> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/fabric/dev/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/fabric/_mcp/server.

# dev

## Docs

- [NVIDIA NeMo Fabric Documentation](https://docs.nvidia.com/nemo/fabric/dev/about-nemo-fabric/overview.md): Configure, plan, run, and observe agent harnesses and custom agents through one typed execution contract.
- [NVIDIA NeMo Fabric Ecosystem](https://docs.nvidia.com/nemo/fabric/dev/about-ne-mo-fabric/ecosystem.md): See how NVIDIA products use and extend NVIDIA NeMo Fabric.
- [Release Notes](https://docs.nvidia.com/nemo/fabric/dev/about-ne-mo-fabric/release-notes.md): Review the current NVIDIA NeMo Fabric release status and find the official release history.
- [NVIDIA NeMo Fabric Installation](https://docs.nvidia.com/nemo/fabric/dev/getting-started/install.md): Install guide.
- [NVIDIA NeMo Fabric Quickstart](https://docs.nvidia.com/nemo/fabric/dev/getting-started/quickstart.md): Get started with NVIDIA NeMo Fabric.
- [NVIDIA NeMo Fabric Experimentation CLI](https://docs.nvidia.com/nemo/fabric/dev/experimentation/cli.md): Use presets, maintained examples, and editable scaffolds to experiment with NeMo Fabric.
- [NVIDIA NeMo Fabric Python SDK](https://docs.nvidia.com/nemo/fabric/dev/sdk/python-sdk.md): Use the NeMo Fabric Python SDK from applications, services, and evaluation harnesses.
- [Overview](https://docs.nvidia.com/nemo/fabric/dev/adapter-contract/overview.md)
- [Custom-Agent Integrations](https://docs.nvidia.com/nemo/fabric/dev/adapter-contract/custom-agent-integrations.md)
- [Describe Adapter](https://docs.nvidia.com/nemo/fabric/dev/adapter-contract/tutorials/describe-adapter.md)
- [Map Normalized Configuration](https://docs.nvidia.com/nemo/fabric/dev/adapter-contract/tutorials/map-normalized-configuration.md)
- [Implement Execution](https://docs.nvidia.com/nemo/fabric/dev/adapter-contract/tutorials/implement-execution.md)
- [Normalize Results and Telemetry](https://docs.nvidia.com/nemo/fabric/dev/adapter-contract/tutorials/normalize-results-and-telemetry.md)
- [Register and Discover Adapter](https://docs.nvidia.com/nemo/fabric/dev/adapter-contract/tutorials/register-and-discover-adapter.md)
- [Verify Adapter](https://docs.nvidia.com/nemo/fabric/dev/adapter-contract/tutorials/verify-adapter.md)
- [Optional OpenAI Streaming](https://docs.nvidia.com/nemo/fabric/dev/adapter-contract/optional-open-ai-streaming.md)
- [Examples and References](https://docs.nvidia.com/nemo/fabric/dev/adapter-contract/examples-and-references.md)
- [Consumer Integrations](https://docs.nvidia.com/nemo/fabric/dev/integrations/consumer-integrations/overview.md): Connect applications, evaluation systems, and platforms to NVIDIA NeMo Fabric.
- [Harbor](https://docs.nvidia.com/nemo/fabric/dev/integrations/consumer-integrations/harbor.md): Run agent harnesses selected by NVIDIA NeMo Fabric in Harbor evaluations.
- [Harness Integrations](https://docs.nvidia.com/nemo/fabric/dev/integrations/harness-integrations/overview.md): Connect NVIDIA NeMo Fabric to agent harnesses through adapters.
- [Authenticate the Claude Adapter](https://docs.nvidia.com/nemo/fabric/dev/integrations/harness-integrations/claude-code.md): Configure cached login, bearer token, API key, or Workload Identity Federation authentication for the NeMo Fabric Claude adapter.
- [Use the Codex Adapter](https://docs.nvidia.com/nemo/fabric/dev/integrations/harness-integrations/codex.md): Configure capabilities, authentication, and telemetry for the NeMo Fabric Codex adapter.
- [Use the Cline Adapter](https://docs.nvidia.com/nemo/fabric/dev/integrations/harness-integrations/cline.md): Install and configure the NVIDIA NeMo Fabric harness integration for Cline.
- [Use the Hermes Agent Adapter](https://docs.nvidia.com/nemo/fabric/dev/integrations/harness-integrations/hermes-agent.md): Install and configure the NeMo Fabric harness integration for Hermes Agent.
- [Use the LangChain Deep Agents Adapter](https://docs.nvidia.com/nemo/fabric/dev/integrations/harness-integrations/lang-chain-deep-agents.md): Install and configure the NeMo Fabric harness integration for LangChain Deep Agents.
- [Use the Kilo Code Adapter](https://docs.nvidia.com/nemo/fabric/dev/integrations/harness-integrations/kilo-code.md): Install and configure the NVIDIA NeMo Fabric harness integration for Kilo Code.
- [Use the mini-SWE-agent Adapter](https://docs.nvidia.com/nemo/fabric/dev/integrations/harness-integrations/mini-swe-agent.md): Install and configure the NVIDIA NeMo Fabric harness integration for mini-SWE-agent.
- [Use the OpenClaw Adapter](https://docs.nvidia.com/nemo/fabric/dev/integrations/harness-integrations/open-claw.md): Run an isolated OpenClaw Gateway with NVIDIA NeMo Fabric.
- [Use the OpenHands Adapter](https://docs.nvidia.com/nemo/fabric/dev/integrations/harness-integrations/open-hands.md): Install and configure the NVIDIA NeMo Fabric harness integration for OpenHands.
- [Use the OpenCode Adapter](https://docs.nvidia.com/nemo/fabric/dev/integrations/harness-integrations/open-code.md): Install and configure the NVIDIA NeMo Fabric harness integration for OpenCode.
- [Use the Pi Adapter](https://docs.nvidia.com/nemo/fabric/dev/integrations/harness-integrations/pi.md): Install and configure the NVIDIA NeMo Fabric harness integration for Pi.
- [Use the Qwen Code Adapter](https://docs.nvidia.com/nemo/fabric/dev/integrations/harness-integrations/qwen-code.md): Install and configure the NVIDIA NeMo Fabric harness integration for Qwen Code.
- [Use the Remote Agent Adapter](https://docs.nvidia.com/nemo/fabric/dev/integrations/harness-integrations/remote-agent.md): Configure a remote OpenAI- or Anthropic-compatible agent for NVIDIA NeMo Fabric.
- [Python SDK Reference](https://docs.nvidia.com/nemo/fabric/dev/reference/api/python-library-reference.md): Complete reference for the public NeMo Fabric Python SDK.
- [Client](https://docs.nvidia.com/nemo/fabric/dev/reference/api/python-library-reference/client.md): Resolve, plan, diagnose, and run agents with NVIDIA NeMo Fabric.
- [Adapter Capability Inspection](https://docs.nvidia.com/nemo/fabric/dev/reference/api/python-library-reference/capabilities.md): Inspect standalone adapter metadata and verify host/task descriptor correspondence.
- [Runtime](https://docs.nvidia.com/nemo/fabric/dev/reference/api/python-library-reference/runtime.md): Drive stateful multi-turn execution through the Runtime API.
- [Service](https://docs.nvidia.com/nemo/fabric/dev/reference/api/python-library-reference/service.md): Prepare, attach, share, and release long-lived adapter services.
- [Relay Streaming](https://docs.nvidia.com/nemo/fabric/dev/reference/api/python-library-reference/streaming.md): Consume raw NVIDIA NeMo Relay ATOF records and terminal invocation results.
- [OpenAI Streaming](https://docs.nvidia.com/nemo/fabric/dev/reference/api/python-library-reference/openai-streaming.md): Consume adapter-native OpenAI Chat Completions chunks and terminal invocation results.
- [Models](https://docs.nvidia.com/nemo/fabric/dev/reference/api/python-library-reference/models.md): Pydantic authoring models for NVIDIA NeMo Fabric config and request inputs.
- [Types](https://docs.nvidia.com/nemo/fabric/dev/reference/api/python-library-reference/types.md): Typed config, request, plan, result, artifact, telemetry, and runtime contracts.
- [Errors](https://docs.nvidia.com/nemo/fabric/dev/reference/api/python-library-reference/errors.md): Structured exception hierarchy for config, capability, state, and runtime failures.
- [Rust Library Reference](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference.md): Generated Rust API reference for NeMo Fabric crates.
- [nemo-fabric-core](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core.md): Core config and runtime contract for NeMo Fabric.
- [Module adapter_contract](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/adapter_contract.md): Shared southbound adapter contract metadata.
- [Constant ADAPTER_CONTRACT_VERSION](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/adapter_contract/constant-adapter-contract-version.md): Southbound adapter contract version supported by this core.
- [Enum Adapter Extension Point](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/adapter_contract/enum-adapterextensionpoint.md): Extensible block types within the southbound adapter contract.
- [Module agent_config](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/agent_config.md): Configuration projected southbound to an adapter target.
- [Struct Agent Config](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/agent_config/struct-agentconfig.md): Configuration projected southbound to one adapter target.
- [Struct Agent Harness Config](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/agent_config/struct-agentharnessconfig.md): Adapter-owned target settings projected from `FabricConfig.harness`.
- [Struct Agent Instruction Config](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/agent_config/struct-agentinstructionconfig.md): One normalized instruction value projected to an adapter target.
- [Struct Agent Instructions Config](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/agent_config/struct-agentinstructionsconfig.md): Normalized instructions projected to an adapter target.
- [Struct Agent McpConfig](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/agent_config/struct-agentmcpconfig.md): Named MCP servers routed to an adapter target.
- [Struct Agent McpServer Config](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/agent_config/struct-agentmcpserverconfig.md): One MCP server routed to an adapter target.
- [Struct Agent Model Config](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/agent_config/struct-agentmodelconfig.md): Configuration for one named model role projected to an adapter target.
- [Struct Agent Runtime Config](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/agent_config/struct-agentruntimeconfig.md): Runtime behavior applied by an adapter target.
- [Struct Agent Skill Config](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/agent_config/struct-agentskillconfig.md): Skill paths made available to an adapter target.
- [Struct Agent Tool Definition](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/agent_config/struct-agenttooldefinition.md): One named tool or tool-group definition resolved by an adapter.
- [Struct Agent Tools Config](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/agent_config/struct-agenttoolsconfig.md): Named tool definitions and effective adapter-target tool policy.
- [Struct Agent Workflow Config](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/agent_config/struct-agentworkflowconfig.md): Custom agent or workflow selection and construction settings.
- [Struct Agent Workflow Entrypoint Config](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/agent_config/struct-agentworkflowentrypointconfig.md): Adapter-declared resolution semantics for one custom agent or workflow.
- [Module agent_execution](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/agent_execution.md): Request and result structures exchanged with an adapter target.
- [Struct Agent Artifact](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/agent_execution/struct-agentartifact.md): One artifact produced by an adapter target.
- [Struct Agent RunError](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/agent_execution/struct-agentrunerror.md): Error reported by an adapter target.
- [Struct Agent RunRequest](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/agent_execution/struct-agentrunrequest.md): Southbound invocation request passed to an adapter target.
- [Struct Agent RunResult](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/agent_execution/struct-agentrunresult.md): Southbound terminal result returned by an adapter target.
- [Enum Agent RunResult Validation Error](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/agent_execution/enum-agentrunresultvalidationerror.md): Invalid relationship or value within an adapter result.
- [Enum Agent RunStatus](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/agent_execution/enum-agentrunstatus.md): Completion status reported by an adapter target.
- [Struct Agent Usage](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/agent_execution/struct-agentusage.md): Normalized model usage reported by an adapter target.
- [Module config](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config.md): NeMo Fabric config models and loading helpers.
- [Enum Adapter Config Field](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/enum-adapterconfigfield.md): Adapter-translated normalized NVIDIA NeMo Fabric configuration fields.
- [Struct Adapter Config Support](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/struct-adapterconfigsupport.md): Adapter config support.
- [Struct Adapter Descriptor](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/struct-adapterdescriptor.md): Language-neutral adapter descriptor for a harness integration.
- [Enum Adapter Kind](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/enum-adapterkind.md): Adapter implementation kind.
- [Struct Adapter Requirements](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/struct-adapterrequirements.md): Adapter runtime requirements.
- [Enum Adapter Target](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/enum-adaptertarget.md): Type-specific Adapter Target Descriptor payload.
- [Struct Adapter Target Descriptor](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/struct-adaptertargetdescriptor.md): Independently registered target implemented by an adapter.
- [Enum Adapter Target Type](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/enum-adaptertargettype.md): Adapter target categories understood by this Adapter Contract version.
- [Struct Adapter Telemetry Provider Support](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/struct-adaptertelemetryprovidersupport.md): Telemetry capabilities for one adapter-supported provider.
- [Struct Adapter Telemetry Support](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/struct-adaptertelemetrysupport.md): Adapter telemetry support.
- [Struct Capability Route](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/struct-capabilityroute.md): One capability execution assignment.
- [Struct Capability Target Plan](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/struct-capabilitytargetplan.md): Capabilities routed to one target.
- [Struct Capability Plan](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/struct-capabilityplan.md): Resolved capability configuration.
- [Enum Control Location](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/enum-controllocation.md): Where NeMo Fabric control code runs relative to the environment.
- [Struct McpServer Config](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/struct-mcpserverconfig.md): MCP server configuration.
- [Struct Descriptor Provenance](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/struct-descriptorprovenance.md): One physical source for a discovered descriptor record.
- [Enum Descriptor Source](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/enum-descriptorsource.md): Where NeMo Fabric discovered descriptor metadata.
- [Struct Discovery Config](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/struct-discoveryconfig.md): Explicit descriptor discovery inputs.
- [Struct Environment Config](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/struct-environmentconfig.md): Execution environment configuration.
- [Struct Relay Atif Config](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/struct-relayatifconfig.md): Relay ATIF export configuration.
- [Enum Environment Ownership](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/enum-environmentownership.md): Whether NeMo Fabric owns the underlying environment resource.
- [Struct Relay Atof Config](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/struct-relayatofconfig.md): Relay ATOF export configuration.
- [Struct Environment Plan](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/struct-environmentplan.md): Resolved environment plan.
- [Struct Relay Component Config](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/struct-relaycomponentconfig.md): Generic NeMo Relay plugin component configuration.
- [Struct Fabric Config](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/struct-fabricconfig.md): Versioned NVIDIA NeMo Fabric agent config.
- [Struct Relay Config](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/struct-relayconfig.md): NeMo Relay integration configuration.
- [Struct Harness Config](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/struct-harnessconfig.md): Harness selection.
- [Struct Relay Config Policy](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/struct-relayconfigpolicy.md): Relay validation policy.
- [Struct Instruction Config](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/struct-instructionconfig.md): One portable instruction value.
- [Struct Relay Observability Config](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/struct-relayobservabilityconfig.md): NeMo Relay observability component configuration.
- [Enum Instruction Mode](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/enum-instructionmode.md): How an instruction value is applied to the selected harness.
- [Struct Relay Open Telemetry Config](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/struct-relayopentelemetryconfig.md): Relay OpenTelemetry export section.
- [Struct Instructions Config](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/struct-instructionsconfig.md): Harness-neutral agent instruction configuration.
- [Struct Relay Open Telemetry Endpoint Config](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/struct-relayopentelemetryendpointconfig.md): One typed Relay OpenTelemetry OTLP destination.
- [Enum McpAuthentication Config](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/enum-mcpauthenticationconfig.md): MCP server authentication configuration.
- [Struct McpConfig](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/struct-mcpconfig.md): MCP capability configuration.
- [Enum McpExposure](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/enum-mcpexposure.md): MCP exposure strategy.
- [Struct McpServer Plan](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/struct-mcpserverplan.md): Resolved MCP server exposure.
- [Enum McpTransport](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/enum-mcptransport.md): MCP server transport.
- [Struct Metadata Config](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/struct-metadataconfig.md): Human-readable metadata.
- [Struct Model Config](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/struct-modelconfig.md): Model configuration.
- [Enum OAuth Token Endpoint Auth Method](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/enum-oauthtokenendpointauthmethod.md): OAuth client authentication method used at the token endpoint.
- [Enum Resolution Strategy](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/enum-resolutionstrategy.md): Adapter install or availability strategy.
- [Struct Resolve Context](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/struct-resolvecontext.md): Source context used when resolving an in-memory NeMo Fabric config.
- [Struct Resolved Adapter Descriptor](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/struct-resolvedadapterdescriptor.md): Adapter descriptor selected for a run plan.
- [Struct Resolved Adapter Target Descriptor](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/struct-resolvedadaptertargetdescriptor.md): Adapter target descriptor selected for a run plan.
- [Struct RunPlan](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/struct-runplan.md): Resolved NeMo Fabric run plan.
- [Struct Tools Plan](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/struct-toolsplan.md): Normalized tool policy for a run.
- [Struct Runtime Capabilities](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/struct-runtimecapabilities.md): Lifecycle behavior implemented by a resolved runtime path.
- [Struct Runtime Config](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/struct-runtimeconfig.md): Invocation runtime contract.
- [Struct Skill Config](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/struct-skillconfig.md): Skill capability configuration.
- [Struct Telemetry Config](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/struct-telemetryconfig.md): Telemetry configuration.
- [Struct Telemetry Plan](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/struct-telemetryplan.md): Resolved telemetry plan.
- [Enum Telemetry Provider](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/enum-telemetryprovider.md): Telemetry runtime provider.
- [Struct Telemetry Provider Config](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/struct-telemetryproviderconfig.md): Provider-specific telemetry configuration.
- [Enum Capability Kind](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/enum-capabilitykind.md): Capability kind.
- [Struct Tool Definition Config](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/struct-tooldefinitionconfig.md): One named normalized tool or tool-group definition.
- [Enum Capability Target](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/enum-capabilitytarget.md): Component responsible for executing a configured capability.
- [Struct Tools Config](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/struct-toolsconfig.md): Harness-neutral tool capability configuration.
- [Struct Workflow Config](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/struct-workflowconfig.md): Registered workflow target and immutable construction settings.
- [Struct Workflow Entrypoint Config](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/struct-workflowentrypointconfig.md): Adapter-owned workflow entry point supplied by an Adapter Target Descriptor.
- [Struct Workflow Target Spec](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/struct-workflowtargetspec.md): Workflow-specific Adapter Target Descriptor fields.
- [Function load_adapter_descriptor](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/fn-load-adapter-descriptor.md): Load an adapter descriptor from JSON package metadata.
- [Function load_adapter_target_descriptor](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/fn-load-adapter-target-descriptor.md): Load an Adapter Target Descriptor from declarative JSON metadata.
- [Function resolve_run_plan_from_config](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/fn-resolve-run-plan-from-config.md): Resolve a typed NVIDIA NeMo Fabric config into a runnable plan.
- [Enum Relay Atif Storage Config](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/enum-relayatifstorageconfig.md): Relay ATIF remote storage configuration.
- [Enum Relay Atof Mode](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/enum-relayatofmode.md): Relay ATOF file mode.
- [Enum Relay Atof Sink Config](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/enum-relayatofsinkconfig.md): Relay ATOF sink configuration.
- [Enum Relay Atof Stream Field Name Policy](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/enum-relayatofstreamfieldnamepolicy.md): Relay ATOF stream field-name policy.
- [Enum Relay Atof Stream Transport](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/enum-relayatofstreamtransport.md): Relay ATOF stream transport.
- [Enum Relay Open Telemetry Endpoint Type](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/enum-relayopentelemetryendpointtype.md): Relay OpenTelemetry span projection.
- [Enum Relay Open Telemetry Mark Projection](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/enum-relayopentelemetrymarkprojection.md): Relay OpenTelemetry mark projection policy.
- [Enum Relay Otlp Transport](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/enum-relayotlptransport.md): Relay OTLP transport.
- [Enum Relay Unsupported Behavior](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/config/enum-relayunsupportedbehavior.md): Relay unsupported/unknown config handling.
- [Module doctor](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/doctor.md): Plan diagnostics for NeMo Fabric.
- [Struct Doctor Check](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/doctor/struct-doctorcheck.md): Diagnostic check result.
- [Struct Doctor Report](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/doctor/struct-doctorreport.md): Diagnostic report for a resolved run plan.
- [Enum Doctor Status](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/doctor/enum-doctorstatus.md): Diagnostic status.
- [Function doctor_plan](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/doctor/fn-doctor-plan.md): Inspect a resolved run plan without mutating the environment.
- [Module error](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/error.md): Error types for NeMo Fabric core.
- [Enum Fabric Error](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/error/enum-fabricerror.md): Errors raised by NeMo Fabric config loading and validation.
- [Type Alias Result](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/error/type-result.md): Core NeMo Fabric result type.
- [Module runtime](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/runtime.md): Runtime invocation helpers.
- [Struct Adapter Invocation](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/runtime/struct-adapterinvocation.md): One invocation against an initialized adapter runtime.
- [Struct Artifact Manifest](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/runtime/struct-artifactmanifest.md): Manifest of run artifacts.
- [Struct Artifact Ref](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/runtime/struct-artifactref.md): Reference to one artifact.
- [Struct Environment Handle](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/runtime/struct-environmenthandle.md): Resolved execution environment context.
- [Struct Error Info](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/runtime/struct-errorinfo.md): Normalized error metadata.
- [Struct Fabric Event](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/runtime/struct-fabricevent.md): NeMo Fabric lifecycle or progress event.
- [Struct Invocation Handle](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/runtime/struct-invocationhandle.md): One request sent to a runtime.
- [Struct OpenAI Chat Completion Chunk](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/runtime/struct-openaichatcompletionchunk.md): OpenAI Chat Completions chunk accepted by the native streaming profile.
- [Struct OpenAI Chat Completion Chunk Choice](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/runtime/struct-openaichatcompletionchunkchoice.md): One choice within an OpenAI Chat Completions streaming chunk.
- [Struct OpenAI Chat Completion Chunk Delta](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/runtime/struct-openaichatcompletionchunkdelta.md): Incremental assistant message fields carried by one OpenAI choice.
- [Struct OpenAI Stream Invocation](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/runtime/struct-openaistreaminvocation.md): One adapter-native OpenAI streaming invocation.
- [Struct OpenAI Stream Sink](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/runtime/struct-openaistreamsink.md): Adapter-facing stream sink with invocation identity generated by NVIDIA NeMo Fabric.
- [Struct OpenAI Stream Transport](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/runtime/struct-openaistreamtransport.md): SDK-owned loopback transport for one native OpenAI streaming invocation.
- [Struct RunRequest](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/runtime/struct-runrequest.md): A request passed to a NeMo Fabric-managed harness runtime.
- [Struct RunResult](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/runtime/struct-runresult.md): Result from a NeMo Fabric-managed harness invocation.
- [Struct RunUsage](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/runtime/struct-runusage.md): Normalized invocation usage exposed to NeMo Fabric consumers.
- [Struct Runtime Context](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/runtime/struct-runtimecontext.md): Context generated for one invocation of a started runtime.
- [Struct Runtime Handle](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/runtime/struct-runtimehandle.md): Active or resumable harness runtime.
- [Struct Runtime Telemetry Context](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/runtime/struct-runtimetelemetrycontext.md): Runtime telemetry config passed to adapters.
- [Struct Service Handle](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/runtime/struct-servicehandle.md): Public identity and binding for one prepared or attached service.
- [Struct Service Reference](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/runtime/struct-servicereference.md): Caller-supplied reference to an already-running service.
- [Struct Telemetry Ref](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/runtime/struct-telemetryref.md): Reference to telemetry emitted by Relay or another configured telemetry path.
- [Enum Error Stage](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/runtime/enum-errorstage.md): NeMo Fabric lifecycle stage associated with an error.
- [Enum OpenAI Chat Completion Chunk Object](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/runtime/enum-openaichatcompletionchunkobject.md): Exact OpenAI object discriminator accepted by the v1 chunk profile.
- [Enum OpenAI Stream Host](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/runtime/enum-openaistreamhost.md): Supported native-streaming listener host.
- [Enum OpenAI Stream Profile](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/runtime/enum-openaistreamprofile.md): Supported OpenAI-compatible chunk profile.
- [Enum OpenAI Stream Protocol Version](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/runtime/enum-openaistreamprotocolversion.md): Supported southbound native-streaming protocol version.
- [Enum OpenAI Stream Record](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/runtime/enum-openaistreamrecord.md): One correlated NDJSON record on the adapter-native stream channel.
- [Enum RunStatus](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/runtime/enum-runstatus.md): Runtime completion status.
- [Enum Service Ownership](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/runtime/enum-serviceownership.md): Ownership of a service exposed through NeMo Fabric.
- [Function attach_service](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/runtime/fn-attach-service.md): Attach to a caller-owned long-lived service for a resolved run plan.
- [Function invoke_openai_stream](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/runtime/fn-invoke-openai-stream.md): Invoke a started harness runtime and pass through native OpenAI chat-completion chunks.
- [Function invoke_runtime](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/runtime/fn-invoke-runtime.md): Invoke a started harness runtime.
- [Function prepare_environment](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/runtime/fn-prepare-environment.md): Resolve or attach to the execution environment context for a run plan.
- [Function prepare_service](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/runtime/fn-prepare-service.md): Prepare a Fabric-owned long-lived service for a resolved run plan.
- [Function release_service](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/runtime/fn-release-service.md): Release a Fabric-owned service or detach from a caller-owned service.
- [Function run_plan](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/runtime/fn-run-plan.md): Invoke a NeMo Fabric run plan.
- [Function start_runtime](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/runtime/fn-start-runtime.md): Start or connect to a harness runtime.
- [Function start_runtime_with_service](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/runtime/fn-start-runtime-with-service.md): Start a runtime connected to an active service.
- [Function stop_runtime](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/runtime/fn-stop-runtime.md): Stop or detach from a harness runtime.
- [Module schema](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/schema.md): JSON Schema generation for the public NeMo Fabric contract.
- [Enum Schema Name](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/schema/enum-schemaname.md): Public schema snapshots generated by NeMo Fabric.
- [Function generate_all_schemas](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/schema/fn-generate-all-schemas.md): Generate all schemas keyed by stable schema name.
- [Function generate_schema](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/schema/fn-generate-schema.md): Generate one schema as a JSON value.
- [Function generate_schema_json](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/schema/fn-generate-schema-json.md): Generate one schema as pretty JSON.
- [Function write_schema_snapshots](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/schema/fn-write-schema-snapshots.md): Write all schema snapshots to `directory`.
- [Function version](https://docs.nvidia.com/nemo/fabric/dev/reference/api/rust-library-reference/nemo-fabric-core/fn-version.md): Returns the crate version compiled into this build.
- [Legal](https://docs.nvidia.com/nemo/fabric/dev/resources/legal.md): Legal information for NVIDIA NeMo Fabric.
- [Open Source Software](https://docs.nvidia.com/nemo/fabric/dev/resources/legal/oss.md): Open source software attribution for NVIDIA NeMo Fabric.
- [License Agreement](https://docs.nvidia.com/nemo/fabric/dev/resources/legal/license-agreement.md): License information for NVIDIA NeMo Fabric.