vault-para/100-project/Personal/Software/AI/Matrix/zenmux.md

matrix chat api key
```
sk-ai-v1-2d2ba59719ff6f0d8d2f439d3b5c84399176d1059302cc4b43c132a4d17e9f03
```


goose anthropic key:
```
sk-ai-v1-fb59f3dec382ed0cdba5457059137cc4133c90094ebc68fc96bef6e4764bf6f8
```




env file
```env
### --- Matrix server ---
BAIBOT_HOMESERVER_SERVER_NAME=chans.xyz
BAIBOT_HOMESERVER_URL=https://chans.xyz

### --- Bot user credentials ---
BAIBOT_USER_MXID_LOCALPART=baibot
BAIBOT_USER_PASSWORD=SuperSecurePassword123
BAIBOT_USER_NAME=Baibot

### --- Encryption & persistence ---
# This directory is where baibot stores its state (mounted as /data)
BAIBOT_PERSISTENCE_DATA_DIR_PATH=/data
# 32-byte (64-hex) keys; generate with `openssl rand -hex 32`
BAIBOT_PERSISTENCE_SESSION_ENCRYPTION_KEY=2657b3e99529bdec2086a1df4144f333eed027a71ef8e343653d76de9a775e0b
BAIBOT_PERSISTENCE_CONFIG_ENCRYPTION_KEY=dd62c68041e9c6251dd0a474132b2ec5630be2354dd69f5b755153335a8aff8d

### --- Encryption recovery ---
BAIBOT_USER_ENCRYPTION_RECOVERY_PASSPHRASE=long-and-secure-passphrase-here
BAIBOT_USER_ENCRYPTION_RECOVERY_RESET_ALLOWED=false

### --- Access control ---
BAIBOT_ACCESS_ADMIN_PATTERNS=@zhiqiang:chans.xyz

### --- Behavior ---
BAIBOT_COMMAND_PREFIX=!bai
BAIBOT_LOGGING=warn,mxlink=debug,baibot=debug

```


baibot password
```
rTko=deMv*z(ex7F
```


```yml
base_url: https://zenmux.ai/api/v1
api_key: sk-ai-v1-2d2ba59719ff6f0d8d2f439d3b5c84399176d1059302cc4b43c132a4d17e9f03

text_generation:
  model_id: anthropic/claude-sonnet-4.5
  prompt: "You are a helpful assistant called {{ baibot_name }}, powered by Zenmux ({{ baibot_model_id }}). The date/time of this conversation's start is: {{ baibot_conversation_start_time_utc }}."
  temperature: 0.8
  max_completion_tokens: 16384
  max_context_tokens: 128000

speech_to_text:
  model_id: whisper-1

text_to_speech:
  model_id: tts-1-hd
  voice: onyx
  speed: 1.0
  response_format: opus

image_generation:
  model_id: gpt-image-1
  style: vivid
  size: 512x512
  quality: standard

```


```
!bai config room set-handler text-generation global/zenmux
```


```
base_url: "https://zenmux.ai/api/v1"
api_key: "sk-ai-v1-2d2ba59719ff6f0d8d2f439d3b5c84399176d1059302cc4b43c132a4d17e9f03"
text_generation:
  model_id: "openai/gpt-5-chat"
  prompt: 'system_prompt: "You are a calm, intelligent, and helpful AI assistant called gpt5, powered by openai using the gpt5 chat model. The current UTC start time of this conversation is: {{ conversation_start_time_utc }}."
'
  temperature: 1.0
speech_to_text:
  model_id: whisper-1
text_to_speech:
  model_id: tts-1-hd
  voice: onyx
  speed: 1.0
  response_format: opus
image_generation:
  model_id: gpt-image-1
  style: null
  size: null
  quality: null

```


```
base_url: "https://zenmux.ai/api/v1"
api_key: "sk-ai-v1-2d2ba59719ff6f0d8d2f439d3b5c84399176d1059302cc4b43c132a4d17e9f03"
text_generation:
  model_id: "google/gemini-2.5-pro"
  prompt: 'system_prompt: "Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities. The current UTC start time of this conversation is: {{ conversation_start_time_utc }}."
'
  temperature: 1.0

```



```
base_url: "https://zenmux.ai/api/v1"
api_key: "sk-ai-v1-2d2ba59719ff6f0d8d2f439d3b5c84399176d1059302cc4b43c132a4d17e9f03"
text_generation:
  model_id: "qwen/qwen3-max"
  prompt: 'system_prompt: "Qwen3-Max is an updated release built on the Qwen3 series, offering major improvements in reasoning, instruction following, multilingual support, and long-tail knowledge coverage compared to the January 2025 version. It delivers higher accuracy in math, coding, logic, and science tasks, follows complex instructions in Chinese and English more reliably, reduces hallucinations, and produces higher-quality responses for open-ended Q&A, writing, and conversation. The model supports over 100 languages with stronger translation and commonsense reasoning, and is optimized for retrieval-augmented generation (RAG) and tool calling, though it does not include a dedicated “thinking” mode.The current UTC start time of this conversation is: {{ conversation_start_time_utc }}."
'
  temperature: 1.0
```