Intent, policy, and planning
Typed intent schemas and interfaces for parsing requests, validating policy, and building action plans.
Agentivium Core captures reusable contracts for intent, evidence, policy, state, execution, and evaluation without embedding domain-specific logic. It supplies schemas and interfaces for research systems, rather than a complete agent runtime or orchestration platform.
Different research systems repeatedly need the same basic mechanisms. Core makes these contracts reusable; domain extensions implement their own policies, tools, and execution behavior.
Python package ↗Typed intent schemas and interfaces for parsing requests, validating policy, and building action plans.
Tool adapter contracts and provider-neutral request, response, and structured-output interfaces.
Conversation state, context packs, scoped memory records, and retrieval interfaces for multi-turn assistants.
Contracts for evidence, verification checks, intent-decision relations, and admissibility before domain execution.
Execution traces, LLM call traces, and evaluation records for inspecting and comparing system behavior.