diff --git a/README.md b/README.md
index bd38b50..be7f057 100644
--- a/README.md
+++ b/README.md
@@ -20,7 +20,7 @@ the QPU sits unused inside the labyrinth's walls.
 (VP9 + AV1 CDEF + H.264). Public API exposes all 9 kernels.
 3 kernels deploy on QPU, 6 on CPU, 2 with opportunistic-QPU
 helper paths. Phase 8 (V4L2 deployment) ongoing in sibling
-[daedalus-v4l2](https://git.reauktion.de/marfrit/daedalus-v4l2).
+[daedalus-v4l2](https://git.reauktion.de/reauktion/daedalus-v4l2).
 On hertz, all kernels exceed the 30fps@1080p user-facing floor by
 8-30×.**
 
@@ -108,7 +108,7 @@ The first deliverable was one back-end kernel; nine cycles later
 the public API in `include/daedalus.h` exposes nine kernels each
 with bit-exact NEON and (where worthwhile) QPU paths. The V4L2
 wrapper is the next-up sibling project
-([daedalus-v4l2](https://git.reauktion.de/marfrit/daedalus-v4l2)),
+([daedalus-v4l2](https://git.reauktion.de/reauktion/daedalus-v4l2)),
 which turns the kernel-library into a `/dev/videoNN` device for
 libva-v4l2-request-fourier / browser consumption.
 
@@ -127,7 +127,7 @@ libva-v4l2-request-fourier / browser consumption.
 ## Out of scope (lives in sibling repos)
 
 - The V4L2 stateless driver — that's
-  [daedalus-v4l2](https://git.reauktion.de/marfrit/daedalus-v4l2).
+  [daedalus-v4l2](https://git.reauktion.de/reauktion/daedalus-v4l2).
 - Bitstream parsing — that lives in daedalus-v4l2 too, via
   `dlopen`'d FFmpeg at runtime (Option γ).
 - Browser-side consumption — libva-v4l2-request-fourier +
@@ -257,7 +257,7 @@ See `include/daedalus.h` for the full API.
 
 ## Sibling projects in the same orbit
 
-- **[daedalus-v4l2](https://git.reauktion.de/marfrit/daedalus-v4l2)**
+- **[daedalus-v4l2](https://git.reauktion.de/reauktion/daedalus-v4l2)**
   — V4L2 stateless wrapper. Linux kernel module +
   userspace daemon that consume `libdaedalus_core.a` from this
   repo. Scaffold + roadmap; Phase 8 implementation work.