Model Catalog — Register any model via OpenAI-compatible API: vendor-hosted (OpenAI, Anthropic, etc.) or self-hosted (Nemotron, Llama, Mistral, etc.). Keys managed securely. Metadata (context windows, capabilities, internal/external classification) tracked per model.

 

MCP Server Registry — Register Model Context Protocol servers (internal or external) with automatic tool discovery. Agents see only tools they're authorized to access.

 

Agent Registry — Define agents using Oracle's AgentSpec DSL (JSON). Platform compiles to the configured runtime. Agents are version-controlled with full lineage tracking.

 

Policy Engine — Every action against the platform passes through Cerbos-based policy enforcement. Policies define which models & tools agents can access, how internal data flows to external providers and what actions are authorized across the agent graph. All rules are configurable via YAML, enabling flexible, environment-specific governance without hardcoding logic.

 

Observability — Every agent run instrumented end-to-end via OpenTelemetry. Full audit logs with literal input/output content at every step.

 

Memory Layer — Based on MemGPT research. Treats LLM as operating system—agent decides when to access memory. Enables small models (Claude Haiku, GPT-4o mini) to handle deep, multi-turn research by automatically managing context window economics. Creates knowledge graphs during execution.

 

Resource Governance — Set limits at any level: per model, per team, per month. Control token budgets, tool call limits, delegation depth. Prevent runaway costs and infinite agent recursion.

 

Profiling & Tuning — Configurable profiling integration provides flame-graph style execution timelines. See where time is spent, identify bottlenecks, auto-tune hyperparameters against evaluations.