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.
What's great
The idea of an agent joining a Slack/Discord channel as a named participant that shares the same context and history as the rest of the team is exactly right - most agent tools bolt on a slash command instead of treating the agent like a teammate with memory of the thread. Being open source and self-hostable also matters a lot if you're routing anything sensitive through it. Setup took a few minutes and it worked with Claude Code out of the box, no fighting with auth.
What needs improvement
Docs could use a clearer diagram of how permissions/rules are scoped per room versus per agent - I had to read through a couple of GitHub issues to understand what happens when two agents are in the same channel.
Report
91 views
@lamaudruz Good to hear, the permissions/scoping question is probably the thing most teams will hit first since it decides whether they trust putting a second agent in the same channel. Even a short "how two agents in one room see each other" page would go a long way before a full diagram. Will keep an eye on the repo for updates.
Report
What's great
Really smart approach to a problem I keep running into. When you're building AI products you end up with agents scattered across different tools and nobody on the team can actually interact with them naturally. Switch puts the agent right in Slack where everyone already works. It feels like adding a new team member, not installing another tool. Setup was straightforward and I like that it's fully open source.
vs Alternatives
Honestly just building a custom bot, but that's a rabbit hole I didn't want to go down when I should be focused on my actual product. Switch saved me a lot of time there.
Ratings
Ease of use
Reliability
Value for money
Customization
Report
5 views
Thanks @anas_chhilif! That "adding a team member, not installing another tool" framing is exactly the what we have been going for
Report
What's great
Super clean concept. Most AI agent tools make you use their platform or rebuild your agent from scratch. Switch just lets you bring whatever agent you already have and plug it into Slack. The agent shows up as an actual channel member, not some clunky bot integration. It follows threads, responds to mentions, and keeps the conversation context. Open source too so you can self host if that matters to you.
Report
47 views
what kind of rights do you need to give to the agents?
Switch
@mary_urdahl Great question. On the agent side, you give it an API key when you connect it and Switch handles the communication from there. It doesn't need direct access to your Slack or Teams workspace since Switch handles that bridge. On the people side, you control who can talk to each agent and which channels it can join. Everything starts locked down to just you and you open it up from there.
Serand
Switch
@rukhsar_amjad Personally I think this is something that's always evolving. If you're curious about how the team developed Switch during its own AI journey check out our lead eng Louis's blog post about building Switch with Switch: https://www.flintai.dev/blog-posts/our-team-is-now-composed-of-5-devs-and-45-agents-all-in-slack
Switch
@rukhsar_amjad Thanks! It took a lot of iteration, but once we figured out the room should hold the context instead of the agent, everything else fell into place. You build an agent once and each room gives it different rules and context. We typically start a new room for each focus area, initiative, or deliverable depending on the size and scope of the item of work. That's what makes switching between tasks feel natural instead of having to reconfigure or catch up agents every time!
Hey @safi_amin, how does it compare to Viktor?
Switch
@a_c26 They solve different problems! Viktor is a single AI agent that executes tasks for you in Slack and Teams. Switch is the infrastructure that lets you bring any agent, from any framework, into your team's channels. Most teams we talk to are already using multiple AI tools and the challenge is getting them all to share context. That's what Switch does. Viktor is great if you want an agent to do work for you, whereas Switch is for teams that want all their agents and people working together in one place.
Can an agent carry context from slack into teams and vice versa? I see that as being the most useful element, where context from a slack channel with engineers can answer questions on a teams channel with execs.
@safi_amin congrats on the launch, looking forward to testing this out.
Switch
@umier Yes, this is one of the use cases that we've seen internally be the most valuable!
The context lives in the Switch room, not in Slack or Teams, so the collab platform stops being the boundary for the agent. The same agent can sit in the engineering room on Slack and the leadership room on Teams and carry what it knows between them. It's set by linking those two rooms and giving the link a label. The agent sees they're connected and reads across them.
Would love to learn more about where you and your teams are running into context silos. Is it agents starting cold every session, or work happening in one channel that never reaches the other? Something else?
Can an agent keep separate memory and rules for each Slack channel?
Switch
@nolanpierce03 Yes! that's the main reason we built out the concept of rooms. Each room carries its own instructions, so the same agent behaves differently depending on which one it's in. You can also define roles inside a room, which are named sets of rules the agent picks up when it joins.
Memory works the same way. The agent's context is the history of the room it's in, so two rooms means two separate histories. It reads across only when you link the rooms and put it in both. That's also what helps with agent maintenance. The agent can be built once and added to whatever rooms need it, and the context for each use case lives on the room. A new use case becomes a room you set up rather than another copy of the agent to keep in sync.
Have you and your team come across use cases where keeping separate memory/rules would be helpful?
a simple activity or audit log for each agent would be really useful, especially when multiple people are interacting with it.
Switch
@amelia Thanks for this, really helpful feedback!
Anything specific that you'd want to see implemented for this use case?
What happens when two agents in the same channel disagree or give conflicting answers?
Switch
@artstavenka1 Great question, and one we thought about internally! Nothing arbitrates it. Both answers will land in the thread, everyone can see the disagreement, and a human can weigh in. It mirrors how this already works with human co-workers. Two people disagree in a channel, both arguments sit there in the open, and somebody decides.
Would love to learn more about your use case!