REKI
Intro
**REKI** is a newly tracked term on FastToolHub's radar. Source signal: X+Web. Radar summary: Kyutai: "We introduce REKI, a 2.4B vision-language-action model (VLA) pretrained exclusively on public data… we endow it with a memory… makes oscillations between poses about four times rarer." Weights kyutai/reki-2b, code github.com/kyutai-labs/reki (MIT code, non-commercial weights); released Oct 16, FrameSignal coverage Oct 18; X: "Kyutai open-sourced REKI: a 2.4B robot model with built-in memory."
Explain
REKI appears in the model / AI-system category: something teams would load, call, or fine-tune rather than a pure UI gadget. Coverage ties it to robotics or embodied AI (manipulation, teleop, or physical agents). Open-source or public-repo signals show up in the excerpt, so inspection and self-hosting may be possible. Do not invent parameters, prices, or benchmarks beyond what the excerpt already states.
Usage
Start from the primary link: https://kyutai.org/reki/. For models: verify context length, license, and hardware needs from official docs; run a small smoke test before production. Numbers and claims in this page only repeat the radar excerpt — double-check upstream before publishing.