Poly
For teams: Poly lets you steer AI agents together in a shared room so everyone sees prompts, diffs, and credits transparently.
Built by Poly · Artificial Intelligence · Productivity · Developer Tools · Freemium
In category: #510 of 1953 · Artificial Intelligence
Poly is a Community listing on Launch Llama with 43 total upvotes, founded by Poly who joined in Sep 2026, compared against 6 alternatives.
Community listing
Listing status
43upvotes
Community score
Poly (Joined Sep 2026)
Founder
Compared against 6 alternatives
Market comparison
About
A shared room where your team steers AI agents Claude and/or ChatGPT. Every prompt, diff and credit visible to everyone. Free to sign up, no API keys needed.
Key Features
- Steer AI agents Claude and ChatGPT in a shared collaborative workspace
- View all prompts, code diffs, and API credits transparently across your team
- Collaborate without requiring individual API keys from team members
- Sign up and start using immediately with no setup or authentication barriers
Use Cases
- Collaborate on code generation with Claude or ChatGPT in a shared Poly room, viewing prompts and output diffs in real-time
- Jointly steer AI agents through feature specification in a shared Poly room with transparent prompts and suggested changes
- Collaboratively draft and refine content with AI agents in a Poly room, tracking every prompt revision and credit usage
- Brainstorm iteratively with Claude or ChatGPT in a shared Poly room, tracking changes and monitoring token consumption
- Onboard new team members on AI workflows in Poly, letting them observe prompts, diffs, and credit allocation
Pricing
Poly offers a free plan plus paid tiers. See the website for current pricing.
Founder story
Poly started with a small, familiar annoyance. This summer, my co-founder and I were building something together using Claude Code, and it was going well, except for one thing. We'd each work alone with the agent, make real progress, and then have to sit down and explain to the other what had happened. What changed, why, how, and which ideas got tried and thrown out. Half of it got lost in the retelling. It took me a few days to realize this was something AI had quietly broken. Building a product used to be slow enough to invite collaboration and communication. Now, it's too cheap and fast to collaborate or even talk through what you're doing, let alone the fact that you're in a private session with an agent. The two of us could each be confident we knew how something worked, and both be describing different conversations. So I built a room. One agent per project, and everyone in it watching the same timeline. When someone sends a prompt, the whole team sees it, the reply, and file changes; they can also jump in to redirect, approve, or deny. Nobody has to play catch-up or broken telephone anymore. Alignment stopped being a meeting and became a side effect of doing work.
FAQ
What is multiplayer AI?
AI a group uses together: everyone works with the same AI agent in one shared place, sees what was asked and what it did, and can steer it, instead of each person prompting alone. That's Poly.
Is it really multiplayer, or just a shared history?
It's live. Everyone in the room sees prompts, answers and changes as they happen, and anyone can answer the agent's questions, approve what it does next, or stop it mid-flight.
Which models can we use?
Claude, GPT, Grok, Meta's Muse and Kimi, in the same room. Each person picks their own model and thinking effort, and nobody needs an API key. Every lab has a free model — Sonnet 5.5, Haiku 5.5, GPT-6 Luna, Muse Spark 1.3, Kimi K2.7 Code and Grok Build; any plan or top-up unlocks the rest — Opus 5.5, Fable 5.1, GPT-6 Astra, GPT-6 Sol, GPT-5.6 Terra, Kimi K3 and Grok 4.7.
Do we have to stop using Claude Code or ChatGPT on our own?
No. Keep your solo sessions for solo work. Poly is for the work you'd do together anyway — the moments you'd normally screen-share.
Does it work with code we already have?
Yes. Connect a GitHub repository to a room and changes go straight into it, attributed to whoever made them. Push to a branch or open a pull request when you're ready. Or start from nothing.
What if the AI breaks something?
Every step is saved with a readable list of exactly what changed, and any step can be undone with the Undo button right under it. You can also require a yes before the agent edits anything at all.
What does it cost?
It's free to start, with no card. You pay only for the AI you run: plans from $20/month and top-ups from $5. Watching, chatting and approving in a room are always free.
Do you have a plan for teams?
Yes, in early access. Poly for Teams adds organizations, a room per team with its own playbook, shared team memory the agent reads on every turn, cross-team rooms, and usage by team. Book a demo or email support@usepoly.co.
Do I need my own API key?
No. Credits cover it.
Do my teammates need to pay?
Not on Team. Everyone's turns come out of one shared balance. On Pro or Max, each person pays for the turns they run. Joining, watching and approving are always free.
Alternatives
WaggletFor teams: Wagglet delegates AI tasks without sharing accounts so you collaborate safely while keeping work visible on shared boards.Ask AI about Poly
Supporters
33 founders
33 founders supported Poly on Launch Llama.
Reviews
1 comment
Hey, thanks for commenting! Just updated the founder story. Check it out.