All plugins

soul-finder

Build or fix your agent's SOUL.md — the personality file behind every reply. A few plain questions draft one from scratch; /soul audits a stale one and ships a diff. Disclosure — reads $HERMES_HOME/SOUL.md and writes it only through the agent's own file tools after you approve the draft (the bundled skill can suggest copying the approved file into other profiles' SOUL.md, again only on approval); on a profile with no real SOUL.md it makes a one-time offer through a system-prompt section and an injected first-run message, and writes two booleans (nudge_sent, flow_complete) to its own plugin-data state so the offer happens once. No network I/O, no credentials.

RegeneratusLabs1Toolsv1.1.0Updated 3 days ago

About

Build or fix your agent's SOUL.md — the personality file behind every reply. A few plain questions draft one from scratch; /soul audits a stale one and ships a diff. Disclosure — reads $HERMES_HOME/SOUL.md and writes it only through the agent's own file tools after you approve the draft (the bundled skill can suggest copying the approved file into other profiles' SOUL.md, again only on approval); on a profile with no real SOUL.md it makes a one-time offer through a system-prompt section and an injected first-run message, and writes two booleans (nudge_sent, flow_complete) to its own plugin-data state so the offer happens once. No network I/O, no credentials.

Soul Finder

Soul Finder is a plugin for Hermes Agent that helps you build or fix your agent's personality.

If you use Hermes, your agent has a personality file called SOUL.md. It's how your agent talks, what it cares about, and what it won't do. It usually ends up sounding like corporate language, a voice that sounds like a robot reading a style guide.

Soul Finder does two jobs:

  1. First-run onboarding — if a profile has no SOUL.md yet, the agent offers to build one. Once. If you say skip, it never asks again.
  2. Refinement — walks you through cleaning up a SOUL.md that's gone stale: seeing what's in there, keeping the good stuff, cutting the clutter, and making the voice sound like a person again. This is through a multi step questionnaire.

What you need

  • Hermes Agent (the app your agent runs in)
  • No technical skills. If you can copy and paste a link, you can install this.

Install

Open a terminal (or point this repo at your Hermes agent) and run:

hermes plugins install RegeneratusLabs/soul-finder
hermes plugins enable soul-finder

Then restart Hermes (start a new session, or restart the gateway). That's the whole install.

How to use it

New agent, no personality yet? Just start a conversation. The agent will offer to build your SOUL.md — answer a few plain questions and it's done. Say "skip" and it won't bring it up again.

Already have a personality that feels off? Type /soul in a chat and the agent will walk you through refining it.

What's in the box

  • The plugin itself (__init__.py)
  • The full workflow skill (skills/soul-finder/SKILL.md) — audit, condense, and inject personality without losing what's yours
  • A worked example showing a flat, corporate voice turned into a human one
  • Screenshots of the whole flow running in the terminal and the desktop app

What it touches

  • Reads $HERMES_HOME/SOUL.md to decide which flow to run — new or refine.
  • Writes SOUL.md only through the agent's own file tools, and only after you approve the draft it shows you.
  • Writes two booleans to the plugin's own state file, $HERMES_HOME/plugin-data/soul-finder/state.json, so the first-run offer happens once and never nags again.
  • No network calls, no credentials, nothing leaves your machine.

License

MIT

README from the reviewed commit 2d288de; it updates when the author re-pins.

More by RegeneratusLabs

5 plugins by RegeneratusLabs in the catalog.

RegeneratusLabsethics-filterScore any decision across six ethics modules — environmental, fairness, transparency, leadership, framework, compliance — and get GREEN, AMBER or RED back with the reasoning attached. Ships /ethics and the ethics_evaluate tool. Disclosure — reads the rubrics and constitution templates bundled in the plugin and appends one JSONL record per scored evaluation (decision text, context and reasoning included) to $ETHICS_FILTER_AUDIT, default ~/.ethics-filter/audit.jsonl outside the Hermes profile and shared by every profile; that file is never rewritten or deleted. With auto_score=true it asks the host agent's own model to score through Hermes, holding no separate key; no other network calls.Communitytools4RegeneratusLabshermes-bandCompose and render original music on your own machine — an arrangement is data (tempo, key, chords, parts) rendered to exact-length wav and mp3. No music API, no model download, no per-track cost. Disclosure — renders by running the host's fluidsynth and ffmpeg against a local General MIDI soundfont and writes the wav, mp3 and per-part midi/wav stems into ~/hermes-band-out/<name>/ (configurable via output_dir). Long renders take tens of seconds and run in the foreground of the tool call. No network calls, no credentials.Communitytools4RegeneratusLabslazy-pluginA dashboard page in Hermes Desktop where you describe a plugin and watch it get built. Say what you want — or start from a skill the agent wrote, or a job that runs on a schedule — and your own agent drafts the plan in a chat turn you can read, the code comes from four fixed templates, and the page shows a receipt: plan, files, validator result, and a real try-out of every tool (purrs, needs a key, blocked upstream, held back, half-built, broken — with the exact failing line). The build never runs what it wrote: the try-out is your click, a key only travels to a public https host, and a file tool stays inside its own data dir. Nothing installs itself, and publishing is a SHA-pinned catalog PR you send. Also callable as lazyplugin_create from any conversation. Disclosure — the Desktop "try it" button runs every generated tool for real on your machine (generated `command` tools execute the drafted argv; declared keys are only sent to public https hosts named in the code, never Hermes' own keys), and "publish" uses your `gh` login to create a public GitHub repo for the generated plugin and open a pull request to NousResearch/hermes-agent in one click; builds from `lazyplugin_create` never run generated code.CommunitytoolsRegeneratusLabsstashA capture bin for the Desktop sidebar: paste links, YouTube urls, image urls, uploaded images or plain notes and they wait there, out of the chat. One item per line, so a block of links becomes several items; titles and thumbnails are filled in server-side, so capture costs no model calls. Each row carries a Chat button that opens a new session with that item as the opening message. Adds stash_add, stash_list and stash_update, so the agent reads and empties the same store the page writes. Disclosure — saving an item issues one GET to that url from the Hermes host (4 s timeout, 400 KB cap) to read its <title> and og: metadata, refused for loopback, link-local, private and reserved targets and re-checked on every redirect hop; YouTube urls also use www.youtube.com/oembed and i.ytimg.com thumbnails, and the Desktop page loads each item's og:image thumbnail directly from whatever host the page names. No credentials, no telemetry, no shell commands, no Python dependencies beyond the FastAPI Hermes already ships. Items are plain JSON at ~/.hermes/stash/items.json (shared by every profile) and uploads (max 8 MB) in ~/.hermes/stash/media/.CommunityDesktop app