Harald Hoyer fdefdf31b2 feat(litellm): add LiteLLM gateway on sgx fronting halo's llama-server ... Exposes an OpenAI-compatible endpoint on sgx:4000 (LAN-reachable) that routes the `coder` model to halo's llama-server, so clients get a stable gateway with per-key auth instead of hardcoding halo's address. Master key is sourced from a sops-encrypted env file.		2026-05-21 23:15:47 +02:00
..
amd	chore(halo): llama.cpp update	2026-05-21 20:46:06 +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): set spec-draft-p-min for coder model	2026-05-21 23:15:09 +02:00
mx	feat(halo): add song <URL> command to convert via song.link	2026-05-20 09:42:11 +02:00
nixtee1	refactor(nix): extract common system configs into reusable modules	2026-01-30 10:42:09 +01:00
sgx	feat(litellm): add LiteLLM gateway on sgx fronting halo's llama-server	2026-05-21 23:15:47 +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