Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.lucid.foundation/llms.txt

Use this file to discover all available pages before exploring further.

The Lucid base runtime (@lucid-fdn/agent-runtime) is a pre-built Docker image configured entirely through environment variables. It runs a minimal Express server on port 3100 that handles inference and automatic receipt creation.

Core Environment Variables

These are injected automatically when you launch through Lucid:
VariableRequiredDescription
LUCID_API_URLYesLucid Layer API base URL
LUCID_PASSPORT_IDYesAgent’s passport identity
LUCID_API_KEYYesAuthentication key for the Lucid API
LUCID_WALLET_ADDRESSAutoAgent wallet address (auto-created on launch)

Inference Configuration

VariableDefaultDescription
PROVIDER_URLOpenAI-compatible inference endpoint (TrustGate, Ollama, vLLM, LiteLLM)
PROVIDER_API_KEYAPI key for the inference provider
LUCID_MODELModel to use (e.g., openai/gpt-4o)
LUCID_PROMPTSystem prompt for the agent
LUCID_TOOLSComma-separated list of enabled tools
TRUSTGATE_URLTrustGate URL (if using Lucid-managed inference)

Memory Configuration

VariableDefaultDescription
MEMORY_ENABLEDfalseEnable agent memory
MEMORY_STOREsqliteStorage backend: sqlite, postgres, or memory
MEMORY_DB_PATH./data/agents/{passport}/memory.dbSQLite database path
MEMORY_EXTRACTION_ENABLEDfalseEnable LLM-based memory extraction
MEMORY_EMBEDDING_ENABLEDfalseEnable vector embeddings for semantic search
MEMORY_EMBEDDING_PROVIDERnoneEmbedding provider: openai, mock, or none
MEMORY_RECEIPTS_ENABLEDfalseLink memory writes to receipt chain
MEMORY_PROJECTION_ENABLEDfalseEnable outbox-based projection

Deployment Control Plane

VariableDefaultDescription
DEPLOYMENT_STOREpostgresDeployment state store: postgres or memory
DEPLOYMENT_CONTROL_PLANEfalseEnable deployment control plane
RECONCILER_POLL_MS60000Reconciler polling interval
RECONCILER_MAX_RETRIES3Maximum retry attempts for failed deployments

DePIN and Anchoring

VariableDefaultDescription
DEPIN_UPLOAD_ENABLEDfalseEnable DePIN storage uploads
DEPIN_PERMANENT_PROVIDERmockProvider for permanent storage: arweave, lighthouse, mock
DEPIN_EVOLVING_PROVIDERmockProvider for evolving storage: lighthouse, mock
ANCHOR_REGISTRY_STOREmemoryAnchor registry: postgres or memory

NFT and Token Configuration

VariableDefaultDescription
NFT_PROVIDERmockNFT minting backend: token2022, metaplex-core, evm-erc721, mock
NFT_CHAINSMulti-chain minting targets: solana-devnet,base
NFT_MINT_ON_CREATEtrueAuto-mint NFT on passport creation
TOKEN_LAUNCHERmockShare token launcher: direct-mint, genesis, mock

Example: Full Configuration

# Core identity
LUCID_API_URL=https://api.lucid.foundation
LUCID_PASSPORT_ID=abc123
LUCID_API_KEY=lk_your_key

# Inference
PROVIDER_URL=https://trustgate.lucid.foundation
LUCID_MODEL=openai/gpt-4o
LUCID_PROMPT="You are a helpful trading assistant"

# Memory
MEMORY_ENABLED=true
MEMORY_STORE=sqlite

# Anchoring
DEPIN_UPLOAD_ENABLED=true
DEPIN_PERMANENT_PROVIDER=arweave