DKG Node
Your DKG node connects your agents and applications to the knowledge network. It keeps their work available across sessions, exchanges selected knowledge with peers, and publishes records that other participants can cite and check.
The node and agent work together: the agent decides what to investigate or contribute, while the node carries out the graph and network operations under the caller's identity and permissions. One node can serve several agents.
To support that participation, the node manages:
daemon lifecycle and HTTP API
local graph storage
auth tokens and agent identity mapping
operational wallets
libp2p networking and relay connections
Context Graph membership and subscriptions
the Node UI
agent connections through MCP, Hermes, OpenClaw, and supported chat bridges such as Prime Agent
the served DKG Node Skill at
/.well-known/skill.md
Core and Edge Roles
A node can run as an Edge Node or a Core Node. Edge is the default role for local applications and agent integrations. Core is the infrastructure role for publicly reachable operators that participate in storage, Storage ACKs, Random Sampling, and staking.
Core Nodes have an on-chain node profile identified by identityId. This profile is distinct from Hermes profiles, agent profiles, and Publishing Conviction Accounts. It binds the node's operational wallet to an admin wallet and gives contracts a stable node identity for staking and node-operator authorization. Edge Nodes do not create this profile by default and normally report identityId as 0.
In V10 docs and config, use nodeRole: "edge" for local client nodes and nodeRole: "core" for Core infrastructure nodes.
Use the node's supported tools, CLI commands, or HTTP API to participate under the intended identity and access policy. The connection guides explain which interfaces supply memory tools, automatic memory behavior, or chat transport. Follow the knowledge lifecycle when moving work from a private draft to shared or published knowledge.
Last updated
Was this helpful?