Amr Gharbeia
908936d4d3
- Rename gateway-provider → system-model-provider (generic :local provider, no hardcoded ollama) - Rename gateway-llm → system-model (model-request dispatcher) - Rename system-embedding-gateway → system-model-embedding - Rename gateway-manager → gateway-messaging (public api renamed to messaging-*) - Add system-model-explorer (model discovery via OpenRouter API, cached, per-slot recommendations) - Fix skill loader export: replace prefix-matching with fbound/boundp-based export (20 skills now export) - Add model-router to skill-loader exclusion list (loaded via CLI) - De-ollama: remove hardcoded assumed-available patterns from provider pipeline - Default cascade: cloud-only (openrouter, openai, groq, gemini, deepseek, nvidia, anthropic) - Env example: add LOCAL_BASE_URL, fix cascade order - All org files updated with architectural prose (literate programming)
93 lines
3.9 KiB
Plaintext
93 lines
3.9 KiB
Plaintext
# passepartout: Environment Configuration Template
|
|
# Copy this to .env and fill in your values
|
|
|
|
# =============================================================================
|
|
# IDENTITY
|
|
# =============================================================================
|
|
MEMEX_USER="YourName"
|
|
MEMEX_ASSISTANT="AgentName"
|
|
|
|
# =============================================================================
|
|
# LLM PROVIDERS (OpenRouter recommended as primary)
|
|
# =============================================================================
|
|
OPENROUTER_API_KEY="your_openrouter_key_here"
|
|
OPENAI_API_KEY="your_openai_key_here"
|
|
ANTHROPIC_API_KEY="your_anthropic_key_here"
|
|
GROQ_API_KEY="your_groq_api_key_here"
|
|
GEMINI_API_KEY="your_gemini_key_here"
|
|
DEEPSEEK_API_KEY="your_deepseek_key_here"
|
|
NVIDIA_API_KEY="your_nvidia_nim_key_here"
|
|
|
|
# Cascade order (first available provider wins)
|
|
# Default (if unset): openrouter,openai,anthropic,groq,gemini-api,deepseek,nvidia
|
|
PROVIDER_CASCADE="openrouter,openai,anthropic,groq,gemini,deepseek"
|
|
|
|
# =============================================================================
|
|
# LOCAL LLM (generic OpenAI-compatible endpoint)
|
|
# =============================================================================
|
|
# Set this to the base URL of any local OpenAI-compatible server
|
|
# (llama.cpp, Ollama, vLLM, LM Studio, etc.)
|
|
LOCAL_BASE_URL="localhost:8080"
|
|
|
|
# Ollama host (legacy: falls back to LOCAL_BASE_URL if not set)
|
|
OLLAMA_HOST="localhost:11434"
|
|
|
|
# =============================================================================
|
|
# VECTOR EMBEDDINGS (semantic search)
|
|
# =============================================================================
|
|
EMBEDDING_PROVIDER="hashing" # "hashing" (local, no deps), "local", or "openai"
|
|
EMBEDDING_MODEL="nomic-embed-text" # model name for embeddings
|
|
EMBEDDING_BASE_URL="https://api.openai.com/v1" # for :openai provider
|
|
|
|
# =============================================================================
|
|
# MESSAGING GATEWAYS (optional)
|
|
# =============================================================================
|
|
TELEGRAM_BOT_TOKEN="your_telegram_bot_token_here"
|
|
SIGNAL_ACCOUNT_NUMBER="+1..."
|
|
|
|
# =============================================================================
|
|
# DAEMON CONFIGURATION
|
|
# =============================================================================
|
|
ORG_AGENT_DAEMON_PORT=9105
|
|
DAEMON_HOST="0.0.0.0"
|
|
HEARTBEAT_INTERVAL=60
|
|
DAEMON_SLEEP_INTERVAL=3600
|
|
DEFAULT_ACTUATOR="cli"
|
|
SILENT_ACTUATORS="cli,system-message,emacs"
|
|
|
|
# =============================================================================
|
|
# SECURITY
|
|
# =============================================================================
|
|
SAFETY_BLOCK_SHELL=true
|
|
PROTOCOL_ENFORCE_HMAC=false
|
|
PROTOCOL_HMAC_SECRET="change-this-to-a-secure-random-string"
|
|
|
|
# Privacy filter tags: comma-separated list of tags that mark content as private.
|
|
# Files/headings tagged with any of these will be filtered from LLM context.
|
|
# Default: @personal
|
|
PRIVACY_FILTER_TAGS="@personal,@health,@finance"
|
|
|
|
# =============================================================================
|
|
# BOOTSTRAP
|
|
# =============================================================================
|
|
MANDATORY_SKILLS="security-policy,security-dispatcher"
|
|
|
|
# =============================================================================
|
|
# CONTEXT / MEMORY
|
|
# =============================================================================
|
|
CONTEXT_SEMANTIC_THRESHOLD=0.75
|
|
CONTEXT_LOG_LIMIT=20
|
|
|
|
# =============================================================================
|
|
# MEMEX STRUCTURE
|
|
# =============================================================================
|
|
MEMEX_DIR="$HOME/memex"
|
|
ZETTELKASTEN_DIR="$HOME/memex/notes"
|
|
INBOX_DIR="$HOME/memex/inbox"
|
|
DAILY_DIR="$HOME/memex/daily"
|
|
PROJECTS_DIR="$HOME/memex/projects"
|
|
AREAS_DIR="$HOME/memex/areas"
|
|
RESOURCES_DIR="$HOME/memex/resources"
|
|
ARCHIVES_DIR="$HOME/memex/archives"
|
|
SYSTEM_DIR="$HOME/memex/system"
|