You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Commit d9cb6e3
Browse filesBrowse the repository at this point in the historyBrowse files
Add model comparison view and a keyboard shortcuts cheat-sheet
- Compare page (new /compare route): pick any combination of installed
Ollama models, downloaded llama.cpp models, and cloud models, send one
prompt to all of them at once, and watch each response stream in side
by side with its own token count and cost estimate. Reachable from the
sidebar and the command palette.
- Keyboard shortcuts dialog (Ctrl/Cmd+/, or the keyboard icon next to
Settings): lists every existing shortcut in one place (command
palette, new chat, settings, send/newline, stop generating) - none of
these were newly added, just made discoverable.
Verified the comparison view end-to-end in a live browser session
(mocked window.api with a fake streaming chat.send): selected two
models, ran a prompt, confirmed both streamed independently and
rendered with correct token/cost info.
Copy file name to clipboardExpand all lines: README.md
+3-1Lines changed: 3 additions & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -36,7 +36,9 @@ Beyond chat, Modelforge includes an **agentic mode** — the model can read/writ
36
36
-**Projects** — group related chats under shared instructions and default model parameters.
37
37
-**Per-session and per-project overrides** — pin a specific prompt, model, temperature, seed, top-K/top-P, repeat penalty, context length, GPU offload, or stop sequences to a single chat or an entire project, falling back to sane defaults. Provider-specific parameters (e.g. seed isn't supported by Claude, top-K isn't supported by ChatGPT) are automatically disabled when they don't apply to the selected model.
38
38
-**Prompt library** — save and reuse system prompts across chats. Prompts can include `{{variables}}` (e.g. `{{topic}}`) that you fill in each time you apply one, and edits keep version history so a bad change can be restored.
39
-
-**Command palette** (`Ctrl/Cmd+K`) — jump between chats, projects, and settings without touching the mouse.
39
+
-**Command palette** (`Ctrl/Cmd+K`) — jump between chats, projects, settings, and Compare without touching the mouse.
40
+
-**Keyboard shortcuts cheat-sheet** (`Ctrl/Cmd+/`, or the keyboard icon next to Settings) — everything you can do without the mouse, in one place.
41
+
-**Compare models** — send one prompt to several models at once (local or cloud) and see every response stream in side by side, with per-model token counts and cost estimates.
40
42
-**Full-text search** — the sidebar search box matches message content across every chat, not just titles.
41
43
-**Tags** — label chats with freeform tags and filter the sidebar by them; lighter-weight than Projects for ad-hoc organization.
42
44
-**Pin messages** — bookmark any message in a chat and jump straight to it from a "Pinned" panel in the toolbar.
0 commit comments