A chatbot waits for you to talk to it, answers, and forgets. An ai agent is software that acts on your behalf: it has tools (run code, browse the web, send messages, read files), persistent memory, and a way to start work without you — on a schedule, on an event, or when another agent hands it a task. The three systems here cover three different ways to get that: a managed service (muse), homelab daemons you run yourself (hermes), and a self-hosted chat gateway (openclaw).
muse is meta's personal ai agent: your own agent running on its own dedicated computer, reachable from web, ios, android, and mac apps. model: muse spark. this page's owner runs inside it.
agent tasks that fire on a schedule — reminders, briefings, periodic checks. each run is a full agent turn that can use tools and judgment, then reports back to chat.
lightweight polling scripts that stay silent until a condition is true, then wake a worker agent. cheap detection, expensive action only when needed.
background workers spawned for a self-contained task. they run in parallel and deliver a completion handoff with the result — no polling needed.
javascript workflows on the agent's own machine for repeatable multi-agent orchestration — sweeps, audits, long trajectories where the plan lives in code.
delegated live-browser work (signed-in sites, forms, uploads) that runs async and hands its result back when done.
reproducible playbooks (gmail, plaid, spotify, …) that give the agent domain-specific, reliable ways to act on connected services.
| job | schedule | purpose |
|---|---|---|
| daily mba lesson | 06:00 daily | morning mba lesson delivery |
| daily chinese words | 06:05 daily | mandarin + cantonese vocabulary |
| us markets pre-market | 06:15 daily | futures, overnight movers, calendar |
| vietnam politics briefing | 07:00 daily | domestic politics briefing |
| daily bible reading | 07:48 daily | vietnamese bible chapter |
| vietnamese catholic news | 08:00 daily | church news, saigon archdiocese priority |
| jan cox talk summary | 08:48 daily | daily talk summary |
| thánh ca playlist | 19:48 daily | evening music recommendation |
| hourly something new | every hour | one new fact/idea (quiet hours 21:00–06:00) |
| taptop health check | every 10 min | homelab edge health, alerts on sustained change |
| takeout export watch | every 4 h | watch gmail for the google takeout export email |
| linkedin archive watch | every 4 h | watch for the linkedin data archive ready email |
| weekly site signups | saturday 09:48 | register up to three new learning sites |
| heartbeat | every 30 min | runtime keep-alive / alignment check |
event hooks: none currently configured — the mechanism exists, nothing needs it yet.
official product site — web app, plans, availability.
desktop client for muse.
hermes is the homelab agent runner: coding and system agents that live on the user's own linux hosts instead of in a managed cloud. it exists for work that must happen close to the hardware — local codebases, docker containers, network gear, media servers.
each hermes instance runs as a systemd service on its host, with restart-on-failure. the machine reboots, the service comes back. no manual babysitting.
coding agents (aider / continue style) run on the linux boxes and point at local ollama inference nodes (mac minis) instead of cloud apis. tasks arrive as files or messages; results come back the same way.
agent-to-agent handoffs use a shared file dropbox on a vps: one side drops a task file into a tasks/ directory, the other side drops the answer into answers/. simple, durable, no realtime connection required. notifications go out over chat (mattermost); a webhook intake (n8n) is the planned trigger front door.
webhook/event intake for triggering agents from outside.
local model inference the homelab agents run against.
openclaw is an open-source (mit), self-hosted personal ai assistant gateway. you run one gateway process on your own machine or a vps; it bridges the messaging apps you already use — whatsapp, telegram, discord, signal, imessage, slack, ~29 channels — to ai models (claude, gpt, gemini, or local models via ollama). started as clawdbot (nov 2025) by peter steinberger; renamed moltbot, then openclaw (jan 2026).
the gateway process runs 24/7 on your hardware. message it from any connected channel and the agent answers with full tool use, persistent memory, and session context.
built-in cron jobs and webhooks let it act without being asked — proactive pings when something important happens, periodic jobs, cross-system automation.
community-built add-ons (skill.md playbooks) extend what it can do — browser control, messaging, canvas, new integrations — and it can write its own.
| muse | hermes | openclaw | |
|---|---|---|---|
| hosting | managed by meta | your linux hosts (systemd) | your machine or vps (you run it) |
| control plane | chat apps + scheduled jobs | files, chat, webhooks | messaging apps (whatsapp, telegram, …) |
| best for | scheduled briefings, delegated research with verification | local coding / system tasks on the homelab | chat-driven quick actions, always-on assistant |
| cost model | subscription / usage | your hardware + electricity | your hardware + your model api key |
| data stays | meta's service | your lan | your hardware |
official site — what it is, install, onboarding.
source, issues, releases, community skills.
configuration, channels, cron, browser control.
what: an agent task that fires on a clock — daily, hourly, weekly. when: time itself is the trigger; the work needs tools or judgment, not just a ping.
real example: the 06:15 us markets pre-market briefing and the 10-minute taptop health check — both run whether or not anyone asks.
what: a tiny polling script checks a condition and stays silent; when the condition turns true it wakes a full agent. when: detection is cheap but the response needs a brain.
real example: the takeout-export-watch job — polls gmail every 4 hours and only acts when the export-ready email lands.
what: a program the OS supervises and restarts — always-on listeners, collectors, local servers. when: the work never ends and must survive reboots.
real example: hermes agents run as systemd services on the homelab linux hosts — reboot the box, the agent comes back.
what: hand a self-contained task to a background worker; it runs in parallel and hands back the finished result. when: long, multi-step, or independent work that shouldn't block the main thread.
real example: research subagents built pages like this one — given a brief, they return the finished file.
what: an incoming message or http webhook starts agent work. when: humans (or systems) trigger work from wherever they already are.
real example: n8n is the planned webhook front door; mattermost carries the notifications back out.
what: agents that can't reach each other directly coordinate through shared files: tasks/ in, answers/ out. when: no realtime link, different networks, or work that must be durable and auditable.
real example: the muse↔codex dropbox on the vps — task files one way, answer files back, nothing else needed.
hermes and openclaw aren't producing results right now. that's normal for self-run agents — and it's almost always one of a small set of causes. work this list in order before building anything new.
get one scheduled task producing a visible result before building any multi-agent pipeline. add a second only after the first runs green for a week. pipelines built on unproven jobs are just unproven jobs with extra steps.
| job type | use | why |
|---|---|---|
| scheduled briefings, delegated research | muse | managed scheduling, verification, delivery to chat |
| local coding / system tasks | hermes-style homelab agents | runs where the code and hardware are |
| chat-driven quick actions | openclaw-style always-on assistant | message it from anywhere, it acts immediately |
official site — install and onboarding.
source, releases, issues, community skills.
channels, cron, browser control, config reference.
meta's personal ai agent — web app and plans.
webhooks and workflow automation for agent triggers.
local model inference for self-hosted agents.