refactor(cli)!: remove Hermes CLI support

README.md

@@ -28,14 +28,17 @@ evaluation products, see [the Ecosystem guide](https://docs.nvidia.com/nemo/rela
 
 | Goal | Start With |
 |---|---|
-| Observe Codex, Claude Code, or Hermes locally with the CLI | [Quick Start CLI](https://docs.nvidia.com/nemo/relay/nemo-relay-cli/about) |
+| Observe Codex or Claude Code locally with the CLI | [Quick Start CLI](https://docs.nvidia.com/nemo/relay/nemo-relay-cli/about) |
 | Instrument app-owned LLM or tool calls | [Quick Start Application](https://docs.nvidia.com/nemo/relay/getting-started/quick-start) |
 | Use LangChain, LangGraph, Deep Agents, or OpenClaw | [Supported Integrations](https://docs.nvidia.com/nemo/relay/supported-integrations/about) |
 | Build a framework or provider integration | [Integrate into Frameworks](https://docs.nvidia.com/nemo/relay/integrate-into-frameworks/about) |
 | Export ATOF, ATIF, or typed OpenTelemetry projections | [Observability Plugin](https://docs.nvidia.com/nemo/relay/configure-plugins/observability/about) |
 | Package reusable middleware or exporters | [Build Plugins](https://docs.nvidia.com/nemo/relay/build-plugins/about) |
 | Develop or test this repository from source | [CONTRIBUTING.md](CONTRIBUTING.md) |
 
+Hermes Agent understands NeMo Relay plugin configurations. NeMo Relay is built
+into Hermes Agent, so no separate observability plugin or Relay CLI setup is
+required.
 
 ## Quick Start CLI
 
@@ -45,7 +48,7 @@ trajectory file, you have concrete data to inspect, debug, and build on.
 ### Local Agent Trajectory
 
 This walkthrough shows an end-to-end quick success setup. Install the
-NeMo Relay CLI, turn on local exporters, run Codex, Claude Code, or Hermes
+NeMo Relay CLI, turn on local exporters, run Codex or Claude Code
 through Relay, and check that Relay wrote both raw events and normalized
 trajectories.
 
@@ -129,12 +132,6 @@ For Claude Code, run:
 nemo-relay claude -- "Summarize this repository."
 ```
 
-For Hermes, run:
-
-```bash
-nemo-relay hermes -- -z "Summarize this repository."
-```
-
 Refer to the full [Quick Start CLI](https://docs.nvidia.com/nemo/relay/nemo-relay-cli/about) docs for more options.
 
 The transparent wrapper starts a local Relay gateway, injects host-specific hook
@@ -318,7 +315,7 @@ coverage.
 |:--|:--:|:--:|:--:|:--|
 | Claude Code | Yes | Yes | Partial | Hook forwarding, pre-tool blocking, and gateway-routed LLM observability are supported. |
 | Codex | Yes | Yes | Partial | Persistent install verifies the exact plugin hooks. Each `Stop` finalizes a turn snapshot; the supported generated schema does not install `SessionEnd`. |
-| Hermes Agent | Yes | Yes | Partial | User config installs the shared native MCP gateway lifecycle plus exact trusted hooks; gateway-routed or hook-backed LLM observability is supported. |
+| Hermes Agent | Yes | Yes | Partial | NeMo Relay is built into Hermes Agent, and Hermes Agent understands NeMo Relay plugin configurations. No separate observability plugin or Relay CLI setup is required. |
 
 ### Public API Integrations
 

crates/cli/Cargo.toml

@@ -34,7 +34,6 @@ async-stream = "0.3"
 axum = "0.8"
 base64 = "0.22"
 bytes = "1"
-chrono = "0.4"
 clap = { version = "4", features = ["derive", "env"] }
 clap_complete = "4"
 console = "0.16"

crates/cli/README.md

@@ -28,8 +28,8 @@ with the installed `nemo-relay` command rather than link against the crate.
 
 The CLI is designed for these tasks:
 
-- **Observe existing coding agents**: Run Claude Code, Codex, or Hermes
-  Agent through a local NeMo Relay gateway without changing the agent
+- **Observe existing coding agents**: Run Claude Code or Codex through a local
+  NeMo Relay gateway without changing the agent
   itself.
 - **Configure transparent runs interactively**: Use the setup wizard to write
   project or user configuration for supported agents.
@@ -47,14 +47,14 @@ The CLI provides these capabilities:
   Cargo package.
 - **First-run setup**: Bare `nemo-relay` launches setup when no config exists,
   then runs doctor once config is present.
-- **Agent shortcuts**: `nemo-relay claude`, `nemo-relay codex`, and
-  `nemo-relay hermes` start observed agent runs.
+- **Agent shortcuts**: `nemo-relay claude` and `nemo-relay codex` start
+  observed agent runs.
 - **Config-driven launch**: `nemo-relay run` resolves config, environment, and
   CLI overrides for deterministic non-interactive use.
 - **Hook forwarding server**: A local gateway accepts agent hook events and
   provider-shaped OpenAI or Anthropic requests.
-- **Persistent agent integration**: `nemo-relay install` configures Codex,
-  Claude Code, or Hermes Agent with one generated MCP bootstrap and the host's
+- **Persistent agent integration**: `nemo-relay install` configures Codex or
+  Claude Code with one generated MCP bootstrap and the host's
   canonical lifecycle hooks.
 - **Shared gateway lifecycle**: Every persistent integration launches the same
   host-neutral `nemo-relay mcp` client. Concurrent clients share one native

crates/cli/src/agents/claude/mod.rs

@@ -35,7 +35,6 @@ pub(super) const DESCRIPTOR: AgentDescriptor = AgentDescriptor {
         "PostCompact",
         "SessionEnd",
     ],
-    direct_hook_entries: false,
 };
 
 pub(super) fn parse_version(raw: &str) -> Option<Version> {

crates/cli/src/agents/codex/mod.rs

@@ -32,7 +32,6 @@ pub(super) const DESCRIPTOR: AgentDescriptor = AgentDescriptor {
         "PreCompact",
         "PostCompact",
     ],
-    direct_hook_entries: false,
 };
 
 pub(super) fn parse_version(raw: &str) -> Option<Version> {