.env.example

# OpenAI-compatible completions endpoint (e.g. Ollama, LM Studio, OpenAI)
LLM_ENDPOINT=http://localhost:11434/v1/chat/completions

# Model name passed to the endpoint
LLM_MODEL=llama3

# Optional API key (sent as Bearer token) — leave blank for local servers
LLM_API_KEY=

# Default system prompt for the voice AI loop
LLM_SYSTEM_PROMPT=You are Jibo, a friendly social robot. Keep responses brief and conversational.
Initial release — Re-Commander v1.0 Local web-based control interface for the Jibo social robot via the ROM WebSocket API (port 8160) and on-device ASR (port 8088). Features head navigation via click-to-look and arrow keys, speech/listen/Voice-AI loop, display control, camera/photo capture, and entity tracking — no cloud dependency required. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> 2026-04-19 02:40:41 -04:00			`# OpenAI-compatible completions endpoint (e.g. Ollama, LM Studio, OpenAI)`
			`LLM_ENDPOINT=http://localhost:11434/v1/chat/completions`

			`# Model name passed to the endpoint`
			`LLM_MODEL=llama3`

			`# Optional API key (sent as Bearer token) — leave blank for local servers`
			`LLM_API_KEY=`

			`# Default system prompt for the voice AI loop`
			`LLM_SYSTEM_PROMPT=You are Jibo, a friendly social robot. Keep responses brief and conversational.`