence: high |
— |
Full changelog
Velora 0.6.0 — voice intelligence, meeting memory, and local agents
This release makes Velora useful beyond the moment text is inserted, while keeping the same local-first boundary.
What’s new
- Voice Intelligence: see words and dictations over time, estimated time saved, streaks, app/mode usage, latency, cleanup rate, and an honest zero-edit rate with observation coverage. Share cards contain aggregate numbers only.
- Private Meeting Memory: get optional suggestions for Zoom, Google Meet, Teams, Slack Huddles, and nearby Calendar events. Recording always requires explicit confirmation. Velora keeps microphone and computer audio as separate local tracks, then creates a searchable transcript, summary, decisions, and action items.
- Local CLI and MCP: opt in to an owner-only local control socket for history, search, stats, file transcription, and one visibly approved live dictation. There is no network listener, and access is off by default.
Under the hood
- Meeting post-processing is chunked and resumable; live dictation takes priority.
- Active meeting capture is finalized on graceful quit. Microphone audio uses a crash-resilient CAF container; after a crash or forced termination, frames that reached disk are preserved for explicit retry instead of being orphaned.
- Interrupted processing resumes, while permanently failed meetings wait for a manual retry and repeated engine restarts are capped to prevent poison-file loops.
- Meeting audio has configurable local retention and can be played, exported, retried, or deleted from Settings.
- Intelligence was tested against a 100,000-row history, including migration from older databases.
- History/search responses return only the user-visible final text and bounded display metadata; they omit the raw-vs-cleaned transcript pair, bundle identifiers, audio paths, screen context, contacts, learning data, and internal row/session identifiers. File transcription returns only its caller-supplied path, local timing metadata, and cleaned text.
- Long-running CLI/MCP requests are bounded and cancelled when their requesting client disconnects; that cancellation is scoped to the exact request. Quitting also revokes pending consent, cancels active agent work, and closes accepted control clients before engine teardown.
Upgrade
Replace the existing app in Applications with the new DMG. Existing preferences, history, modes, dictionary entries, and archived dictation audio are preserved. Local CLI/agent access and Calendar matching both remain off until you enable them.
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
About Velora
All releases →Beta — feedback welcome: [email protected]