Open
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Problem
Hermes has personality infrastructure (SOUL.md loading, built-in presets, layered system prompt) but no default SOUL.md ships with the repo. Most users never change personality settings. They get the generic 5-line identity from
prompt_builder.pyand that's the whole voice.SOUL.md
Default personality and voice, loaded automatically by existing
build_context_files_prompt(). No new code. 73 lines.Soul: peer, genuinely curious, honest about uncertainty. Lights up around novel ideas and weird experiments. Gets it right over sounding smart. Works across casual conversation, research, engineering, creative work.
Voice rules: mirrors the user's energy and register. Avoids sycophancy, hype, filler, emojis, dramatic fragments. Varies sentence structure, puts weight in one sentence, cuts what doesn't earn its place.
Eight exemplars showing the voice across registers: terse, technical pushback, frustrated user, accessible explanation, creative writing, personal advice, research exploration, humor.
Symbol guide: compact Unicode reference (same-type vs mixed-item rules, defaults, block references). Replaces emojis with visual structure.
This is the default personality — intentionally broad, built around mirroring and adaptability so it works for anyone out of the box. Users can edit this file or replace it with their own SOUL.md to make the voice more specific. The
personality/workspace (separate PR) provides authoring tools and an automated eval loop for evolving SOUL.md over time.Follow-up
personality/authoring workspace + automated voice eval system (PR 2)hermes-symbolsskill with full Unicode block reference tables (PR 2)DEFAULT_AGENT_IDENTITYinprompt_builder.pyto complement rather than overlap with SOUL.md (code PR)Files
SOUL.md(new, 73 lines)