AgentConnect today introduced its open-source platform for teams and multiple AI agents to work together across the communication and development tools they already use. The platform aims to address a key limitation of current AI agents: most agent work begins and ends with one person, with sessions in individual terminals and fragmented context. AgentConnect brings agents into existing team conversations, allowing teams to connect Claude Code, Codex, and other ACP-compatible agents, assign distinct roles, and facilitate collaboration through shared conversations and agent-to-agent calls.
“AI agents become much more useful when they can work with the rest of the team, not just one person in one terminal,” the AgentConnect team said. “AgentConnect brings agents with different roles into the conversations where work is already happening.” This approach is exemplified in incident response scenarios, where a triage agent can inspect context, a code specialist can trace a regression, and a verification agent can check results—all while human teammates add context and follow the diagnosis in the same Slack thread.
The platform's utility extends beyond incident response. For instance, a support issue can move from a customer-facing Telegram conversation into a trusted Slack workspace without manual context copying. Engineering teams can combine general and specialist reviewers for pull requests, with inline GitHub comments and independent check results. Scheduled and webhook-driven work can also continue in shared conversations when human input is needed.
AgentConnect includes several key features. It supports multiple agents with distinct models, workspaces, memory, MCP servers, skills, repository access, and sandbox policies. It integrates with existing tools such as Slack, Telegram, and Discord, and can start work from conversations, GitHub pull requests, webhooks, or schedules. Fine-grained access control allows managing agent access separately from session visibility, controlling which tools, repositories, and other agents each agent may reach. The platform is open source under Apache 2.0 and can be self-hosted with Docker Compose or Kubernetes, ensuring agent execution and workspaces remain in the team's environment.
The importance of this announcement lies in its potential to shift AI agent usage from individual, isolated tasks to collaborative, team-oriented workflows. By integrating agents into existing communication platforms, AgentConnect reduces the need for dedicated workspaces and enables more efficient, transparent collaboration between humans and AI. This could significantly impact how teams handle incident response, customer support, and code review, making AI agents more practical and accessible for everyday team operations.
AgentConnect OSS is available today. Teams can explore the source and star the project on GitHub, learn more at agentconnect.md, or read the documentation.
