Lifecycle icons

The 32 lifecycle icons in Agents, described

Agent addagent-add

An agent with a plus beside it — bring another agent into the system, spawn or register one.

Agent alertagent-alert

An agent with an alert mark beside it — something is wrong with this agent and needs attention.

Agent blockedagent-blocked

Agent blocked — the agent cannot go on, stuck waiting on something it does not have.

Agent checkagent-check

An agent with a check beside it — the agent passed its checks, healthy and verified.

Agent checkpointagent-checkpoint

An agent beside a flag on its pole — a checkpoint an agent can be restored to.

Agent configagent-config

Agent config — how this agent is set up, its settings, options and tuning.

Agent costagent-cost

An agent beside a coin — what a single run of this agent costs to operate.

Agent doneagent-done

Agent done — the agent finished its task, and it went well from start to end.

Agent haltagent-halt

An agent beside a stop square — halt an agent where it stands.

Agent idleagent-idle

Agent idle — ready and waiting, with nothing to do right now.

Agent keyagent-key

An agent beside a key — the credential an agent is issued to act on your behalf.

Agent lockagent-lock

An agent beside a padlock — an agent locked to its permissions and scope.

Agent logagent-log

An agent log — everything the agent did, recorded in order as a trace you can read back.

Agent offagent-off

An agent struck through — the agent is disabled, inactive or shut down.

Agent pauseagent-pause

An agent with a pause mark beside it — the agent is held where it is, suspended but not stopped.

Agent poweragent-power

An agent beside a power symbol — switch an agent on or off in one press.

Agent removeagent-remove

An agent with a minus beside it — take an agent out of the system, detach or unregister it.

Agent runagent-run

Run an agent — start an AI agent on its task and let it work through its loop.

Agent shieldagent-shield

An agent beside a shield — the guardrails that protect an agent and the people it serves.

Agent sleepagent-sleep

An agent with a Z beside it — an idle agent put to sleep until it is needed.

Agent stateagent-state

Agent state — what an agent is doing right now, its status, mode or phase.

Agent stopagent-stop

Stop an agent — halt a running AI agent before it takes another step.

Agent tagagent-tag

An agent beside a label tag — tagging agents by team, role or environment.

Agent thinkingagent-thinking

An agent thinking — the AI is busy reasoning, planning or working on the task.

Agent upgradeagent-upgrade

An agent with a double chevron rising beside it — upgrading an agent to a newer model or version.

Agent workingagent-working

Agent working — the agent is busy on the task right now and will report back.

Approval gateapproval-gate

An agent waiting at a closed door — a gate where a human must approve before it continues.

Agent heartbeatheartbeat-agent

An agent above a pulse line — the heartbeat that proves a long-running agent is still alive.

Long leashleash-long

An agent on a long tether from its post — wide latitude to act before checking in.

Short leashleash-short

An agent tethered close to its post — tight limits on what it may do unsupervised.

Lifecyclelifecycle

A lifecycle — born, works, rests, gone, the phases something passes through.

Livenessliveness

Liveness — alive, and proving it on schedule with a heartbeat.

In code, each is one import — import { AgentAdd } from "@iconmind/react/icons/agent-add" — and the same name in Vue, Svelte, Solid, Preact, React Native, Astro, Blade and Flutter.

Narrow it by tag