How it works Run a worker Dashboard Network

LightNode

Loading...

LightNode - an independent ecosystem tool for LightChain AI. Not an official LightChain product.

Built builder-to-builder for LightChain worker operators GitHub

Multi-turn Conversation

lightnode-sdk

Optional system prompt + maxHistoryTurns cap.

npm Source Example

Type a message. The server fires one real encrypted testnet inference per turn (free LCAI from the faucet), rate-limited to 3 per hour per IP so the demo stays available. For your own keys + mainnet, use the runnable example.

More from lightnode-sdk

Top up a server wallet, let users pay in ETH, or move earnings back. Typed wrapper around the LightChain Hyperlane Warp Route - quote, approve, transfer LCAI both directions. Pair it with a Uniswap swap for a complete ETH-to-native-LCAI flow.

Read + vote on LCAI Governor proposals on Ethereum. Real OZ Governor v5 wrapper. Cast votes, propose, queue, execute.

Worker preflight + watch

workerPreflight submits ONE real test inference + returns verdict. workerWatch streams state-change events (registered, went-stale, jobs-completed) for any worker, no key required.

Dispute / refund queries

ln.getJobStatus(jobId) classifies a job (submitted / in-flight / completed / stalled / disputed / resolved) and exposes a refundable flag.

Models on-chain (AIConfig)

On LightChain mainnet the official model registry is AIConfig - whitelisted models, fees, and output limits. ln.getModels() / ln.estimateFee() read it directly. The custom lcai_listSupportedModels RPC method returns the live whitelist.

Back to all modules Build hub