MagiCrew
Give everyone their own AI workforce in one platform
735 followers
Give everyone their own AI workforce in one platform
735 followers
MagiCrew is an open-source AI Agent platform that gives everyone their own AI workforce. Instead of simply chatting with AI, deploy specialized digital workers that research, analyze, create reports, generate presentations, and complete real business tasks. With multi-agent collaboration, enterprise controls, and deliverable-ready outputs, MagiCrew helps teams turn AI from a tool they use into a workforce they can manage.
Dial
congrats on the launch. the "shared workspace so context carries between agents" bit is the interesting part to me, most multi agent tools I've tried just re-explain everything at each handoff. since it's open source, can I bring my own LLM keys and self host, or is the open part just the agent definitions while the platform itself stays hosted? asking because running several specialized agents per workflow instead of one chat could add up fast on the LLM bill
MagiCrew
@galdayan Thanks! You nailed the part we care about most — the shared workspace is the whole point. Every agent reads/writes the same filesystem and sees the full conversation context, so there's no "here's what the last agent did" summary step. It's less like a relay race and more like coworkers sharing a desk.
On the open-source / self-host question:
The platform itself is fully open source (Apache 2.0 with some additional terms), not just the agent definitions. The full stack — is all on GitHub (dtyq/magic). You can git clone → docker compose up and run the whole thing locally.
Yes, bring your own keys. You configure your LLM provider via .env — it works with any OpenAI-compatible API, so Claude, OpenAI, DeepSeek, Qwen, or whatever you're running behind a local gateway like LiteLLM. That's exactly the setup for people who, like you said, want to run several specialized agents per workflow without the per-seat cloud bill adding up.
The cost concern is real. Our take: the shared workspace actually helps with token spend too — agents don't burn context re-explaining state to each other, they just read the files. Shorter prompts, fewer wasted tokens.
Happy to answer anything more specific if you dig into the repo.
Dial
@enzy_magicrew that's a thorough answer, appreciate it. the "agents read files instead of re-explaining state" point is a good one, hadn't thought about shared-workspace as a token optimization rather than just a UX nicety. going to pull the repo and try wiring it to a local model, thanks.
Do you have plans for connecting these agents directly with tools like Slack, Notion, or Google Drive?
MagiCrew
@mercy_james3 Great question! Yes, absolutely — third-party integrations are very much on our roadmap. We're actively building a Connector framework right now to link up with tools like Slack, Notion, Google Drive, and more. It's not live just yet, but it's coming soon. The goal is to let your agents pull from and push to the tools you're already using, so everything stays in sync. Stay tuned — we'll share updates as we roll it out! 🔔
@enzy_magicrew congratulation on your product launch. Magic crew is a great product.
@enzy_magicrew i really like your Magic cew is open source AI, its quite interesting. i am looking forward to its more features. good luck with the launched, i supported you.
Curious! How this actually handles replacing between agent types without it feeling awkward, that's normally where these tools fall apart for me.
MagiCrew
@colton_drake Totally get that — clunky transitions are a dealbreaker. With us, you do switch between specialized agents, but the key difference is they all work in the same shared workspace. So when you move from a research agent to a slide-building agent, all the context, files, and progress are already there — no re-uploading, no re-explaining. It's like handing off a project to a teammate who's already been in the room the whole time. The switch is intentional, but the continuity makes it feel smooth. Give it a spin and let us know how it compares! 💪
I am running a startup that consists of only two people, hence, “AI workforce” means simply a chatbot with added steps in the marketing material. The reason for my interest was that it used deliverable-ready material such as presentations. I am going to try out the tool with our next investor presentation.
Congratulations on the launch, @enzy_magicrew solving a last miles problems where an output actually becomes usable is huge.
@enzy_magicrew how do you decides which tasks should be handle by one specialist agents versus multiple agents working togethers?
Congrats! Been burned by so many half completed AI outputs so this connects hard. Subscribing to see if it really delivers on the finish the thing promise.
MagiCrew
@james_carter35 Ha, we've been burned by those too — that frustration is literally why we built this 😅 "Finish the thing" isn't just a tagline, it's the bar we hold ourselves to. The whole point is you get a usable, polished deliverable — not a draft you have to spend another hour fixing. Welcome aboard, James — hold us to it and let us know how it goes 💪
Expertise AI
the “one step away from useful” problem is so real. getting an AI output is easy now, turning it into something I can actually use is usually where the work starts 😅 curious to see how MagiCrew handles that handoff in practice