GitHubJoin Us
Projects

Research systems for agent-native workloads.

A curated public view of research assets and applied research environments. Entries describe scope and maturity; they do not imply that planned outputs have been released.

Research Assets

Supporting assets for the systems research program.

01In progress

Agentivium Core

Research asset

An inherited set of shared schemas, protocols, and design ideas that can support experiments across the research program.

Agentivium Core is a supporting technology and research asset. It is not presented as the organization’s sole product or as a released SDK.

Research Themes

Digital ProfileDigital StreamEvidence PacketAdaptive ActionEvaluation ProtocolShared schemas and SDKs

Expected outputs

  • Core schemas
  • Python and TypeScript packages
  • Validation CLI
  • Evaluation protocol
  • Digital Entity Loop diagram
02Experimental

hpc-claw

Research asset

An infrastructure testbed for compute-aware orchestration of agentic workloads on HPC systems.

hpc-claw treats agentic workloads as schedulable, observable, and governable workloads, contributing execution streams, agent action traces, and value-per-compute metrics back to Agentivium Core.

Research Themes

Execution StreamAgent Action TraceCompute-aware orchestrationBudgeted executionValue-per-compute

Expected outputs

  • Execution event schema
  • Agent workload trace schema
  • Budgeted orchestration baseline
  • Value-per-compute metrics
Applied Research Environments

Selected environments used to study mechanisms under real constraints.

01Prototype

Learner Intelligence Layer

Applied research environment

A learning testbed where learner profiles, learning streams, and evidence-based recommendations validate the Digital Entity Loop.

This testbed applies Agentivium Core to education by modeling learners as evolving digital profiles updated from learning events and used for evidence-based exercise recommendations.

Research Themes

Learner Digital ProfileLearning StreamEvidence-based recommendationTeacher usefulnessProfile freshness and completeness

Expected outputs

  • Learner profile schema
  • Learning event taxonomy
  • Exercise recommendation baseline
  • Teacher usefulness rubric
02Prototype

Xanh Narrative Engine

Applied research environment

An agriculture testbed that converts plant, product, and farm traces into evidence-grounded narratives.

Xanh Narrative Engine validates the Digital Entity Loop in agriculture by connecting plant/product profiles, farm event streams, evidence packets, and narrative generation.

Research Themes

Plant/Product/Farm ProfileFarm/Product StreamEvidence-grounded storytellingTrace-to-narrativeDomain-grounded evaluation

Expected outputs

  • Plant/product event taxonomy
  • Trace-to-narrative pattern
  • Evidence-grounded narrative schema
  • Narrative evaluation rubric
03Exploratory

Smart Building PoC

Applied research environment

A cyber-physical validation of policy-aware agent-native execution using room, device, and sensor streams.

The Smart Building PoC applies Agentivium Core to room and device profiles, sensor/device streams, evidence packets, and policy-aware suggested actions.

Research Themes

Room/Device ProfileSensor/Device StreamPolicy EnvelopeHuman approval loopCyber-physical safety

Expected outputs

  • Cyber-physical event schema
  • Device/action policy schema
  • Human approval workflow
  • Safety edge cases
Contribute

Interested in building agent-native testbeds?

Join UsResearch Areas