> For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.nvidia.com/nemo/relay/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/relay/_mcp/server. # Basic Usage The `nemo-relay` binary observes coding agents that do not expose every LLM call site directly. It combines agent-specific hook endpoints with a passthrough LLM gateway so NeMo Relay owns both the agent lifecycle and the model request lifecycle. Use the gateway when you need one observability boundary for OpenAI Codex, Claude Code, and Hermes without replacing each agent's canonical hook payload. ## Hook Endpoints Each hook endpoint accepts the agent's native hook JSON directly. Do not wrap the payload in a shared gateway envelope. * `POST /hooks/codex` accepts Codex hook JSON and returns the Codex-compatible hook response object. * `POST /hooks/claude-code` accepts Claude Code hook JSON and returns Claude-compatible fields such as `continue` and permission decisions when the hook event supports them. * `POST /hooks/hermes` accepts Hermes shell hook JSON and returns the empty JSON object expected by Hermes hook commands. The adapters preserve vendor fields such as session IDs, working directories, transcript paths, model names, tool payloads, shell payloads, MCP payloads, file payloads, user identity, and subagent metadata in NeMo Relay event metadata. ## Gateway Routes Route all coding-agent LLM traffic through the gateway when full LLM lifecycle observability is required. * `POST /v1/responses` * `POST /v1/chat/completions` * `POST /v1/messages` * `POST /v1/messages/count_tokens` * `GET /v1/models` The gateway forwards raw provider JSON without rewriting OpenAI or Anthropic payload schemas. It removes only hop-by-hop transport headers, forwards streaming responses as streams, and emits NeMo Relay LLM start and end events under the active session scope. ## Transparent Run Use the agent shortcuts for no-install local observability. The wrapper starts a gateway on a dynamic `127.0.0.1` port, injects the resolved hook and gateway configuration into the launched coding agent, and stops the gateway when the agent exits. Relay owns the launched wrapper and its descendants as one process tree, so a gateway failure cannot leave an agent running without its private gateway and hook configuration. Interactive Unix launches transfer foreground terminal ownership and preserve Ctrl-C and Ctrl-Z job control. Non-interactive Unix launches forward termination signals to the complete agent process tree before Relay removes the injected configuration. ```bash nemo-relay codex nemo-relay claude nemo-relay hermes ``` Use `nemo-relay run -- ` when you want to launch an explicit command instead of the built-in shortcut: ```bash nemo-relay run -- codex ``` For Claude Code and Codex, transparent mode leaves the caller's source settings, selected profile, and installed plugin state unchanged. A process marker makes any installed Relay MCP borrow the wrapper-owned dynamic gateway. Claude's persistent hooks exit without forwarding; Codex disables the known Relay plugin hook identities in its process-local CLI state. Only the injected wrapper hooks deliver events. Hermes gets the same isolation through its process-private configuration overlay. If a launcher or wrapper hides the real agent name, set that wrapper as the configured command and pass `--agent`. The same pattern applies to Claude Code, Codex, and Hermes: ```toml [agents.codex] command = "my-codex-wrapper" ``` ```bash nemo-relay run --agent codex ``` For Hermes, interactive setup configures only Relay's transparent wrapper. Persistent MCP and trusted shell-hook state is owned by `nemo-relay install hermes`. Transparent `run --agent hermes` exports the dynamic `NEMO_RELAY_GATEWAY_URL` through a process-private `HERMES_HOME` overlay; it never rewrites the user's Hermes config. Use `--dry-run --print` to inspect the generated hook config, gateway environment, gateway URL, and final command without launching the agent. ## Persistent Host Integrations Use persistent integration installation to let Claude Code, Codex, or Hermes Agent load Relay without a wrapper command: ```bash nemo-relay install claude-code nemo-relay install codex nemo-relay install hermes nemo-relay install all ``` Claude Code and Codex use marketplace plugins. Hermes exposes the same stdio MCP lifecycle through user configuration. Hermes, Claude Code, and Codex MCP clients can share the native gateway on `127.0.0.1:47632`. Every `nemo-relay mcp` process acquires that gateway when it launches. Claude Code uses `alwaysLoad` to wait for the MCP connection; Hermes starts discovery asynchronously, so its hook command waits for gateway readiness before it sends the original payload. For Claude Code and Codex, installation writes a local marketplace, installs the generated `nemo-relay-plugin`, and configures host-specific hooks and provider routing. For Hermes, installation updates the Relay-owned portions of the user configuration instead. All three paths use the local `nemo-relay` binary on `PATH`. Use plugin doctor and uninstall for the installed host state: ```bash nemo-relay doctor --plugin codex nemo-relay uninstall codex ``` Refer to [Coding Agent Installation](/nemo-relay-cli/plugin-installation) for install directories, host-specific behavior, and the shared-sidecar lifecycle. ## Shared Configuration Shared TOML config is optional. The gateway loads defaults, then system config, then project config, then user config. User config takes priority over system and project config. CLI flags and environment variables override file config. ### Interactive Setup Run `nemo-relay config` to set up Relay interactively: 1. Choose whether the base configuration should apply to the current project, your user account, or both. 2. Select the coding agents that Relay should observe. 3. Review and save the base `config.toml`. 4. Choose whether to continue to the plugin editor. The base `config.toml` stores the agent settings. Select **Yes** at the plugin prompt to configure optional Relay components and save them separately in `plugins.toml`. Project setup uses the project plugin configuration, global setup uses the user plugin configuration, and `both` continues with the project plugin configuration. Select **No** to finish after saving `config.toml`. Canceling the prompt or leaving the plugin editor does not remove the saved base configuration. You can open the plugin editor again later with `nemo-relay plugins edit`, or use `nemo-relay plugins edit --project` for project configuration. ### Provider Upstreams Set provider base URLs under `[upstream]` when you want Relay to forward compatible requests to a proxy, enterprise endpoint, or another provider host: ```toml [upstream] openai_base_url = "https://api.openai.com/v1" anthropic_base_url = "https://api.anthropic.com" ``` Relay normally chooses the upstream from the request path, regardless of which compatible client sends the request. The gateway routes map to settings as follows: | Gateway Endpoint | Upstream Setting | | ------------------------------------------- | -------------------- | | `/responses`, `/v1/responses` | `openai_base_url` | | `/chat/completions`, `/v1/chat/completions` | `openai_base_url` | | `/models`, `/v1/models` | `openai_base_url` | | `/v1/messages`, `/v1/messages/count_tokens` | `anthropic_base_url` | For ordinary provider requests, Relay resolves credentials in this order: 1. Relay preserves an inbound `Authorization`, `x-api-key`, `api-key`, or `anthropic-api-key` header. 2. If no inbound credential is present, Relay uses the route-specific custom `Authorization` value from `[upstream]` or its environment override. 3. If no custom value is configured, Relay reads `OPENAI_API_KEY` or `ANTHROPIC_API_KEY` and applies the provider's standard authentication scheme. Set `openai_auth_header` or `anthropic_auth_header` under `[upstream]` only when an enterprise gateway, proxy, or compatible endpoint requires a complete `Authorization` value such as `Bearer ...` or `Basic ...`. Prefer the corresponding environment variables so you don't store credentials in `config.toml`: ```bash export NEMO_RELAY_OPENAI_AUTH_HEADER="Bearer " export NEMO_RELAY_ANTHROPIC_AUTH_HEADER="Basic " ``` If you override a base URL with `NEMO_RELAY_OPENAI_BASE_URL` or `NEMO_RELAY_ANTHROPIC_BASE_URL`, set the matching auth-header environment variable when the new endpoint needs custom authentication. Relay doesn't carry a custom header from `config.toml` across an environment-level endpoint override. An MCP-managed gateway uses custom or environment credentials only after the client proves that it belongs to that managed gateway. Codex ChatGPT credentials are the exception to the normal inbound precedence. On OpenAI routes, Relay recognizes `Bearer eyJ...` JWTs and `Bearer at-...` access tokens. If `openai_auth_header`, `NEMO_RELAY_OPENAI_AUTH_HEADER`, or a nonempty `OPENAI_API_KEY` is available, Relay removes the ChatGPT credential, applies the replacement, and forwards the request to the configured `openai_base_url`. Without a replacement, Relay preserves the ChatGPT credential and routes the request to the Codex ChatGPT backend instead of `openai_base_url`. ### Operational Logging The CLI initializes operational logging before operational commands run. `nemo-relay config` and `nemo-relay plugins edit` skip initialization so invalid logging settings do not prevent configuration repair. Configure temporary CLI settings with `--log-level` and `--log-stderr-format`, or select an absolute TOML file with `--log-config-path`. For defaults, source precedence, environment variables, TOML file sinks, and Rust APIs, refer to [Operational Logging](/reference/operational-logging). ## Add Model Pricing for Cost Estimates Model pricing is configured with the same `plugins.toml` discovery path as Observability. The configured sources apply to transparent agent runs, standalone gateway runs, and evals or custom agents that initialize the same gateway plugin config. Framework integrations, harnesses, and custom hosts do not need their own model pricing logic when they emit managed LLM calls with response codecs: Relay attaches cost to the annotated response when the provider reports cost or when a configured model pricing source matches the response model and token usage. Create a Relay model pricing catalog JSON file: ```json { "version": 1, "entries": [ { "provider": "openai", "model_id": "gpt-4o-mini", "aliases": ["openai/openai/gpt-4o-mini"], "currency": "USD", "unit": "per_token", "rates": { "input_per_million": 0.15, "output_per_million": 0.6, "cache_read_per_million": 0.075 }, "prompt_cache": { "read_accounting": "included_in_prompt_tokens" }, "pricing_as_of": "2026-06-06", "pricing_source": "internal-pricing-snapshot" } ] } ``` Validate and add the file-backed source: ```bash nemo-relay model-pricing validate /path/to/pricing.json nemo-relay model-pricing init --project nemo-relay model-pricing add-source /path/to/pricing.json --project ``` Use `--user` instead of `--project` for a device-wide user config, or `--global` for `/etc/nemo-relay/plugins.toml`. `model-pricing add-source` prepends the source by default, so the new file becomes the highest-priority source for that scope. Use `--append` to add it as a lower-priority fallback. Resolve a model before running an agent: ```bash nemo-relay model-pricing resolve gpt-4o-mini \ --provider openai \ --prompt-tokens 1000 \ --completion-tokens 500 ``` `model-pricing resolve` prints the source that won, the matched provider/model, and an estimated total when token counts are supplied. Use it to debug overlapping fleet, project, and user model pricing files. Run doctor to validate the active model pricing sources alongside exporter checks: ```bash nemo-relay doctor codex ``` Doctor fails when an enabled model pricing source is unreadable or contains an invalid catalog, and it reports passing sources as `Model pricing source`. Relay does not ship a canonical price catalog. Unknown models and missing token fields leave cost absent instead of defaulting to zero. For the catalog schema, provider-aware lookup behavior, threshold-based model pricing, and custom `PricingSource` integrations, refer to [Provider Response Codecs and Model Pricing](/integrate-into-frameworks/provider-response-codecs#cost-estimation). Transparent runs always bind the managed gateway to `127.0.0.1:0`. The selected port is discovered by the wrapper and exposed to hooks through `NEMO_RELAY_GATEWAY_URL`. Common environment variables for direct gateway server use are: * `NEMO_RELAY_GATEWAY_BIND` * `NEMO_RELAY_OPENAI_AUTH_HEADER` * `NEMO_RELAY_OPENAI_BASE_URL` * `NEMO_RELAY_ANTHROPIC_AUTH_HEADER` * `NEMO_RELAY_ANTHROPIC_BASE_URL` * `NEMO_RELAY_MAX_HOOK_PAYLOAD_BYTES` * `NEMO_RELAY_MAX_PASSTHROUGH_BODY_BYTES` The default hook payload limit is `20MiB`. The default provider passthrough body limit is `100MiB`. Set both values in bytes. Plugin configuration controls process-level Observability exporters. Per-session configuration controls structured metadata on the top-level agent begin event and the plugin configuration metadata associated with the session. For example, attach a user identity to a transparent run: ```bash nemo-relay run --session-metadata '{"user_id":"alice"}' -- codex ``` The CLI emits one `session.start` mark for the lifecycle and copies the merged metadata onto each top-level trace scope. It also adds a non-overridable `session_instance_id` derived from the session's existing root scope UUID. Keep `user_id` a top-level string when OTLP exporters should expose it as `user.id`. `hook-forward` can also pass per-session configuration through headers: * `x-nemo-relay-config-profile` * `x-nemo-relay-session-metadata` * `x-nemo-relay-plugin-config` * `x-nemo-relay-gateway-mode` The accepted gateway mode values are `hook-only`, `passthrough`, and `required`. The gateway records this value as session metadata so downstream exporters and review tooling can distinguish hook-only traces from sessions where provider traffic was expected to pass through the gateway. ## Runtime Mapping The gateway normalizes vendor hook payloads into private internal events before calling NeMo Relay APIs. * Agent start emits a `session.start` mark on a dedicated `ScopeStackHandle`. Harnesses with a reliable session boundary also open a top-level `ScopeType::Agent` scope; Claude Code and Codex use bounded turn scopes. * Subagent start opens a child `ScopeType::Agent` scope. Subagent stop closes that scope when it is still active. * Tool pre-use starts a NeMo Relay tool span. Tool post-use, denial, or failure closes it. * Generated `UserPromptSubmit`, `Stop`, and Hermes `pre_llm_call` / `post_llm_call` hooks are retained as private correlation hints. The adapters do the same when a custom or older integration delivers a response or agent-thought hook. These hints are not emitted as NeMo Relay events. * Compaction, notification, and unknown hook events become mark events under the active session scope. * Gateway requests emit NeMo Relay LLM start and end events under the active session scope. Before each LLM start, the gateway uses explicit subagent headers, pending hints, shared conversation/generation/request identifiers, and the previous correlated owner to choose the parent scope. * LLM responses that contain future tool-use suggestions are retained as private tool-call hints. The next matching tool hook can then inherit the subagent scope that owned the LLM response, even when the hook payload does not include a subagent id. Gateway requests can provide explicit correlation identifiers with these headers: * `x-nemo-relay-session-id` * `x-nemo-relay-subagent-id` * `x-nemo-relay-conversation-id` * `x-nemo-relay-generation-id` * `x-nemo-relay-request-id` When those headers are absent, the gateway also looks for `conversation_id`/`conversationId`/`conversation.id`, `generation_id`/`generationId`/`generation.id`, and `request_id`/`requestId`/`request.id` fields in the provider request body. Correlation hints expire after five minutes. If the gateway cannot select one unambiguous hint, it falls back to the previous LLM owner, then to the only active subagent, then to the top-level agent scope. Every gateway LLM event includes `llm_correlation_status` metadata. Managed requests can use `explicit`, `single_hint`, `matched_hint`, `request_affinity`, `sticky_last_owner`, `recent_tool_owner`, `subagent_start`, `active_subagent`, `agent_fallback`, or `ambiguous_fallback`. Claude Code startup probes use `pre_turn_probe`. Matched hints can also add `llm_correlation_source`, `llm_correlation_subagent_id`, `llm_correlation_conversation_id`, `llm_correlation_generation_id`, `llm_correlation_request_id`, and `llm_correlation_agent_type`. Generated hook bundles subscribe to the events needed for that mapping: | Agent | LLM Lifecycle and Correlation Hooks | Scope, Tool, and Mark Hooks | | ----------- | ------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Claude Code | `UserPromptSubmit`, `Stop` | `SessionStart`, `SessionEnd`, `UserPromptExpansion`, `SubagentStart`, `SubagentStop`, `PreToolUse`, `PostToolUse`, `PostToolUseFailure`, `PermissionRequest`, `Notification`, `PreCompact`, `PostCompact` | | Codex | `UserPromptSubmit`, `Stop` | `SessionStart`, `SubagentStart`, `SubagentStop`, `PreToolUse`, `PostToolUse`, `PermissionRequest`, `PreCompact`, `PostCompact` | | Hermes | `pre_api_request`, `post_api_request`, `api_request_error`, `pre_llm_call`, `post_llm_call` | `on_session_start`, `on_session_end`, `on_session_finalize`, `on_session_reset`, `subagent_start`, `subagent_stop`, `pre_tool_call`, `post_tool_call` | Hermes `pre_api_request`, `post_api_request`, and `api_request_error` hooks map to NeMo Relay LLM start/end events when present. Hermes `pre_llm_call` and `post_llm_call` remain private correlation hints. ## Hook Forwarding Transparent Claude Code and Codex hooks invoke `nemo-relay hook-forward ` with the canonical payload on standard input. The wrapper-owned hook command embeds its ephemeral gateway URL and is marked as transparent so it cannot recover the fixed gateway. Persistent Claude Code, Codex, and Hermes hooks also use `nemo-relay hook-forward `. Each generated command identifies the fixed gateway and its private install-generation fence, waits for the MCP-owned Relay gateway, verifies it, and forwards the unchanged payload once. Hermes setup stores the canonical absolute command and trusts only its exact event pairs; it does not enable global hook auto-acceptance. `hook-forward` reads the canonical hook payload from standard input, sends it to the matching endpoint, and prints the endpoint response. It fails open by default so observability outages do not block the coding agent. Add `--fail-closed` only when policy requires hook delivery to block the agent. These flags control delivery and metadata: * `--gateway-url ` selects the Relay gateway that receives the payload. * `--forward-only` allows source plugins and custom automation to use an existing compatible gateway without an installer-owned generation fence. It verifies the gateway but never launches or recovers Relay. Generated installed hooks use a private generation fence instead. * `--session-metadata` sets `x-nemo-relay-session-metadata`. * `--profile` sets `x-nemo-relay-config-profile`. * `--gateway-mode` sets `x-nemo-relay-gateway-mode`. * `--fail-closed` returns a failure when delivery fails or Relay rejects the hook. Without it, forwarding fails open so an observability outage does not block the coding agent. ## Agent Guides Use the per-agent guide for end-to-end setup, smoke tests, and GUI or application-mode caveats. * [Claude Code](/nemo-relay-cli/claude-code) * [Codex](/nemo-relay-cli/codex) * [Coding Agent Installation](/nemo-relay-cli/plugin-installation) * [Hermes Agent](/nemo-relay-cli/hermes) Each guide covers transparent run setup, gateway routing, hook smoke tests, Agent Trajectory Interchange Format (ATIF) export verification at the host's supported snapshot boundary, and troubleshooting missing LLM lifecycle data.