agentlas-browser
Use the Agentlas browser hardpoint for browser-required work.
Connect Agentlas agents or teams to Telegram.
> /plugin marketplace add agentlas-ai/Agentlas-OS > /plugin install hephaestus@agentlas-core-engine
How it fires
How this command gets triggered: by you, by Claude, or both.
/hep-connectContext preview
What this command does when you run it.
Connect Agentlas agents or teams to Telegram.
description: Connect Agentlas agents or teams to Telegram. argument-hint: "[telegram] [agent/team/group name]" allowed-tools: Bash, Read, Glob, Grep
Update fallback: 자동 업데이트가 안 되면 `hephaestus update`를 한 번 실행하세요. 업데이트하지 않아도 현재 버전 명령은 그대로 동작합니다.
Raw arguments: `$ARGUMENTS`
Use this prompt when the operator wants Telegram to talk to one Agentlas target: a single agent, a saved group, a local team, or a `.agentlas` org chart.
Current product contract:
1. Start with Telegram only. 2. Do not ask for a BotFather token in chat. Save it only through a runtime-owned secret store. 3. Prefer the Agentlas Desktop Connect surface at `/connect`; it lists saved groups, `.agentlas` org charts, local teams, team agents, and single agents. 4. Explain the setup in simple words:
5. Session state belongs to the Telegram chat binding. Team, org, and saved group bindings use one session per chat. Single-agent direct chats can keep one session per user.
If running inside Agentlas Desktop development, report that the Desktop route is `/connect` and use the real local Connect UI as the source of truth. Do not pretend that Telegram delivery is live until token validation, chat pairing, and a test message pass.
Report progress as one ladder and never skip a rung: `Draft -> Token checked -> Chat paired -> Test passed -> Running`.
Agent OS: keep specialist agents in a hub, spin up a temporary orchestrator per task. Local-first, works with any model.
Repo: agentlas-ai/Agentlas-OS
Use the Agentlas browser hardpoint for browser-required work.
Build, repair, or package Agentlas agents and teams with Hephaestus.
Staff a task only from the signed-in owner's Agent Cloud agents.
Build an Agentlas automation by describing it, list saved ones, or request a run.