# dnhkng/GLaDOS

This is the Personality Core for GLaDOS, the first steps towards a real-life implementation of the AI from the Portal series by Valve.

Repository: https://github.com/dnhkng/GLaDOS
Canonical: https://ross.abutalabs.com/products/glados
Language: Python
License: MIT
License Family: permissive
Last push: 2026-08-09T20:02:49+00:00

## Health v2 (maintenance only)
Score: 64/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 96, release rhythm 8, longevity 89
- inputs: {"age_days": 1259, "days_push": 24, "days_rel": 612, "gap_med": null, "n_releases_24m": 1}
- flags: prerelease_only
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5689, forks 444 (observed 2026-08-28T04:09:27.956582+00:00)

## What it is
A real-life implementation of GLaDOS, the sardonic AI from Valve's Portal series, built as a proactive voice assistant with vision, memory, emotions, and tool use via MCP. It uses a multi-agent architecture and a custom TTS model to achieve sub-600ms conversational latency.

## Use cases
- build a voice assistant with a distinct personality
- run an AI companion that sees through a camera and speaks through speakers
- experiment with multi-agent LLM architectures with memory and emotions
- create a low-latency real-time conversational AI
- give a home assistant proactive behavior instead of wake words
- integrate MCP tool use into a voice-driven agent

## When to choose
- you want a characterful, proactive desktop AI assistant with vision and voice
- you need sub-second conversational latency with custom TTS
- you want to explore multi-agent personality and emotion modeling in Python

## When to avoid
- you need a production-grade enterprise voice assistant with SLAs
- you want a neutral, professional assistant without roleplay personality
- you need mobile or web-only deployment

## Facets
- artifact type: application
- maturity: active
- function: speech-recognition, tts, llm-inference, agent-framework, mcp, computer-vision, chatbot
- domain: artificial-intelligence, large-language-models, speech-processing, computer-vision
- platform: python, cross-platform
- tags: voice-assistant, personality-core, portal-fan-project, real-time-conversation, multi-agent, emotional-model, low-latency, ai-agents, desktop

## Member repositories
- dnhkng/GLaDOS (main) score 64

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:27.956582+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 2026-08-29T17:54:13.194798+00:00, confidence not recorded.
  - readme: https://github.com/dnhkng/GLaDOS (fetched 2026-08-28T04:09:27.956582+00:00, sha 00638d6c01e4)
- Data as of 2026-08-30T08:39:29.467469+00:00.