Same with AI: when the data center goes down, every app built on it stops answering.
That's why we built QVAC: so anyone has access to intelligence that runs on their own phone or laptop, with no single point of failure. By default, models download peer to peer over @Holepunch_to.
QVAC. Unstoppable intelligence.
Internet has lost its way.
Heavy centralization within 3/5 datacenter players created predictable point of failures and easy targets.
@tether built unstoppable open-source peer-to-peer communication protocols that can resist to the worst disasters.
Build on @Holepunch_to 🍐
Use @keet_io 🦜
The demo is open source (Apache 2.0) and MegaLoc is MIT licensed. You download the street photos once, with a free Mapillary token.
Photos: Mapillary (CC BY-SA 4.0), Wikimedia Commons. Map: © OpenStreetMap contributors (ODbL).
github.com/tetherto/qvac-exa…
2
212
Our new piece on @TechCrunch looks at the @Holepunch_to ecosystem and the comeback of peer-to-peer software. QVAC is part of it.
Holepunch lets two devices talk directly, with no server in between. @keet_io uses it for messages, calls and file sharing. QVAC uses it to link your own devices into one private mesh, so a phone can hand heavier AI work to a stronger machine of yours.
Read the article: techcrunch.com/sponsor/tethe…
QVAC SDK 0.24 is out, with vector search for RAG up to 8.2x faster and new image generation models.
What's new:
- TurboVec 1.1.2: RAG search in the SDK is now 2x to 8.2x faster, and more accurate
- MegaLoc: a new model that recognizes places from a photo
- Image generation: adds Flux 3 Klein, Qwen-Image-2.1 Turbo and MOSS-Image with layout control
- qvac serve: better integration with tools such as Codex from @OpenAIDevs and @t3dotcodes
- Sessions: one SDK runtime can now serve several apps at once, each with its own requests
- Pocket TTS: now runs directly through the SDK, with streaming and cancellation
- Cache sharing: conversations reuse each other's cache, so the start of a prompt they share is processed only once
- AMD Ryzen AI NPU: Qwen3.5 can now use the NPU in recent AMD Ryzen AI chips, so your GPU stays free for another model
- And several other developer experience improvements
Learn more in the thread below.
Complete release doc here: github.com/tetherto/qvac/rel…
Star ⭐️ the repo to stay updated.
Transcription gained speaker attribution and more detail:
- Whisper returns token timestamps and confidence, the detected language and speaker turns
- Parakeet adds voice activity tuning, prewarming and device selection, with richer streaming results and lower streaming overhead
- MOSS adds device selection, progress updates and detailed statistics
1
1
192
Other developer experience improvements:
- calcTokens counts the tokens a string or a chat history with tools takes for the loaded model, without running inference
- Fabric moves to llama.cpp b11739, which brings faster flash-attention prompt reading on Metal
- Audio generation can run ACE-Step and its language model on separate devices, and returns output in chunks
- GLM 5.3 Flash is available in the SDK and the AI SDK provider
195

