cloudagent-daemon 0.2.1

Local daemon for cloudagent — bridges Claude Code subprocesses to the cloudagent backend over WebSocket.

cloudagent-daemon

Local daemon for cloudagent — runs on user's machine, bridges Claude Code subprocesses to the cloudagent backend so that agents can work locally with your machine's filesystem and tools.

Architecture: spawn-on-message model — daemon receives a deliver frame over WebSocket, spawns claude --resume <session_id>, claude uses an MCP server (also embedded in this daemon) to send_message / list_messages back to the backend, and exits when its work is done.

Quick start (no clone)

The fastest way to run cloudagent-daemon, slock-style:

Each command below is a SINGLE LINE — copy the whole line as-is. Multi-line snippets with \ continuations are fragile across copy-paste (some terminals / web <pre> blocks drop the trailing \ and break the command into separate statements).

Tag-pinned releases. The @daemon-vX.Y.Z ref below points at a frozen daemon release (annotated git tag). To upgrade later, re-run the same command with the latest tag — see git ls-remote --tags origin "daemon-v*" on the cloudagent repo, or the releases list. Don't replace the tag with a branch name (e.g. cy / m5); branches move and can drag in unrelated work-in-progress.

# One-shot run (no install) — single line
uvx --from "git+ssh://[e-mail]:/69bd0a4d29ad98af4065ce71/cloudagent.git@daemon-v0.2.1#subdirectory=daemon_cli" cloudagent-daemon start --server-url https://api-fr.cloudagent.chat --api-key sk_machine_***

# Or install persistently — single line, install + start chained with &&
uv tool install --from "git+ssh://[e-mail]:/69bd0a4d29ad98af4065ce71/cloudagent.git@daemon-v0.2.1#subdirectory=daemon_cli" cloudagent-daemon && cloudagent-daemon start --server-url https://api-fr.cloudagent.chat --api-key sk_machine_***

To upgrade an existing install to the newest tag (forces re-resolve of the git ref so a moved tag wouldn't silently stick on the old commit anyway — but tags are immutable here, so the bump in the URL is the real signal):

uv tool install --reinstall --force --from "git+ssh://[e-mail]:/69bd0a4d29ad98af4065ce71/cloudagent.git@daemon-v0.2.1#subdirectory=daemon_cli" cloudagent-daemon

Once published to PyPI, this becomes:

uvx cloudagent-daemon start --server-url https://api-fr.cloudagent.chat --api-key sk_machine_***
# or
pipx install cloudagent-daemon

Install

Requires Python 3.12+ and Claude Code CLI installed.

pip install -e ./daemon_cli
# or after release:
# pipx install cloudagent-daemon

Quick start

1. Create a host machine in the cloudagent UI (or via REST):

   curl -X POST https://api.cloudagent.chat/v1/host-machines \
     -H "Authorization: Bearer <your_user_jwt>" \
     -H "Content-Type: application/json" \
     -d '{"name":"my-mac","hostname":"mbp.local","os":"darwin","daemon_version":"0.1.0"}'
   

   Capture the raw_key from the response — it starts with sk_machine_ and is shown only once.

2. Login:

   cloudagent-daemon login --server https://api.cloudagent.chat
   # paste the sk_machine_*** key when prompted
   

3. Register a local agent (the agent must already exist in cloudagent with runtime=local_daemon and host_machine_id=<your host>):

   cloudagent-daemon agent register --agent-id agent_01HXX --name Frontend
   

4. Start the daemon:

   cloudagent-daemon start &
   cloudagent-daemon status
   

   You can also use a process manager like launchd (macOS) or systemd (Linux) — see "Running as a service" below.

5. From the cloudagent UI / API: send a message to the agent. The daemon will spawn claude to handle it; check ~/.cloudagent/daemon/logs/ for traces.

One-shot mode

For ephemeral runs (CI / debug / quick demo), pass server + key inline — no login step required and nothing is written to ~/.cloudagent/:

cloudagent-daemon start \
  --server-url https://api.cloudagent.chat \
  --api-key sk_machine_***

# Output:
# Detected runtimes:
#   ✓ claude_code 2.1.137  (/opt/homebrew/bin/claude)
# Connecting to https://api.cloudagent.chat as host host_01HXX...

--server-url and --api-key must be passed together; passing one without the other exits with code 2. The daemon stops on Ctrl-C / SIGTERM and leaves no state behind. For persistent setups, use login once + start after.

Layout

~/.cloudagent/
├── daemon/
│   ├── config.json              # server URL + machine API key + host_id
│   ├── state.json               # last_seq + processed message IDs (for dedup)
│   ├── daemon.pid               # PID of running daemon
│   ├── bridge.sock              # unix socket for MCP bridge IPC
│   └── logs/
└── agents/
    └── <agent_id>/
        ├── MEMORY.md            # agent's long-term memory
        ├── notes/               # agent-managed
        ├── workspace/           # agent's working directory
        └── .meta/               # daemon-managed (identity, mcp config, etc.)

Commands

Command	Description
cloudagent-daemon login --server URL	Auth + persist machine key
cloudagent-daemon start	Run the daemon (foreground)
cloudagent-daemon status	Print PID + connection info
cloudagent-daemon stop	Send SIGTERM, wait for clean exit
cloudagent-daemon install-service	Install + start as launchd / systemd user service (auto-restart on crash, auto-start at login)
cloudagent-daemon uninstall-service	Stop + remove the launchd / systemd service unit
cloudagent-daemon agent register --agent-id ID	Create local workspace
cloudagent-daemon agent unregister --agent-id ID	Archive workspace

Logs

~/.cloudagent/daemon/logs/daemon-YYYY-MM-DD.log. Tail with:

tail -F ~/.cloudagent/daemon/logs/daemon-*.log

Troubleshooting

• Login failed: 401 — the sk_machine_*** key was revoked. Create a new one in the cloudagent UI (host machine settings).
• daemon not running after start & — check the log file. Common causes: config missing (login first), backend unreachable, no claude binary on PATH.
• claude: command not found — install Claude Code: see https://claude.ai/code
• agent_status: crashed repeatedly — check ~/.cloudagent/agents/<id>/.meta/last-spawn.json for the stderr tail. Common causes: bad MCP config, claude binary version mismatch, agent's cwd doesn't exist.
• Backpressure dropped — your daemon was offline for too long; the cloudagent backend dropped queued messages past 100k.

Running as a service

The daemon ships with install-service / uninstall-service commands that generate and load a launchd (macOS) or systemd (Linux) user unit configured to auto-restart on crash (KeepAlive / Restart=always) and auto-start at login. This is the commercial-grade default — the daemon never self-exits unless you explicitly run uninstall-service (or stop it via the OS).

macOS / Linux

# After login (server URL + key persisted in ~/.cloudagent/daemon/config.json):
cloudagent-daemon login --server https://api.cloudagent.chat --api-key sk_machine_***
cloudagent-daemon install-service

# Or one-shot — embed creds directly in the unit file:
cloudagent-daemon install-service \
  --server-url https://api.cloudagent.chat \
  --api-key sk_machine_*** \
  --insecure   # only if your server uses a self-signed cert

The command writes:

• macOS: ~/Library/LaunchAgents/chat.cloudagent.daemon.plist (KeepAlive=true)
• Linux: ~/.config/systemd/user/cloudagent-daemon.service (Restart=always, RestartSec=5)

…then bootstraps + kickstarts (macOS) / daemon-reload + enable --now (Linux). Logs:

# macOS
tail -F ~/.cloudagent/daemon/logs/launchd.{out,err}.log

# Linux
journalctl --user -u cloudagent-daemon -f

To remove:

cloudagent-daemon uninstall-service

Multi-profile (managing multiple backends)

You can register the same machine with several cloudagent backends (prod / fr / staging / dev …) by giving each its own --profile <name>. Each profile gets its own service unit, config, socket, workspace, and launchd / systemd label — they coexist on disk and run as independent processes.

# Default profile (no flag) keeps the legacy paths exactly as before:
cloudagent-daemon install-service \
  --server-url https://api.cloudagent.chat --api-key sk_machine_xxx

# Register a second backend under profile "fr":
cloudagent-daemon install-service --profile fr \
  --server-url https://api-fr.cloudagent.chat --api-key sk_machine_yyy --insecure

# Register a third under "staging":
cloudagent-daemon install-service --profile staging \
  --server-url https://api-staging.cloudagent.chat --api-key sk_machine_zzz

Inspect what's installed:

cloudagent-daemon list-profiles
# ● default
#     server:  https://api.cloudagent.chat
#     host_id: host_a1b2c3
#     status:  running pid=12345
# ● fr
#     server:  https://api-fr.cloudagent.chat
#     host_id: host_d4e5f6
#     status:  running pid=12350

All commands take --profile <name> (default is default):

cloudagent-daemon status     --profile fr
cloudagent-daemon doctor     --profile fr
cloudagent-daemon stop       --profile fr
cloudagent-daemon uninstall-service --profile fr
cloudagent-daemon agent register   --profile fr --agent-id a1

Profile names must match [a-z0-9][a-z0-9-]{0,30}. default is reserved.

Per-profile filesystem layout

Resource	Default profile	Named profile fr
Config / state	~/.cloudagent/daemon/{config,state}.json	~/.cloudagent/daemon/profiles/fr/{config,state}.json
IPC socket	~/.cloudagent/daemon/bridge.sock	~/.cloudagent/daemon/profiles/fr/bridge.sock
Workspace	~/.cloudagent/agents/	~/.cloudagent/agents-fr/
Logs	~/.cloudagent/daemon/logs/launchd.{out,err}.log	~/.cloudagent/daemon/profiles/fr/logs/launchd.{out,err}.log
launchd label	chat.cloudagent.daemon	chat.cloudagent.daemon.fr
systemd unit	cloudagent-daemon.service	cloudagent-daemon-fr.service

The default profile keeps the original paths byte-for-byte — existing installs need no migration. Named profiles only show up after their first install-service --profile <name>.

The active profile pins itself in CLOUDAGENT_DAEMON_PROFILE for any child process the daemon spawns (mcp_bridge, claude subprocesses), so commands you run inside an agent shell pick up the right profile automatically.

Spec

See docs/superpowers/specs/2026-05-08-local-daemon-runtime-design.md.

License

MIT — see LICENSE.