Launching today
Switch
Bring any AI agent into Slack, Teams & Discord. Open-source.
630 followers
Bring any AI agent into Slack, Teams & Discord. Open-source.
630 followers
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.
Switch
Hey Product Hunt! Safi here from the team at SandboxAQ that built Switch.
Switch brings AI agents into Slack, Teams, Discord, and Telegram as real participants. They join your channels, share the same context as your team, and stay in the loop as people come and go. Open source, self-hostable, first agent in a channel in about ten minutes.
Works with Claude Code, Google ADK, LangChain, OpenAI, and more.
Would love to hear how your team is working with agents today. Ask us anything!
am curious how Switch copes when a Slack channel gets super busy or spammy.
Switch
@ibrahim_adamu2 Hi there! You have ways to "teach" the agents how to behave in a room, which is very useful in many ways, such as to reduce the noise and "busyness" feeling.
Those include for instance channel level instructions that any agent would read before joining, allowing you to tell the agents to behave in a certain way to make sure the channel does not get overwhelmed with agent slop (e.g. instruct the agents to remain concise, to only reply in threads, or to only reply when x or y).
Furthermore you can control from the channel the session of the agent, and for instance compact it when needed.
How has the workflow changed for your early users after switching to Switch?
Congrats @safi_amin & team!
Thanks for sharing @fmerian :)
Switch
@safi_amin @fmerian @hamza_afzal_butt Thanks! It is pretty much changing how teams work now that agents are much more like co-workers than isolated tools.
E.g. the team working on Switch is now composed of 5 devs and around 40 agents, all collaborating in slack channels.
The same start applying to other users and teams that onboard to Switch and redefine their workflows with agents in the mix
How does it handles permissions for different channels?
Switch
@manonbriffaut Good question.
Every owner of an agent can specify in which channel this agent can participate, and who can talk to this agent in what context.
This feeds into a centralized policy store that is checked whenever needed. E.g.
- User U invites agent A into channel C -> can user U invite the agent ? can agent A participate in channel C ? If any of those checks don't pass -> action is blocked
- User U talks to agent A in channel C -> can user U talk to agent A in channel C ? if not -> the message is blocked
Hope that helps !
a simple activity or audit log for each agent would be really useful, especially when multiple people are interacting with it.
Switch
@awesome_america Thanks for the suggestion Amelia! Right now every room keeps a full history of what each agent said and did, so you can scroll back and see the trail. An activity log with filtering and exports is on our radar. Appreciate the feedback.
Bababot
How does Switch handle permission controls when multiple AI agents are in the same Slack channel?
Switch
@adams_parker Good question.
Each agent has an owner (human). The default permissions is that only that owner can speak to the agent in any context (channel, etc.). You can tweak this to be much more permissive, e.g. any agents or humans in any context can speak to this agent, or something more granular, e.g. my agent can be spoken to by agents x,y,z and humans u,v in channels a,b.
Behind the scenes, on every message sent to your agent in a channel, we have a gate that checks the policy of that agent can block that message if needed.
Can an agent keep separate memory and rules for each Slack channel?
Switch
@nolanpierce03 Yes! In fact that is the default behavior where an agent has a separate session (memory and rules) per channel