docs: rewrite the intro and tighten wording throughout the README - #225
Merged
Conversation
Leads with what Haruspex is and, more usefully, what you don't need to
run it: no separate inference server, because it downloads a model that
fits your hardware and runs it on its own managed llama.cpp. Says up
front that this is switchable if you'd rather point at a remote model.
Also throughout:
- moves Remote access, Email and saved conversations into the Chat
feature list, where people will actually look for them
- says the Audit job is for auditing codebases, which was never stated
- notes that Linux and macOS may need the remote-access port opened by
hand, not just Windows
- retitles the "asking for a file needs a second message" issue to name
the real cause: small models drop the second half of a two-part
instruction
- qualifies the OpenRouter and Apple Silicon claims rather than leaving
them absolute
Co-Authored-By: Timothy MacDonald <tbaxmacdonald@gmail.com>
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_012daTE2Qw7nA45hpZ53SUxd
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
Rewrites the opening paragraph and tightens wording across the README. The intro now leads with what Haruspex is and — more usefully for someone landing on the repo — what you don't need to run it: no separate inference server, because it picks a model for your hardware and runs it on its own managed llama.cpp. It says plainly that this is switchable if you'd rather point at a remote model.
Other changes:
Note on the base
These edits were written against
428a339(#218), before #220 and #221 merged. Applied as a three-way merge rather than taking the file wholesale, so the GPL-3.0 licence section from #220 and both image-related blocks from #221 are preserved — a straight copy would have silently reverted the licence text back to MIT and dropped the "Pictures in answers" feature bullet and the "Image coverage is thin" known issue.One conflict, resolved by keeping both: #221 inserted the image known-issue immediately before the heading renamed here.
Docs only — no code, no tests affected.
🤖 Generated with Claude Code
https://claude.ai/code/session_012daTE2Qw7nA45hpZ53SUxd