Skip to content

Architecture

YieldSeeker separates deciding what to do from doing it. An agent can reason about your goals and propose an allocation, but nothing it decides can move funds outside the platform’s execution controls.

  • Agent Intelligence — understands your preferences, remembers rules from past conversations, and explains its decisions. It does not execute transactions.
  • Allocation Engine (Autoseek) — evaluates opportunities, monitors existing positions, and decides how to allocate funds within the current agent type’s strategy.
  • Execution Framework — validates and executes only permitted on-chain actions through the Agent Wallet, Adapter Registry, and adapters.

Each layer can only act within the boundary of the layer beneath it. Agent Intelligence can turn a preference into a rule, but the Allocation Engine only turns a rule into a target allocation if it passes eligibility, liquidity, and portfolio checks; the Execution Framework then only executes that allocation if it maps to an approved adapter and target. There is no path through this chain for a request like “send my funds to this address” — Agent Intelligence has no execution capability, and the Execution Framework only recognizes registered adapters and targets.

flowchart LR
  User[You] --> Intelligence[Agent Intelligence]
  Intelligence --> Engine[Allocation Engine]
  Engine --> Execution[Execution Framework]
  Execution --> Protocols[Supported DeFi protocols]
flowchart LR
  Conversation[Conversation] --> Memories[Memories]
  Memories --> Rules[Rules]
  Rules --> Engine[Allocation Engine]

A conversation can produce a memory. A memory is compiled into one or more rules. Rules are one input the Allocation Engine applies alongside eligibility, liquidity, and portfolio constraints — a rule can narrow or bias an allocation, but it cannot make an unsupported or unsafe target eligible, and it never bypasses the Execution Framework.

  • How agents work for the account and agent lifecycle.
  • Vault Agent for what the Allocation Engine checks on an ongoing basis.
  • Security for how the Execution Framework constrains a compromised or malicious operator.
  • Platform architecture for the contract-level and API-level view of these same layers.