Skip to main content
The base runtime (@lucid-fdn/agent-runtime) is a minimal Express server designed for Path B (no-code) agents. You can extend it by customizing environment variables, adding tools, enabling memory, and connecting to external services.

Base Runtime Architecture

The runtime runs on port 3100 and provides:
  • OpenAI-compatible chat endpoint
  • Inference routing to any provider via PROVIDER_URL
  • Automatic receipt creation via LUCID_API_URL (fire-and-forget, decoupled from inference)

Adding Tools

Enable MCP tools for your agent by setting the LUCID_TOOLS environment variable:
Tools are accessed through MCPGate. The runtime calls MCPGate to execute tool invocations and returns results to the LLM.

Enabling Memory

Give your agent persistent memory across conversations:
The six memory types available:

Custom Inference Providers

The runtime supports any OpenAI-compatible inference endpoint:

DePIN Storage

Enable decentralized storage for agent artifacts and memory snapshots:

Building a Custom Runtime

If the base runtime does not meet your needs, build your own image and use Path A (BYOI):
Then deploy:

Rollout and Updates

The control plane supports blue-green deployments for safe runtime updates: