Releases
Current software, platform availability, and release status.
We build resilient systems, run our research in the open, and back every claim with proof. No fluff — just software that works.
Ask by voice or by typing. REX opens your apps, works through the steps, and gets it done — on your machine. It’s the main thing we’re building.
Expected launch: August 4, 2026 — the waitlist hears first.
A clear view of every section, product, and policy — each page serves a specific purpose.
Current software, platform availability, and release status.
Free, direct utilities that solve a single problem.
Active research, in-progress builds, and the technical limits we're pushing.
Measured performance, platform stability, and system constraints.
The engineering bar used to decide what is production-ready and what remains research.
Development logs, release notes, and operational updates.
Current shipping and early-access builds. Open a product for its actual platform status, requirements, and known limits.
Instant, on-device voice-to-text — Windows, Linux, and Android today; macOS and iPhone soon.
Speak, and the text appears the moment you stop talking — in whatever app has focus. Transcription runs entirely on your device: no audio upload or inference round trip. Model setup, account validation, and token refresh still use the network. Available now on Windows, Linux, and Android, with macOS and iPhone on the way.
Server-side voice-to-text tuned for the highest accuracy, on every platform.
The same instant dictation, run on a dedicated server engine for the highest accuracy we can deliver on any hardware. Hold the hotkey, speak, and polished text lands at your cursor in well under a second — on Windows, Linux, and Android today, with macOS and iPhone on the way.
Free live speech translation in your ear, on Android.
Walk into a room where nobody speaks your language and hear them as if they did. earslate streams nearby speech directly to Gemini or OpenAI and plays the translation back in your earbuds in real time.
Unresolved problems, in-progress builds, and open edge cases. We document the work in the open, including what's still unsolved.
Browser-based voice transcription without installation.
A web interface for Lven that works directly in the browser. No download, no install. Open the page, speak, copy.
Read frontier detailDocumented performance, hard limits, and architectural constraints. Trust requires actual data, not marketing claims.
One Lven Instant subscription covers every platform as it ships — Windows, Linux, and Android today, macOS and iPhone on the way. Every shipped build runs the same on-device transcription engine.
Each platform uses its native audio stack and text injection method. No emulation layers, no shared web shells.
Speech becomes text on your device with no upload step and no network round trip. The result appears the moment you stop speaking.
The quantised speech model is downloaded during setup and then runs on your CPU. No remote inference means the transcription path has no upload queue, server rate limit, or network round trip.
The floating bubble survives window manager changes, display sleep, and app switching.
Qt6 window flags ensure always-on-top behavior. Position persists across recording sessions.
Audio is written to disk before transcription. Network failure does not lose the recording.
WAV files persist in the cache directory until transcription succeeds or the user clears them.
Transcribed text is injected into the active input field at the exact cursor location.
On Windows, Lven tries UI Automation and falls back to a controlled clipboard paste. Linux currently uses xdotool on X11 or wtype on Wayland. macOS and iPhone remain unshipped, and Android uses its current platform service.
Free, self-hosted builds — engines, tools, and utilities — held to the same engineering standard as our paid releases.
Local code-intelligence engine for AI agents — indexes a repository into a code graph and serves context over MCP and HTTP.
CPU-only Rust LLM inference engine — 4-bit quantized kernels and local serving, no CUDA or PyTorch.
Experimental self-hosted credential proxy for cooperative AI agents — reduces accidental key exposure, but is not yet a same-user isolation boundary.
Free Android opener for PDF, DOCX, RTF, XLSX, CSV, PPTX slide outlines, Markdown, and plain text.
Free live speech translation for Android.
Full access to Lven Instant for 3 days. Card required, cancel anytime.
The engineering gate used to distinguish production-ready software from early access and research.
Production-ready status is reserved for software that operates correctly under sustained real-world load.
Frontier is where active research lives. We document the work in the open and label exactly where it stands.
Public means the source or download is available. It does not automatically mean production-ready or suitable as a security boundary.
Some builds run correctly but still fail the baseline. Function alone is not sufficient.
Everything we make in one place — the products we sell and the public builds we give away, each held to the same engineering baseline.
A private Windows app that runs your computer for you — ask by voice or by typing, and it opens your apps, works through the steps, and gets it done. Credential Airlock and Context Zero are built in.
Windows · voice or text
Instant voice-to-text that runs on your device. Press the hotkey, speak, and the text lands at your cursor in whatever app has focus. Your audio never leaves your hands. Available on Windows, Linux, and Android today, with macOS and iPhone coming soon. A server-side Cloud build is also available.
Windows, Linux, Android now · macOS, iPhone soon
Server-side voice-to-text for users who prioritize the highest available accuracy or whose hardware cannot run the on-device model. Audio is sent over TLS for transcription and is not retained by ClassEve.
Windows, Linux, Android now · macOS, iPhone soon
Walk into a room where nobody speaks your language and hear them as if they did. earslate streams nearby speech directly to Gemini or OpenAI and plays the translation back in your earbuds in real time — no account, and your own API key.
Android · Gemini + OpenAI