terra: ollama (ROCm) + LibreChat with local persistent memory

Local LLM server on the 6800 XT (ollama-rocm, gfx1030 needs no
HSA_OVERRIDE_GFX_VERSION) fronted by a LibreChat web UI, talking to it
over the OpenAI-compatible /v1 route. Also wires up LibreChat's
persistent-memory feature, which needed its own agent+model plus a
custom extraction prompt: the default 3b model couldn't reliably tell
the user's stated facts apart from its own boilerplate, and even a
tuned prompt didn't fix that — so memory extraction now reuses
gemma4:12b, the same model as the daily-driver chat endpoint.

flake.lock bump pulls in the ollama and librechat NixOS modules.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

This commit is contained in:

darman

2026-08-18 00:38:07 +02:00

co-authored by

Claude Sonnet 5

parent 0ec3c6413c

commit 7904433d34

6 changed files with 184 additions and 44 deletions

									
										services/desktop/desktop-apps.nix
									
		+1
		
												View File
												
				@@ -18,6 +18,7 @@ in

				      "claude-code"

				      "proton-pass-cli"

				      "vivaldi"

				      "mongodb" # librechat's local db (services/desktop/librechat.nix) — SSPL

				    ];

				  programs.steam = {