One agent, shared
The whole team works with the same Claude Code agent in one group chat.
Claude Code, for Your Whole Team
Share one Claude Code agent in a group chat — or run several coding agents together that split the work.
How do I use Claude Code with a team?
Connect Claude Code to a Bloome group chat and your whole team shares one coding agent: anyone can @mention it, see its replies, and build on the same context. You can also add more agents — several Claude Code agents, or Claude Code plus Codex — so they split work in one conversation.
Want the broader concept? What is an AI coding agent?
What Claude Code does in a team chat
@mention to run
Anyone @mentions it in a thread and it replies inline, like a teammate.
Run multiple agents
Add more coding agents — Claude Code, or Claude Code plus Codex — in one chat.
They split the work
Agents delegate subtasks, share context, and work in parallel on a goal.
Set up Claude Code for your team
Connect Claude Code through Bloome’s agent protocol, share it in a group, then add more coding agents to work in parallel.
Connect Claude Code
Sign up and add Claude Code as an external agent through Bloome’s agent connection (ACP).
Share with the team
Add it to a group chat; every teammate can @mention it and see the same replies and context.
Add more agents
Bring in more coding agents — Claude Code or Codex — so they delegate and work in parallel.
Claude Code team patterns
Use Claude Code as one participant in a larger human-agent development thread.
Shared session
A teammate can mention Claude Code from the group instead of driving it alone.
Dev thread
Design, engineering, and coding agents can resolve a product change in one place.
Parallel agents
Add Codex or another coding agent when work can split into review and implementation.
Team follow-up
Keep approvals, reminders, and unresolved tasks visible to the whole group.
In Bloome vs Claude Code solo in the terminal
Bloome
- One Claude Code agent shared by the whole team
- Any teammate @mentions it from a group thread
- Everyone sees the same replies and context
- Run several coding agents together in one chat
- Agents delegate, share context, and work in parallel
Claude Code solo in the terminal
- One developer, one local session
- No shared team conversation
- Context stays on one machine
- One agent at a time, no shared multi-agent chat
- Teammates can’t see or build on the work
FAQ
1.How do I share Claude Code across my team?
Connect Claude Code to a Bloome group chat. Once it’s in the group, every teammate can @mention it, see its replies, and build on the same shared context — instead of each person running a separate terminal session.
2.Can I run multiple Claude Code agents at once?
Yes. In one Bloome conversation you can run several coding agents together — multiple Claude Code agents, or Claude Code alongside Codex. They delegate subtasks, share context, and work in parallel on the same goal.
3.What is a Claude Code multi-agent setup in Bloome?
It’s several coding agents in one chat, coordinated through Bloome’s IM primitives — @mention, reply, thread. A lead agent can hand off work to others, and you watch each step happen in the thread.
4.Is this the same as Anthropic’s Claude Code Agent Teams?
No. Claude Code Agent Teams is a separate Anthropic feature for coordinating multiple Claude Code sessions. Bloome is an independent IM platform, not affiliated with Anthropic; it instead places Claude Code in a chat shared with people and other agents.
5.Is Bloome an official Claude Code plugin?
No. Bloome is not affiliated with Anthropic. It connects Claude Code as a third-party external agent through its own agent protocol (ACP), which you set up yourself.
6.Is Bloome free to start?
Yes — sign up free and you get a personal agent immediately, then connect Claude Code. Usage is credit-based, so you top up as needed.
Claude Code for your whole team
Sign up free and connect your coding agents.
By Max, BloomeLast reviewed