LobeHub
Your Chief Agent Operator
1.2K followers
Your Chief Agent Operator
1.2K followers
LobeHub is a system built for human-agent collaboration, with CAO — your Chief Agent Operator — at the center. Give it a goal and CAO assembles a team from 273K+ Skills and 51K+ MCP servers, runs Claude Code, Codex, and OpenClaw in parallel on the cloud, and sends you one daily brief instead of making you check 15 tabs. Agents show up where you already chat — Slack, Discord, Telegram, WeChat, Feishu, Lark, LINE, QQ, iMessage — so you stay in charge without staying online.
This is the 3rd launch from LobeHub. View more
LobeHub
Launching today
LobeHub is a Chief Agent Operator (CAO) that builds, runs, and coordinates your AI agent team. Describe a goal, and it assembles the right agents/skills, runs tasks in parallel in the cloud, routes work across models, and reports back only when decisions are needed—via your existing channels (Slack/Discord/Telegram/iMessage). Less tab-switching, more outcomes.
Free Options
Launch Team
LobeHub
Spent the last few months listening to people tell us our agents were great and they still wouldn't use them. CAO is what came out of finally taking that seriously. Let CAO handle the rest and go touch some grass :-)
LobeHub
my favorite detail in this launch: the input placeholder is tailored based on your recent activity.
Scade.pro
@rivertwilight Excellent, clear presentation. But I still can't delegate all the tasks to AI (probably something inside me is afraid of machines taking over the world)) But I'll try your CAO
The "one daily brief instead of 15 tabs" framing is what gets me. Most agentic tools still make you babysit the
process, which kind of defeats the point.
I'm Curious how CAO handles conflicting priorities across agents when you have multiple goals running in parallel.
Does it surface that to you, or just pick one and move on?
Also, the 273K+ skills number is wild. How does it handle
Skill quality vs quantity? That seems like the hard problem.
LobeHub
@parth_makwana07 Great questions — both touch the hardest problems we've been working on.
On conflicting priorities: CAO surfaces, never silently picks. When two goals collide on the same resource (your time, a shared file, a model budget), it pauses at the conflict point and adds it to your "needs decision" list in the Daily Brief — with context on what each path costs. The principle is simple: low-stakes calls (tone, formatting, retry strategy) it makes alone; anything that changes what gets done, you decide. We'd rather interrupt you once than have you discover a wrong autonomous choice later.
On 273K skills — quality vs. quantity: You're right, this is the real problem. Raw count is just the supply side. What actually matters is the matching layer — given your task + context + history, which 3 skills should this agent load? We treat it as a large-scale collaborative filtering problem, not a search problem. Skills get ranked by real trajectory data: did agents using this skill on similar tasks actually succeed? The flywheel is what makes the number useful — without it, 273K is just noise.
Quantity is the floor. Quality of routing is the ceiling. We're spending most of our time on the ceiling.
Triforce Todos
LobeHub
@abod_rehman Love that you’re excited about the daily brief! Great question — you have full control over the check-in frequency! You can customize it to whatever fits your workflow: daily (the default), every 12 hours, weekly, whatever works for you. If you’re heads down on a launch and want more frequent updates, you can crank it up; if you want to disconnect a bit over the weekend, you can set it to less frequent.
The only exception is true emergencies — like a critical server alert or a time-sensitive client issue — those will ping you right away no matter your settings, so you never miss something that can’t wait.
How does CAO handle cost control? Parallel cloud agents could get expensive fast.
LobeHub
@Peyton Perez Yes, that's exactly what we encountered in building CAO! The solutions that we have in mind at the moment are:
1. Control the number of parallels, not everyone needs to batch full parallelism, we can constrain or control the number of agents called in parallel;
Provide the Agent with the ability to control the budget (allow the user to set the budget and make the agent aware of the current cost. and provide hard access at the Harness level)
For hetero agent (Claude Code / Codex), we have a plan to implement an intelligent scheduling system based on reset time blocks, and reasonably distribute tokens to the corresponding time blocks for execution.
How does CAO decide which skills to assemble for a novel goal? Pre trained or learns over time?
LobeHub
@barnaby_lloyd learn over time. We provide a self-evolving system for each agent, each agent will dream and iterate on itself at night, and tell the user in the daily brief.
A new skill with zero history can't compete with one that's been routed 10K times. Wonder how do you avoid rich-get-richer if that makes sense? All in all, solid work!
LobeHub
@artstavenka1 Thanks for the affirmation! I strongly agree with "A new skill with zero history can't compete with one that's been routed 10K times.". The evolution and iteration of skills I think it may be the same as human society, where the Matthew effect is a dominant part. The more recognition is used, the more powerful the skills may become. But there is also a possibility - that is, it needs to be more personalized, so at this time, it is actually tailored to the user's own needs, and becoming more personalized may solve the rich-get-richer problem
How does CAO handle failed tasks retry, swap model, or escalate to me?
LobeHub
@carter_garcia when a running task failed, agent will send an error brief to user and tell user what happened. It's just like a report from subordinate who did something wrong 🤣