LobeHub - Your Chief Agent Operator for multi-agent work
by•
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.
Replies
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
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.
CtrlOps
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.
Mom Clock
Been using LobeHub since the early days. The CAO update is the first time it felt like the product caught up to what I actually wanted from agents. The daily brief alone is worth it.
LobeHub
@justin2025 This means a lot — thank you for sticking with us since the early days.
Honestly, the Daily Brief was the feature that made us feel the product finally clicked too. For a long time we were building "a better way to talk to agents." The shift to "agents that report back to you" changed how the whole thing felt to use. Glad it landed the same way for you.
More coming on the orchestration side soon — would love to hear what you'd want CAO to handle next.
LobeHub
@justin2025 I'm so proud of the daily brief, and I'm actually feeling much peacer when saw the briefs 😆
273K+ Skills and 51K+ MCPs sounds fantastically large. Where do these skills come from? Has anyone verified them? In other words, is there any kind of quality evaluation beyond what you probably did with a vector database, which can show semantic similarity but does not guarantee that the skill or MCP actually works?
LobeHub
@natalia_iankovych We value the skill quality so we are building the skill curation system right now. Soon there will be some human editor featured skills and collections. We know we cannot guarantee every skill works, but we can recommend those we really love.
LobeHub
Launch video is up on our YouTube — would love feedback on the pacing. Cut it down from 3 minutes to 70 seconds and I think it's better but you tell me.
LobeHub
@rika_lee1 love your motion 🙌
LobeHub
@rika_lee1 nice motion
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 🤣
Does CAO work with custom local models via something like Ollama, or only cloud APIs?
LobeHub
@gaius_loxley yes， We support local model provider like Ollama/vLLM/LM Studio. You can just download our desktop and then set the provider.
LobeHub
Hey Product Hunt 👋 Arvin here, founder of LobeHub.
Quick question before I pitch anything: how many AI tabs do you have open right now?
Claude Code in one window. Codex in another. Maybe OpenClaw or Hermes pinging you in Slack. On paper, you have an AI team. In practice, you became its operator — manually switching contexts, syncing progress across terminals, queuing up a "complex enough" task before bed because letting Claude Code idle feels like burning money.
BCG calls this "AI Brain Fry" — cognitive overload, fragmented attention, decision fatigue. 14% of heavy AI users already report it. We were promised AI would make work lighter. Somehow it made us tired in a new way.
We don't think the answer is a smarter agent. We think you shouldn't be the operator at all.
A company with a CEO but no COO is one where the founder personally chases every deadline and debugs every fire. That's exactly what your AI workflow looks like today.
So we're naming the role: CAO — Chief Agent Operator. And we're building LobeHub to be yours.
Why "CAO" and not "AI agent platform"? Because "agent tools" implies you have one agent and your job is to use it. The reality in 2026 is that you already have several agents running. This category doesn't need a better single agent — it needs a layer above them. Someone (something) to run the team.
Why this is possible now, and wasn't 2 years ago — three things shifted at once:
Agent self-evolution moved from papers to products. OpenClaw and Hermes proved agents can learn from sessions and turn successful workflows into reusable skills. LobeHub covers their capabilities — and goes further, because we're cloud-native: memory and skills evolve across sessions, devices, and teams.
MCP and Skills became the de facto standard. The LobeHub Marketplace now hosts 57k MCP servers and 270k skills. Your CAO has enough tools to actually do the job.
Multi-agent left the demo stage. The future isn't a single super-agent. It's an organization of agents — and organizations need an operator.
What you can do with LobeHub today:
🧠 Run multi-agent teams with shared memory and skills, not isolated chat windows
🔌 Plug into 57k MCP servers and 270k community skills out of the box
📡 Deploy your CAO across Discord, Telegram, Slack, Lark, and iMessage WhatsApp soon— one agent team, every surface
🛠️ Open source, self-hostable, and built on a runtime we've shipped to production for 3 years
I treated agents as first-class citizens on day one of LobeChat, back when "agent" still meant "a prompt with a name." Three years later, tools, MCP, skills, memory, and runtime finally compose into something that feels qualitatively different.
We're nowhere near the CAO I have in my head. Heterogeneous agent adoption, team workspaces, Agent Group 2.0 — all on the roadmap. But the direction is clear: free people from babysitting their AI, so they can spend that energy on what actually matters.
I'll be here all day answering questions. Brutal feedback especially welcome — tell me what's missing, what's broken, or what you'd want your CAO to handle first. 🙏
— Arvin, founder @ LobeHub
LobeHub
@arvinx ship 🚀
Mesh
@arvinx This is only for the cloud version? Self-hosted, especially 2.2.0, is quite regressive.
- No functioning CAO as far as I can see
- GTD completely removed, and replaced with Tasks system that is not quite functional, especially on self-hosted.
- Scheduled tasks (not to be confused with the previous Scheduled Tasks [lobe-cron?]) don't execute on self-hosted, despite it being a full package on a server, that can surely run crons.
- Tasks is not yet stable, despite it already replacing the actually functioning GTD. Tasks don't list properly like GTD did with a nice interface in agent chat. Tasks list in top-left of agent screen doesn't update itself, requiring agent screen refresh to show in Tasks panel in Agent screen
- Agent model configuration, specifically reasoning, deep thinking, token constraints, token reasoning effort, etc, is now missing. Seems to be a known issue, but release should've been rolled back.
- Documentation is wildly outdated and does not reflect the actual features, or system. (ex. Scheduled Tasks)
- Agent chat's skills Interface adds additional steps, and doesn't allow a skill to be disabled, only auto/not. What happened? Was there a UI/UX thinking about this, or just some agent went to town?
It feels like an agent has been promoted to Product Manager as the releases are rapid, but increasingly buggy with real breaking changes. This release was the most breaking change, eliminating GTD in full, model configuration panel, and scheduled tasks / CAO doesn't actually work.
You mention Agent Bridge, to bring my own agents, like OpenClaw, Hermes, etc. I don't see such a thing in self-hosted. I only see options to add Claude Code or Codex. Agent-bridge as your screenshots above show would be great!
It would also be nice, likely available but not exposed, to allow your agents to have their own API endpoint as there's a Developer Mode and API keys, but there's no documentation on how I might be able to make specific calls to specific agents, which is a common thing. The only alternative I can see at the moment is via Channels, but you don't support all channels at the moment. So at least an API endpoint to a LobeHub agent would be a nice option. Since the whole point is to have memory and persistent agents, of course I'd want my spec'd out agent to be able to respond to requests via API so it can be integrated into workflows such as N8N, and other related apps, flows, etc.
Maybe you feature flag the items, and self-hosted is missing this core functionality? But in that case, it should NOT have been updated until it was stable and confirmed. Anyone that updated was welcomed with a relatively broken LobeHub server.
I am strong advocate for LobeHub, and promote it every chance I get. I think it's has the potential to be the best harness/interface into agents, agent groups (teams), as it truly is the most intuitive and easy to get started, and continuously refine (especially as compared with equivalent OpenClaw, Hermes, etc). However, these recent updates have made it super brittle.
I'm hopeful you can clarify a bit as the recent updates promise more than I can see delivered, and worse, 2.2.0 broke it for me completely, wasting tokens in the wind.
I can go and and on and on about ideas for features requests, and other issues (especially memory compression), but I feel that's best left after the base is actually solid and useable again.
I'm hopeful the LobeHub team will get things back on track, and reduce/eliminate these wild breaking changes.
Thank you for reading all this. Please take it all positively, as I only want good things for LobeHub!