<\/p>\n\n\n\n
SandboxAQ<\/a> has announced Switch<\/a>, a new open-source platform that brings AI agents and human teams together in the collaboration tools companies already use. The software connects agents into shared workspaces such as Slack and Microsoft Teams, allowing people and agents to work side by side in the same channel. As a result, teams no longer need to hand work between separate tools.<\/p>\n\n\n\n Switch is designed to be platform- and model-agnostic. Therefore, teams can bring their own agents and connect them into a common workspace, regardless of which provider built them. According to the company, the software can be activated within minutes in any standard enterprise environment, and it is available at no cost.<\/p>\n\n\n\n Developers today are building increasingly capable AI agents. However, putting those agents to work across a team still requires integrations and repeated context sharing. Switch addresses this by turning channels in tools like Slack, Microsoft Teams, and Discord into shared rooms. In these rooms, people and agents work together with the same context, resources, and history. Additionally, through MCP, APIs, and adapters, Switch remains vendor agnostic, so teams are not locked into a single AI ecosystem.<\/p>\n\n\n\n “Every team we talk to has capable agents trapped in separate tools, and a coordination tax eating the productivity those agents were supposed to deliver,” said Mohammed Aboul-Magd, General Manager, SandboxAQ<\/a>. He added that Switch pulls agents into the channels where teams already work, where knowledge compounds instead of being relearned with every task.<\/p>\n\n\n\n Several key capabilities are available in Switch today. First, it is fully open source, with Quick Start and Team editions that deploy in minutes and an extensible architecture for enterprise use. Second, users can bring their own agents, including those built with Claude Code, Google ADK, LangChain, OpenAI, and other frameworks. Third, the platform works within existing collaboration tools, meaning teams do not need to adopt new software. Furthermore, rooms preserve context and history as people and agents join, leave, or hand off work. Finally, a single agent can be reused across multiple rooms, each carrying its own context, participants, and rules.<\/p>\n\n\n\n Notably, the Switch team used Switch itself to build the product, with engineering, design, and marketing groups collaborating inside rooms throughout development. For example, security teams can pull specialized agents into a live incident without briefing them, since the room already holds the timeline. Similarly, a marketing team can staff a campaign room with research, copy, and design agents that build on each other’s work. Legal teams can likewise add drafting and review agents that already understand a deal’s full context, speeding up each round of review.<\/p>\n\n\n\n Switch is part of Flint AI<\/a>, SandboxAQ’s broader portfolio of AI agent products. It builds on the free Flint CLI<\/a>, which developers use to test and evaluate individual agents locally, by extending that work into shared, collaborative rooms.<\/p>\n\n\n\n The software is available now on GitHub under the Apache 2.0 license with the Commons Clause, meaning it is free for enterprise, personal, and product use. Developers can access tutorials and documentation at FlintAI.dev to get started. Ultimately, Switch reflects a broader industry shift toward integrating AI agents directly into the everyday tools that teams rely on.<\/p>\n\n\n\n <\/p>\n","protected":false},"excerpt":{"rendered":" SandboxAQ has announced Switch, a new open-source platform that brings […]<\/p>\n","protected":false},"author":58,"featured_media":107056,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"inline_featured_image":false,"_monsterinsights_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0,"footnotes":""},"categories":[147,9621],"tags":[10371],"contributor":[9732],"class_list":["post-107057","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-artificial-intelligence","category-emerging-technologies","tag-ai-agents","contributor-news-desk"],"featured_image_src":"https:\/\/techxmedia.com\/en\/wp-content\/uploads\/2026\/08\/SandboxAQ.jpg","author_info":{"display_name":"Lubna","author_link":"https:\/\/techxmedia.com\/en\/author\/lubna\/"},"aioseo_notices":[],"_links":{"self":[{"href":"https:\/\/techxmedia.com\/en\/wp-json\/wp\/v2\/posts\/107057","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/techxmedia.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/techxmedia.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/techxmedia.com\/en\/wp-json\/wp\/v2\/users\/58"}],"replies":[{"embeddable":true,"href":"https:\/\/techxmedia.com\/en\/wp-json\/wp\/v2\/comments?post=107057"}],"version-history":[{"count":1,"href":"https:\/\/techxmedia.com\/en\/wp-json\/wp\/v2\/posts\/107057\/revisions"}],"predecessor-version":[{"id":107058,"href":"https:\/\/techxmedia.com\/en\/wp-json\/wp\/v2\/posts\/107057\/revisions\/107058"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/techxmedia.com\/en\/wp-json\/wp\/v2\/media\/107056"}],"wp:attachment":[{"href":"https:\/\/techxmedia.com\/en\/wp-json\/wp\/v2\/media?parent=107057"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/techxmedia.com\/en\/wp-json\/wp\/v2\/categories?post=107057"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/techxmedia.com\/en\/wp-json\/wp\/v2\/tags?post=107057"},{"taxonomy":"contributor","embeddable":true,"href":"https:\/\/techxmedia.com\/en\/wp-json\/wp\/v2\/contributor?post=107057"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}