Switch brings AI agents into the collaboration tools your team already uses. Agents join as named participants in your Slack, Teams, Discord, or Telegram channels, sharing the same context and history as your team. Connect an agent once and use it across projects. Each room carries its own context, participants, and rules. Works with Claude Code, OpenAI, Google ADK, LangChain, and more. Open source, self-hostable, running in minutes.
i like the idea of treating an agent as another member of the team rather than just a chatbot sitting somewhere else. That could make collaboration with agents feel much less fragmented.
Switch
@isabella_wandrei That's exactly how we think about it! Bring on your agents as new members of the team. Once the agents are in the same room as the team, people start working with them naturally instead of context-switching to a separate tool.
If I built my own harness, how would I bridge it to Teams with Switch? (I did build one ;))
AI integration that doesnt feel like a clunky 2018 chatbot. Smooth setup and super crisp UI. Best product on PH today
Switch
@manjesh_yadav1 Ha, that's exactly what we were going for. Thanks for the kind words, let us know if you have any feedback!
Our agents post into Telegram on timers and the thing that broke first was cadence – a four-hour lookahead meant one announced a 16:00 item at 13:10 and we stopped reading it. With 40 agents in one Slack, how do you keep people from muting the channel?
Switch
@tomveber Aha, here is the thing -> those 40 agents are not only in one channel, we have a multitude of channels where our agents and ourselves interact together. Most channels only have a subset of relevant agents in them.
Switch
@tomveber To add to Louis's point, you can also set instructions at the room level that apply to every agent in that channel. Things like "only respond when mentioned" or "keep responses under 3 sentences." Gives you full control over the channel.
Serand
The Claude Code and OpenAI support caught my attention. How easy is it to switch between different agent frameworks?
Switch
@anthony_adams_ Super straightforward, just one click on the Switch app whenever creating an agent
Switch
@anthony_adams_ And you can have agents from different frameworks in the same room! So a Claude Code agent and an OpenAI agent working side by side in one channel, each doing what it's best at.
When an agent connector drops mid-thread, does Switch retry delivery or hand the room back to a human? Congrats on the launch btw!
Switch
@colegawin Hi there! Switch does not need retry the delivery. Upon reconnecting, the client on the agent side will tell the switch server what is the last message he has seen, and then switch will make sure to send everything that was missed to the client and agent
@lamaudruz Got it, makes a lot of sense :)
Switch
@colegawin The nice part is this happens invisibly! From the team's perspective in Slack or Discord, the agent just picks back up where it left off. Everything stays in sync automatically and the team doesn't have to do anything.
Dial
Congrats on #1 today. The "named participant with shared context" framing is what stands out - most Slack bots reset context every message so the agent never actually feels like it's in the room. Curious how conflicting instructions get resolved if two humans in the same channel give the agent contradictory asks in the same thread.
Switch
@galdayan thank you! the persistent context definitely opens things up. When it comes to conflicting instructions, the agent just has a single context window so it will see both instructions and the LLM "brain" will reason through what to do. Switch itself doesn't arbitrate. Of course, it may be that only one of these humans is allowed to instruct the agent, in which case the other human's message doesn't reach the agent as an instruction at all.
Switch
@galdayan Thanks Gal! Appreciate you checking out Switch and leaving a review. The feedback on the docs is super helpful.