Omniscio

Hermes Provider

The Hermes CLI from Nous Research as an alternative session provider — a different agent on your own key, not Claude in a different harness. How to enable it, the readiness gaps, and how it behaves against the other providers.

On this page

What it is

Omniscio can spawn Claude-Code-style sessions backed by the Hermes CLI (hermes, by Nous Research) as an alternative provider, alongside claude (the default), codex, gemini, antigravity, the Anthropic-compatible deepseek / kimi, opencode, and cursor. Hermes is a model-agnostic, tool-using coding agent you install locally; it runs on its own model + provider key (whatever you set with hermes setup), so a Hermes session is "a different agent on your own key," not Claude in a different harness.

Why it exists: a migration on-ramp. An existing Hermes user can run their own Hermes install from inside Omniscio — keeping the agent they know while moving onto Omniscio.

Migrated to ACP (2026-08-01). Hermes was previously driven as a per-turn one-shot spawn (hermes -z), which broke multi-turn memory in Hermes v0.19.0 (the -z mode stopped restoring conversation history). Hermes is now driven over the Agent Client Protocol — a kept-alive hermes acp child, the same pattern as Kimi Code and Gemini — so multi-turn memory is native and real. This was verified live: turn 1 "favorite color is teal" → "got it"; turn 2 "what color?" → "teal".

What the user sees

A Hermes session looks almost identical in the sidebar and main pane to a Claude session — same status dots, same streaming bubbles, same Ctrl+Enter to send. The differences:

  • Hermes Agent mark (Nous Research's published logo, in the theme text color) in the session header next to the title, like every non-default provider. Hermes is a first-class provider — it shows a badge, is a per-project default, and is switch-to-able.
  • Token-by-token streaming. Omniscio drives the kept-alive hermes acp child over JSON-RPC/NDJSON on stdio (the shared ACP layer), so the reply appears incrementally as it generates. When the turn completes, one final push replaces the bubble with the full accumulated text.
  • Real stateful multi-turn. Because Hermes runs as a kept-alive ACP process, conversation memory is native — the agent remembers the full session history without Omniscio replaying prior turns as context.
  • Runs on YOUR Hermes config. Omniscio passes Hermes nothing but your prompt — no model overrides, no --model arg — so the session uses whatever model and key you configured with hermes setup. Omniscio stores no key for Hermes.
  • No per-session dollar cost. Hermes emits no token/cost over ACP v1, so Omniscio shows turn counts but the Cost line is hidden / $0 for Hermes sessions. Your spend is tracked in your own provider account (the key you gave Hermes).
  • Images go straight to the agent when your Hermes build can read them. On start-up Omniscio asks the running hermes acp child whether it accepts image prompts; if it does, an attached image is sent inline as an ACP image block. If it does not, the image is not sent and the session shows a short note saying so — describe the image in words, or switch to an engine with image support — never a silent drop. Documents are not delivered to Hermes (the compose area warns before you send).
  • Your project's MCP servers are handed to Hermes when its session starts, through the same shared ACP layer Gemini and Kimi Code use; remote (HTTP) servers only when the child said it supports that transport. If Hermes refuses to start with the servers, Omniscio starts it once more without them and tells you in the session.

Where to find it

How to enable

Master toggle required first. Hermes is an alternative provider — on a fresh install Hermes is already visible (the master toggle is ON by default since 2026-10-03); on a profile that last saved before that setting existed the entire Hermes setup section stays hidden in Settings → Accounts until you flip it on. Flip Settings → Accounts → Show alternative AI providers to ON and the Hermes (CLI provider) panel appears. With the master off, the per-launch provider switcher hides Hermes. Your "Allow Hermes sessions" toggle is preserved across master-toggle flips.

Two gates must both pass (getProviderSpawnReadiness enforces them in this order) — no API-key gate (Hermes holds its own credential):

  1. Hermes CLI binary — the hermes binary must be installed. Omniscio detects it (on PATH, the official Windows install dir %LOCALAPPDATA%\hermes\venv\Scripts\hermes.exe, or $HERMES_HOME\venv\Scripts) but does not install it. Install it from Nous Research's instructions, then run hermes setup to choose a model and add your provider key. Omniscio waits up to 30s and treats "present on disk = installed." If you just installed it, restart Omniscio so the running process picks up your updated PATH.
  2. Allow Hermes sessions toggle — off by default. Same security stance as the other auto-running providers: enable only because you intend to use it. Lives in the Hermes panel as Allow Hermes sessions in any project.

Once both are green, you launch a Hermes session three ways:

  • Per-project default — the Edit-Project "Default provider" radios and the "+ New Session" split-button include Hermes. New sessions in that project spawn Hermes automatically.
  • Per-launch override — on a fresh (zero-message) session, the Change-provider button (the launch-config pickers on a fresh session) lets you pick Hermes before sending the first message. A not-ready provider appears disabled with an "Install…" suffix that deep-links into the relevant Settings panel.
  • Programmatically — anything that creates a session with provider: 'hermes' (recipes, the CLI control server, deep-links). The same two readiness gates apply on the backend.

Moving your Hermes setup in

Separate from running Hermes sessions, Import from Hermes (a Lab switch, off by default) brings your Hermes memories, skills, scheduled jobs, MCP servers and personalities into Omniscio after a preview. Once the switch is on, the Import from Hermes… link under this Hermes panel opens it. See hermes-import.md.

How it behaves

No virtual project

Hermes has no dedicated __hermes__ sidebar entry (unlike __codex__ / __gemini__ / __antigravity__), and therefore no sentinel bypass of the "Allow Hermes sessions" toggle — the toggle always applies. You spawn Hermes inside any real project. (This matches Cursor/OpenCode; only Codex/Gemini/Anti-Gravity have virtual projects.)

Error states and fixes

Two gap codes (no key gap — Hermes uses its own credential):

Gap What it means Click-to-fix lands you at…
toggle-off "Allow Hermes sessions" is OFF in Settings Settings → Accounts → Allow Hermes sessions toggle
binary-missing hermes CLI not found Settings → Accounts → Hermes CLI panel

If a turn fails after Hermes is found, the most common cause is Hermes not being fully set up — the failure message points you at hermes setup (pick a model + add a key). An auth failure on session creation surfaces "run hermes setup to pick a model and add a key, then try again."

If a turn is rejected because Hermes's own working memory outgrew the model's window (usually a command that printed a huge amount of output), the message says it ran out of room and that the conversation is saved. Omniscio has already replaced the overflowed hermes acp process, so your next message starts fresh on a compact copy of the conversation — usually no new session is needed. If it still runs out of room, the conversation may be too long for the model, so start a new session.

Known issue: Hermes older than 0.21.1 on Windows

Hermes 0.19.x–0.21.0 on Windows freezes on its first shell command: the turn shows the tool starting and then stays "running" with no reply and no error. The cause is inside Hermes — before its first command it checks that Git Bash starts, and that check hands Git Bash the same pipe Omniscio uses to talk to Hermes, which Git Bash cannot start with while Hermes is listening on it. Hermes fixed it in 0.21.1. When a Hermes session starts on Windows with an older version, Omniscio posts one message in the session naming the version and the fix: run hermes update, then start a new session. An unknown version never triggers the message.

  • kimi-code-provider.md — its slim-ACP twin: same SlimAcpSessionManager base (hermes acp vs kimi acp), same 2-gate no-key readiness, same handshake-gated images + MCP servers, same shared permission gate. (Not kimi-provider.md — that is the Kimi MODEL run through the Claude CLI.)
  • ai-providers.md — the cross-provider overview
  • hermes-import.md — bring a Hermes setup (memories, skills, jobs, MCP servers, personalities) into Omniscio

Last verified 2026-11-14