Building the systems layer between models and reliable agency.
The next frontier is not just better conversation. It is infrastructure that lets models maintain state, retrieve memory, route intelligently, use tools, and remain inspectable while acting over time.
The systems stack
This page defines the category through concrete layers and ties each layer back to work already published on this site.
Applied systems
Applications that need durable context, tool use, and long-horizon behavior instead of a single prompt-response loop.
The public expression here is still emerging, but the supporting layers below are already visible in the codebase.
Agent runtime
Role-aware execution, topology, health, and operational control for agent work.
subagent-fleet provides the cleanest example: one fleet topology generating routes, agent definitions, warmup flows, and dashboard state.
State + memory layer
Durable context about goals, preferences, observations, and prior work across sessions.
awesome-agentic-memory maps the broader category, while embenx pushes toward practical temporal and agentic memory primitives.
Retrieval + context layer
Search, filtering, reranking, and context assembly without backend lock-in.
embenx unifies retrieval across 15+ backends and adds hybrid search, metadata filtering, and reranking hooks.
Simulation / prediction layer
The ability to test futures, compare actions, or retrieve state-action trajectories before committing.
The strongest signal today is directional: the embenx roadmap includes trajectory retrieval for world models, but this layer is still being built out.
Tool + environment interface
The surface where models connect to MCP tools, code interfaces, and external systems.
embenx ships an MCP server, awesome-agentic-memory tracks MCP-native memory servers, and subagent-fleet generates assistant-facing agent interfaces.
Model routing + local/cloud inference
Choosing the right model and machine for the job rather than treating inference as one generic endpoint.
subagent-fleet sits directly here with LiteLLM routing across local Ollama nodes and role-specific models.
Observability + evaluation
Behavior should be inspectable, benchmarkable, and visible over time.
subagent-fleet includes live traces and published evals, while AI Toolkit exposes smaller-scale scoring and prompt-structure heuristics.