# agent-topia/evolving_personality

Dynamic MBTI Personality Simulation for LLM Agents via Carl Jung's Theory. A framework that enables LLM agents' MBTI personalities to naturally evolve and grow through interaction.

Repository: https://github.com/agent-topia/evolving_personality
Canonical: https://ross.abutalabs.com/products/evolving_personality
Homepage: https://arxiv.org/abs/2601.10025
Language: Python
License Family: other
Last push: 2026-03-17T10:51:45+00:00

## Health v2 (maintenance only)
Score: 48/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 72, release rhythm 35, longevity 16
- inputs: {"age_days": 231, "days_push": 169, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1145, forks 104 (observed 2026-08-28T04:03:45.584787+00:00)

## What it is
JPAF is a Python framework that gives LLM agents structured, evolving MBTI personalities based on Carl Jung's psychological types. It uses dominant-auxiliary coordination, reinforcement-compensation, and reflection mechanisms to maintain personality coherence while enabling short-term adaptation and long-term personality evolution.

## Use cases
- simulate evolving MBTI personalities for LLM agents
- build game NPCs with consistent personalities
- create personalized AI assistants with adaptive traits
- run social simulation and role-playing agents
- test personality consistency in HCI research
- design differentiated personalities in multi-agent systems

## When to choose
- you need psychologically grounded, interpretable personality control for LLM agents
- you want agents whose personalities evolve over long-term interactions
- you need MBTI alignment and type-activation evaluation tooling
- you work across multiple LLM families like GPT, Llama, or Qwen

## When to avoid
- you need a production-ready framework with a clear license for commercial use
- you want simple persona prompting without psychological modeling overhead
- your project requires guaranteed long-term maintenance (no license, research-stage project)
- you need non-Python integration

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, prompt-engineering, llm-inference, machine-learning
- domain: artificial-intelligence, large-language-models
- platform: python, cross-platform
- tags: mbti, personality-modeling, jungian-psychology, llm-agents, social-simulation, research-framework, no-license, ai-agents, natural-language-processing

## Member repositories
- agent-topia/evolving_personality (main) score 48

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:45.584787+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:34:26.354691+00:00, confidence not recorded.
  - readme: https://github.com/agent-topia/evolving_personality (fetched 2026-08-28T04:03:45.584787+00:00, sha 4cb9585f8051)
  - homepage: https://arxiv.org/abs/2601.10025 (fetched 2026-08-29T12:39:43.722044+00:00, sha 3d7e3fb02f35)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T12:39:43.731478+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T12:39:43.735131+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T12:39:43.737480+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T12:39:43.733409+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.