hersona

English · 日本語

195 reusable character attributes for AI agent personas — compose your own system prompts from personality, speech, archetype, visual, and hobby templates. MIT (code) + CC0 (templates). CLI, MCP server, and Hermes Agent skill.

Docs · PyPI · Repository

Why Hersona?

System-prompt authoring is the most copy-pasted code in AI agents. Most teams either hand-roll long persona descriptions or steal prompts from Discord threads — and the resulting characters drift, contradict themselves, or lose intensity mid-conversation.

Hersona gives you a typed, schema-validated library of 195 character attributes you can mix and match:

• Personality (42) — tsundere, kuudere, yandere, airhead, intellectual, …
• Speech (134) — kansai_ben, keigo, kyoto_ben, british_en, valley_girl_en, mandarin, korean, …
• Archetype (9) — heroine, mentor, rival, idol, shrine_maiden, …
• Visual (5) — silver_hair, glasses, petite, glamorous, animal_ears
• Hobby (5) — cooking, gamer, music, reading, sports

Each attribute declares core_traits, catchphrases, tone, and an explicit compatible_archetypes / conflicts_with matrix — so the blend engine refuses to ship a broken persona, and you can tune intensity per attribute (mild / moderate / strong).

Use it from any OpenAI-compatible API, Claude, local LLMs, LangChain, AutoGen, CrewAI — or as a drop-in MCP server for Claude Desktop.

5-Minute Quickstart

pip install hersona

hersona list                          # browse all 195 attributes
hersona show personality/tsundere     # inspect one attribute
hersona blend personality/tsundere speech/keigo --weight strong

hersona export personality/tsundere speech/keigo --weight strong \
  --format openai_assistants > system_prompt.json

Then drop system_prompt.json["instructions"] into your agent's system message — hersona export also handles messages (chat array), langchain_system_message, json, and plain markdown formats.

For the full programmatic API, see docs/PUBLIC_API.md.

Install (Hermes Agent)

No registry approval needed — works right now via tap:

hermes skills tap add shiro-0x/hersona
hermes skills install hersona
hermes skills install hersona-initializer

Also available (or pending) in skill registries:

License structure

The repository is split into two layers, each under a different license:

What it covers now

195 attributes across 5 categories. The biggest recent expansion is speech 31 → 134 (the +103 new registers in this PR), structured in five phases:

Total breakdown: personality 42 + speech 134 + archetype 9 + visual 5 + hobby 5 = 195.

Overview

An open-source project that systematizes the speech and personality of anime characters and distributes them as a template collection that can be injected into an AI agent's system prompt.

• Provides attribute templates (attributes/<category>/<name>.yaml)
• A user (or agent) builds the personality of any character by assigning the attributes they need

Usage

Use with Hermes Agent

Attach attributes via /hersona <category>/<name>:

/hersona                              # listing + usage help
/hersona list                         # list available attributes
/hersona show personality/tsundere    # details of a given attribute
/hersona personality/tsundere single  # attach a single attribute
/hersona personality/tsundere speech/keigo multi  # blend multiple attributes
/hersona default                      # detach

See skills/hersona/SKILL.md for details. Detailed recipes, the verification checklist, and version history live in skills/hersona/REFERENCE.md (loaded on demand to keep the skill body lightweight per turn).

Use from the CLI

After pip install -e ., the hersona command (or python -m hersona.cli) is available:

hersona list                                  # list available attributes (public + user)
hersona show tsundere                          # attribute details
hersona matrix --json                          # dump the compatibility matrix as JSON
hersona blend tsundere keigo --weight strong   # compose attributes into an injection block (with intensity)
hersona blend airhead intellectual --suggest   # on conflict, suggest non-conflicting replacements (stderr)
hersona diff tsundere dandere                  # compare two attributes (common / only-one fields + relation)
hersona preview tsundere kyoto_ben --weight strong  # injection block + sample phrases (no LLM)
hersona recommend                              # diagnostic quiz -> recommendation (interactive; en UI routes to English speech)
hersona recommend --answers distance=1,speech=0,role=1 --apply
hersona create --category personality --name my_attr \
  --display-ja マイ属性 --display-en MyAttr \
  --desc-ja 説明 --desc-en desc --example "..."  # create an attribute and save to the user namespace
hersona measure kyoto_ben --weight strong --text "ようおいでやすどす"  # score intensity metrics of output
hersona measure tsundere heroine --weight moderate --input out.txt       # intensity metrics of a blend
hersona save my_tsun tsundere keigo --weight strong  # save a blend as a reusable named preset (local)
hersona presets                                # list saved blend presets
hersona load my_tsun                           # replay a saved preset as an injection block
hersona export tsundere keigo --format messages  # export a blend for other frameworks (json/messages/markdown)
hersona update                                 # download the latest attribute data from the repository
hersona update --ref v1.4.1                    # pin to a branch / tag / commit SHA (default: main)
hersona update --clear                         # remove downloaded data and revert to the bundled templates

User-created attributes are saved under ~/.hermes/attributes/ (default) or the directory specified by HERSONA_USER_DIR, and never mix into the public attributes/.

hersona update keeps the attribute templates fresh without reinstalling the package. When you install via pip/wheel, attributes/ and schema/ are bundled at build time, so upstream additions only land after a reinstall. hersona update downloads the latest attributes/ and schema/ from the repository into a local data cache (~/.hermes/data/ by default, or HERSONA_DATA_DIR), which takes precedence over the bundled templates. hersona update --clear removes the cache and reverts to the bundled data. The download uses only the Python standard library (no extra dependencies).

Saved blend presets live under ~/.hermes/presets/ (default) or the directory specified by HERSONA_PRESETS_DIR. A preset is just a named recipe (attributes + weight); hersona load replays it through the same blend engine, so it always reflects the latest attribute templates.

To hand a persona off to another agent framework (LangGraph / LangChain / OpenAI / Anthropic SDK), hersona export <names...> --format {json,messages,markdown} emits a portable artifact: json is structured data (metadata + system prompt + per-attribute summary + conflicts), messages is a ready-to-use [{"role": "system", "content": ...}] chat array, and markdown is the raw injection block. The same export_blend() is available from hersona.core.

Exporting to OpenAI Assistants and LangChain

Two additional --format values let you drop a hersona blend straight into the most common production agent frameworks without any Tavern Card semantics:

• --format openai_assistants returns a JSON payload for the OpenAI Assistants API instructions field, with hersona-specific fields namespaced under metadata.hersona_*.
• --format langchain_system_message returns a LangChain SystemMessage- compatible JSON document (type / content / response_metadata).

Both are framework-neutral: no openai or langchain Python package is required at install time. Pipe the output to the framework's own SDK or HTTP call. Example:

hersona export tsundere keigo --weight strong --format openai_assistants \
  | jq -r '.instructions' > /tmp/system_prompt.txt

Richer CLI output (optional)

Install the tui extra for color tables (list) and panels (show):

pip install "hersona[tui]"

It is opt-in: without rich, when piping/redirecting, or with --plain / NO_COLOR, the CLI prints the same plain text as before. Set HERSONA_FORCE_RICH=1 to keep color when piping (e.g. | less -R).

Shell tab-completion (optional)

Install the completion extra and register the completer with your shell to tab-complete subcommands, attribute names, and preset names:

pip install "hersona[completion]"
eval "$(register-python-argcomplete hersona)"   # add to ~/.bashrc / ~/.zshrc to persist

It is opt-in: without argcomplete, the CLI works exactly the same, only without completion.

Use as an MCP server (optional)

Expose hersona to MCP-aware agents (Claude Desktop, etc.) so they can call list_attributes / show_attribute / blend / export / recommend_blend / compatibility directly:

pip install "hersona[mcp]"
hersona-mcp                       # start the stdio MCP server

The server (hersona.mcp.server) is a thin wrapper over hersona.core; the tool logic lives in hersona.mcp.tools and is usable on its own. mcp is only needed to run the server, not to use the library or CLI.

Use with other LLMs

Paste fields such as core_traits / catchphrases / tone / description_en from attributes/<category>/<name>.yaml directly into the system prompt.

When blending multiple attributes, check compatibility via each YAML's compatible_archetypes / conflicts_with.

Data format

attributes/
├── personality/             # personality attributes (42: ja-base 35 + en-native 5 + ja-base hautaine + ja-base sociable)
├── speech/                  # speech attributes (31: ja 25 + en 5 + archaic_otaku)
├── archetype/               # archetype attributes (9)
├── visual/                  # visual attributes (5)
└── hobby/                   # hobby attributes (5)

Every attribute YAML conforms to schema/attribute.schema.json.

Attribute templates (attributes/)

A template collection of general attribute tags to attach to a character profile, validated by schema/attribute.schema.json. It currently defines 195 in total: personality 42 / speech 134 / archetype 9 / visual 5 / hobby 5 (see under attributes/). The speech category spans 119 Japanese (content_lang: ja) and 15 English (content_lang: en) registers, plus archaic_otaku (文語 register fused with otaku-style work / character references), plus 14 translation-style foreign-language registers (Chinese / Korean / French / German / Italian / Spanish / Russian / Arabic / Hindi / Vietnamese / Thai / Tagalog — content_lang: ja but with native-script catchphrases), plus 1 Ryukyuan-language register okinawa_ben (content_lang: ja but conceptually distinct from mainland Japanese), and personality spans 35 Japanese-base and 5 English-native (content_lang: en) archetypes aimed at international users, plus hautaine (inborn pride / condescending air from background) and sociable (reads the room, bridges people, calibrates tone).

The 195 attributes

Required fields (attribute.schema.json)

Optional fields

Relationship fields

Template generation script

The normal maintenance flow is to add or edit attribute files directly under attributes/<category>/<name>.yaml and run python scripts/validate.py to verify them. The script below is a frozen legacy snapshot — do not use it for day-to-day maintenance.

scripts/_oneoff/gen_v1_attributes.py can regenerate the YAML as a Single Source of Truth. Instead of editing YAML directly, update the lists and re-run:

# regenerate the (legacy) attribute YAMLs without confirmation
python scripts/_oneoff/gen_v1_attributes.py

# only show the paths that would be written
python scripts/_oneoff/gen_v1_attributes.py --dry-run

Note: this generator is a frozen snapshot and emits the legacy metadata format (display_name_ja/en, description_ja/en). After regenerating, run python scripts/migrate_i18n.py to convert back to the i18n block format (BASE=en + i18n.ja).

Validation

python scripts/validate.py

Confirms that all 195 attribute YAMLs validate against the schema.

License

• Code in this repository: MIT
• Templates under attributes/: CC0 1.0 (public domain dedication)
• Disclaimer: be sure to read DISCLAIMER.md

Contributing

1. Add attribute templates in the attributes/<category>/<name>.yaml form
2. examples / core_traits / catchphrases, etc. need no source citation (the LLM interprets them), but must not include proper nouns or specific works
3. Validate with python scripts/validate.py before opening a PR
4. 1 PR = 1 attribute as a rule; for multiple additions, agree in an Issue first

See CONTRIBUTING.md for details.

The implementation guide for agents / developers ("what to build next") is at docs/IMPLEMENTATION_GUIDE.md.