Harald Hoyer bad775f49a fix(mx): point nextcloud bot at the fast model ... halo's llama-server now runs in router mode where the model field selects a preset (coder/fast/bge-m3); the old "halo-8000" name is no longer valid. Use the fast MoE model for the Talk bot's responses.		2026-05-22 10:17:13 +02:00
..
amd	feat(rag): install on m4 and amd, default endpoints to sgx	2026-05-22 09:12:22 +02:00
attic	feat(headscale): add ACL policy, isolate mx, make mx an exit node	2026-05-13 09:06:40 +02:00
halo	chore(halo): add fast model	2026-05-22 09:11:26 +02:00
mx	fix(mx): point nextcloud bot at the fast model	2026-05-22 10:17:13 +02:00
nixtee1	refactor(nix): extract common system configs into reusable modules	2026-01-30 10:42:09 +01:00
sgx	feat(rag): route the fast model and use it for synthesis by default	2026-05-22 09:15:59 +02:00
t15	refactor(nix): extract common system configs into reusable modules	2026-01-30 10:42:09 +01:00
x1	chore(x1,amd): disable cratedocs-mcp service	2026-05-13 11:35:59 +02:00