AgentConnect today announced the release of its open-source platform designed to enable teams and multiple AI agents to collaborate across the communication and development tools they already use. The platform addresses a growing challenge in the AI agent ecosystem: while agents are becoming more capable, their work often remains isolated to individual terminals, leading to fragmented context and duplicated efforts. AgentConnect aims to bring agents into existing team conversations, allowing for more cohesive and efficient workflows.
The company highlights that AI agents become significantly more useful when they can collaborate with the entire team rather than working in isolation. The platform supports integration with Claude Code, Codex, and other ACP-compatible agents, allowing each agent to have a distinct role. Teams can interact with these agents through shared conversations and agent-to-agent calls, all within their familiar tools such as Slack, Telegram, and Discord.
One practical application is incident response. A team can deploy a triage agent to inspect available context, a code specialist to trace a suspected regression, and a verification agent to check proposed results. Human teammates can add context, redirect the work, and follow the entire process within the same Slack thread, ensuring transparency and coordination.
The platform extends beyond incident response. For instance, a support issue can be moved from a customer-facing Telegram conversation into a trusted Slack workspace without manual context copying. Engineering teams can combine general and specialist reviewers to assess the risk of each pull request, with inline GitHub comments and independent check results. Scheduled and webhook-driven work can also continue in shared conversations when human input is needed.
Key features of AgentConnect include the ability to configure multiple agents with distinct models, workspaces, memory, MCP servers, skills, repository access, and sandbox policies. It supports integration with existing tools, allowing work to start from conversations, GitHub pull requests, webhooks, or schedules. The platform offers fine-grained access control, enabling administrators to manage agent access separately from session visibility and link multiple social accounts to one member profile for consistent permissions.
AgentConnect is open source under the Apache 2.0 license and can be deployed using Docker Compose or Kubernetes. This ensures that agent execution and workspaces remain within the environment the team operates, addressing security and control concerns. The OSS version is available today, and the source code can be explored on GitHub, with further details on the AgentConnect website and in the documentation.
The introduction of AgentConnect represents a significant step toward more integrated and collaborative AI agent usage in team environments. By enabling agents to work alongside humans in existing tools, the platform has the potential to streamline workflows, reduce context switching, and enhance productivity across various use cases, from incident response to code review and customer support.
