ACP Host Integration

Python dependency commands on this page use a PM-prepared source checkout. After a dependency change, reactivate the checkout and restart Hermes.

Hermes Agent can run as an ACP server, letting ACP-compatible hosts talk to Hermes over stdio. Editors can render:

• chat messages
• tool activity
• file diffs
• terminal commands
• approval prompts
• streamed thinking / response chunks

Other hosts can use the same protocol to route collaboration events into Hermes. ACP is a good fit when you want Hermes to keep its existing identity, provider setup, memory, skills, and tools while another application owns the conversation transport.

What Hermes exposes in ACP mode

Hermes runs with a curated hermes-acp toolset designed for editor workflows. It includes:

• file tools: read_file, write_file, patch, search_files
• terminal tools: terminal, process
• web/browser tools
• memory, todo, session search
• skills
• execute_code and delegate_task
• vision

It intentionally excludes things that do not fit typical editor UX, such as messaging delivery and cronjob management.

The toolset resolves the same way as on the messaging gateway for the same platform config. That includes the extras the gateway adds on top of the list, such as enabled plugin toolsets, so ACP sessions get those too. platform_toolsets.acp replaces the hermes-acp default, and agent.disabled_toolsets removes toolsets from every ACP session. MCP servers from mcp_servers follow the same rules too. By default ACP gets every enabled server. If you list server names in platform_toolsets.acp, only those servers are included, and no_mcp drops them all. hermes tools has no ACP entry, so edit config.yaml directly:

platform_toolsets:
  acp: [file, web, skills, github]   # only the github MCP server
agent:
  disabled_toolsets: [code_execution]

MCP servers that the editor sends with session/new are separate. The client asks for them per session, and they are always added.

Editor-provided MCP servers

On gateways advertising acp-session-mcp-v1, editor mcpServers belong to the canonical session, not the ACP viewer process. The gateway uses separate registry namespaces even when two editors supply the same server name. Closing an editor does not cancel another session's MCP execution.

Discovery is eager and bounded before the first model turn. The selected tool schemas remain frozen for the conversation; server tool-list changes require a new session. MCP transports are released after each execution, without stopping sibling sessions or the shared MCP loop.

The gateway keeps the editor transport specification (including command arguments, environment values and HTTP headers) only in memory. Durable session policy holds a fingerprint and the selected schemas, not a copy of those credentials. After a gateway restart, the editor must supply the same mcpServers on load/resume. Missing credentials refuse execution; a changed specification or secret refuses reattachment rather than silently changing the session. Start a new session when changing the server configuration. Commands and paths run on the gateway host.

Installation

Install Hermes normally, then add the ACP extra from the install checkout:

cd ~/.hermes/hermes-agent && python -c "import pm; pm.sync_venv(['acp'], explicit=True)"

This installs the agent-client-protocol dependency and enables:

• hermes acp
• hermes-acp
• python -m acp_adapter

Launching the ACP server

Any of the following starts Hermes in ACP mode:

hermes acp

hermes-acp

python -m acp_adapter

Hermes logs to stderr so stdout remains reserved for ACP JSON-RPC traffic.

For non-interactive checks:

hermes acp --version
hermes acp --check

Browser tools (optional)

Browser tools (browser_exec and the CDP tools browser_cdp, browser_dialog, browser_vault) need a local Chromium, which isn't part of the Python wheel. Install it with:

hermes acp --setup-browser           # interactive (prompts before ~400 MB download)
hermes acp --setup-browser --yes     # accept the download non-interactively

This is the standalone command. The terminal-auth flow (hermes acp --setup) also offers the browser bootstrap as a follow-up question after model selection, so most users never need to run --setup-browser directly.

What it does:

• Installs Hermes' pinned Chromium (the chromium package) through the package manager; no Node.js or npm involved
• Hermes launches that Chromium itself when browser_exec first needs a browser

The bootstrap is idempotent — re-running it is fast and skips work that's already done.

Host setup

Buzz channels (relay bridge)

Buzz is a Nostr-based collaboration platform for people and agents. Its buzz-acp harness connects Buzz channels to any ACP agent over stdio:

Buzz relay <-- WebSocket --> buzz-acp <-- ACP over stdio --> Hermes Agent

This is a transport integration, not a second Hermes installation. The subprocess launched by buzz-acp uses the same Hermes configuration, credentials, memory, skills, and state as hermes on that host.

(This is distinct from Buzz Desktop's managed runtime, which spawns Hermes locally as a preset harness. The relay bridge is for joining Buzz channels as an agent identity, typically on a server.)

Prerequisites:

• Complete the ACP installation and hermes acp --check above.
• Build buzz-acp and the buzz CLI from the Buzz repository (cargo build --release -p buzz-acp).
• Mint a dedicated Nostr keypair for Hermes (buzz-admin generate-key) and register it as a relay member (buzz-admin add-member). Every agent needs its own identity — do not reuse a human keypair.
• Add that identity to the intended Buzz channels.

Start a bridge with:

export BUZZ_RELAY_URL="wss://community.example.com"
export BUZZ_PRIVATE_KEY="..."
export BUZZ_API_TOKEN="..."
export BUZZ_ACP_AGENT_COMMAND="hermes"
export BUZZ_ACP_AGENT_ARGS="acp"

buzz-acp

BUZZ_API_TOKEN is needed only when the relay enforces token authentication. Do not commit or paste the private key or API token.

For a persistent server deployment, run buzz-acp under a service manager as the same operating-system user that owns the intended Hermes home. Setup, key generation, channel discovery, and per-agent options are documented in the buzz-acp README.

The bridge discovers every Buzz channel where the Hermes identity is a member and automatically subscribes when it is added to another channel. Buzz channel membership therefore remains the access boundary; Hermes does not need a separate channel list in its own configuration.

To expose Hermes ACP activity in the owner's Buzz Desktop, add:

export BUZZ_ACP_RELAY_OBSERVER="true"

This publishes encrypted kind 24200 observer frames addressed to the agent's owner (Buzz's NIP-AO). Desktop renders the live lifecycle, tool, response, and usage stream in the agent's Activity log. The relay treats these frames as ephemeral, so Desktop must be online before the turn starts; its local observer archive is the durable owner-side history.

Headless bridges answer ACP permission requests themselves because no editor is present to show approval dialogs — see Keep Buzz agents owner-only. Treat the bridge as privileged automation: use a dedicated operating-system account, restrict which Buzz users can prompt the agent (buzz-acp supports an owner-only respond gate via BUZZ_ACP_AGENT_OWNER), and grant membership only in channels where Hermes is expected to work.

VS Code

Install the ACP Client extension.

To connect:

1. Open the ACP Client panel from the Activity Bar.
2. Select Hermes Agent from the built-in agent list.
3. Connect and start chatting.

If you want to define Hermes manually, add it through VS Code settings under acp.agents:

{
  "acp.agents": {
    "Hermes Agent": {
      "command": "hermes",
      "args": ["acp"]
    }
  }
}

Zed

Configure Hermes as a custom agent server in Zed settings:

1. Open the Agent Panel.
2. Add a custom agent server with the following configuration:

{
  "agent_servers": {
    "hermes-agent": {
      "type": "custom",
      "command": "hermes",
      "args": ["acp"]
    }
  }
}

3. Start a new Hermes external-agent thread.

Prerequisites:

• Configure Hermes provider credentials first with hermes model, or set them in ~/.hermes/.env / ~/.hermes/config.yaml.

JetBrains

Use an ACP-compatible plugin and point it at hermes acp or hermes-acp.

Buzz Desktop

Buzz ships Hermes Agent as a preset runtime. With Hermes installed the normal way, Buzz discovers it automatically — open Settings → Runtimes and Hermes appears under your runtimes.

If discovery fails (older installs), make sure the ACP launcher resolves on a login-shell PATH:

command -v hermes-acp || command -v hermes

Recent installs write both hermes and hermes-acp launchers into ~/.local/bin; running hermes update adds the hermes-acp launcher to older installs. As a manual fallback, configure Buzz's agent command as hermes with args ["acp"].

Model picker

Buzz Desktop (v0.5.1+) renders Hermes' full model menu in the agent's runtime settings. The list comes from Hermes itself over ACP: it shows every model from providers you have authenticated in Hermes (the same inventory behind hermes model and the /model command), so a model missing from the menu means its provider has no credentials configured on the Hermes side.

Entry IDs take the form provider:model (e.g. openrouter:z-ai/glm-5.1), or custom:<name>:<model> for custom OpenAI-compatible endpoints defined in config.yaml. Picking a model applies to that agent's session; it does not change your Hermes-wide default — use hermes model for that.

Keep Buzz agents owner-only

Buzz creates every agent with Who can talk to this agent set to Owner only. Leave it there when the runtime is Hermes.

Two behaviors combine on this path. The hermes-acp toolset includes terminal and execute_code, and Buzz's ACP bridge answers Hermes' permission requests itself with allow_once rather than surfacing them. A Hermes agent in Buzz therefore runs shell commands on the host without prompting. I asked one to run rm -rf against a scratch directory and it deleted it, no prompt anywhere.

Selecting Anyone hands that same shell access to every author who can reach the channel. Buzz does not warn when you pick it.

approvals.mode: manual does not help: Hermes raises the permission request, but Buzz auto-approves it and the command still runs. To take the shell away, narrow the toolset instead: set platform_toolsets.acp to a list without terminal and code_execution, or add them to agent.disabled_toolsets. Even an empty platform_toolsets.acp: [] still adds enabled plugin toolsets, so name any plugin toolset you want gone in agent.disabled_toolsets.

!shutdown from the owner stops the agent in any mode, and Buzz ignores that command from everyone else.

Configuration and credentials

ACP mode uses the same Hermes configuration as the CLI:

• ~/.hermes/.env
• ~/.hermes/config.yaml
• ~/.hermes/skills/
• ~/.hermes/state.db

Provider resolution uses Hermes' normal runtime resolver, so ACP inherits the currently configured provider and credentials. Hermes also advertises a terminal auth method (--setup) for first-run ACP clients; this opens Hermes' interactive model/provider setup.

Host integration

Older ACP hosts may still set this variable on the Hermes subprocess they spawn. It is not user configuration — do not set it by hand in .env or config.yaml.

Variable	Value	Effect
HERMES_ACP_SKIP_CONFIGURED_MCP	1	No effect. Hermes no longer reads it. hermes acp / hermes-acp runs as a viewer of the gateway daemon and never starts the config.yaml MCP servers itself, so there is no ACP-side startup to skip.

The ACP process does no MCP discovery. The gateway daemon starts the mcp_servers from its own profile's config.yaml once at gateway boot, and ACP sessions get those servers through the platform_toolsets.acp rules above. Setting the variable on the ACP subprocess or on the gateway does not change that. Use platform_toolsets.acp or no_mcp to keep configured servers out of ACP sessions.

The editor's session/new mcpServers are passed to the gateway and attached to that canonical session (see Editor-provided MCP servers), whether or not the variable is set.

Session behavior

ACP sessions are tracked by the ACP adapter's in-memory session manager while the server is running.

Each session stores:

• session ID
• working directory
• selected model
• current conversation history
• cancel event

Conversations are persisted to Hermes' session database and can be listed, loaded, resumed, or forked after the ACP server restarts. Opening a new session without a prompt keeps it in memory only: model-discovery probes do not create empty history rows. A nonempty fork is persisted immediately, and existing session metadata can still be updated even when its current history is empty.

Existing empty rows from older versions are not automatically deleted. An open ACP row does not prove its client has disconnected. After closing the relevant editor sessions, inspect unwanted rows with hermes sessions show <id> and remove only confirmed unwanted sessions with hermes sessions delete <id>.

Working directory behavior

ACP sessions bind the editor's cwd to the Hermes task ID so file and terminal tools run relative to the editor workspace, not the server process cwd.

Approvals

Dangerous terminal commands can be routed back to the editor as approval prompts. ACP approval options are simpler than the CLI flow:

• allow once
• allow always
• deny

Whether you actually see a prompt is up to the host. A host is free to answer the request programmatically instead of showing it to you, in which case these options exist on the wire but never reach a human. Buzz Desktop does this, so treat that path as unattended execution regardless of your approvals setting.

On timeout or error, the approval bridge denies the request. The wait is approvals.timeout from config.yaml (default 300 s), the same knob the CLI and gateway prompts use — raise it if your editor keeps approval cards open longer.

Session-scoped edit auto-approval

ACP exposes a third tier between allow once and allow always: Allow for session. Picking it from the editor's permission prompt records the approval inside the current ACP session only — every subsequent matching command in that session goes through without prompting, but a new ACP session (or restarting the editor) resets the slate and re-prompts the first time.

Option	Editor label	Scope	Persisted across restarts
allow_once	Allow once	This one tool call	No
allow_session	Allow for session	All matching calls in this ACP session	No — cleared when the session ends
allow_always	Allow always	All future sessions	Yes (written to the Hermes permanent allowlist)
deny	Deny	This one tool call	No

allow_session is the right default for an editor workflow where you trust an agent for the duration of a task but don't want to grant a long-lived allowlist entry. The safety trade-off is straightforward: the broader the scope, the less the editor will interrupt you, and the more damage a misbehaving agent (or prompt injection) can do before you notice. Start with allow_once for unfamiliar commands; promote to allow_session once you've seen the agent run the same pattern correctly a few times; reserve allow_always for truly idempotent commands you trust forever (e.g. git status).

The ACP bridge maps these options onto Hermes' internal approval semantics — allow_always writes a permanent allowlist entry the same way the CLI does, while allow_session only affects the in-process approval cache for the current ACP session.

Troubleshooting

ACP agent does not appear in the editor

Check:

• For manual/local development, verify the host command points to hermes acp.
• Hermes is installed and on your PATH.
• The ACP extra is installed (cd ~/.hermes/hermes-agent && python -c "import pm; pm.sync_venv(['acp'], explicit=True)").

ACP starts but immediately errors

Try these checks:

hermes acp --version
hermes acp --check
hermes doctor
hermes status

Missing credentials

ACP mode uses Hermes' existing provider setup. Configure credentials with:

hermes model

or by editing ~/.hermes/.env. The terminal auth flow (hermes acp --setup) can also trigger the interactive provider/model setup.

See also

• Buzz ACP harness
• ACP Internals
• Provider Runtime Resolution
• Tools Runtime