AgentConnect, a San Francisco-based company, has unveiled its open-source platform designed to enable teams and multiple AI agents to collaborate seamlessly across the communication and development tools they already use. The platform, available under the Apache 2.0 license, addresses the limitations of current AI agent workflows, which often remain isolated to individual terminals and lack team integration.
The new platform allows teams to connect ACP-compatible agents such as Claude Code and Codex, assign distinct roles to each agent, and facilitate collaboration through shared conversations and agent-to-agent calls. This approach moves agents into existing team conversations rather than requiring a dedicated workspace, thereby reducing context fragmentation and streamlining workflows.
One of the key use cases highlighted by AgentConnect is incident response. A team can leverage a triage agent to inspect context, a code specialist to trace regressions, and a verification agent to check proposed results, all within a single Slack thread. Human teammates can add context, redirect tasks, and monitor progress without leaving their communication platform. This model extends to customer support, where issues can transition from a Telegram conversation to a trusted Slack workspace without manual context copying, and to engineering teams that combine general and specialist reviewers for pull requests, with inline GitHub comments and independent check results.
AgentConnect offers several features, including the ability to configure distinct models, workspaces, memory, MCP servers, skills, repository access, and sandbox policies for each agent. It supports integration with Slack, Telegram, and Discord, and can start work from conversations, GitHub pull requests, webhooks, or schedules. Fine-grained access control manages agent access separately from session visibility, allowing teams to control which tools, repositories, and other agents each agent can reach. The platform also supports linking multiple social accounts to a member profile for consistent permission application.
Being open-source and self-hosted, AgentConnect can be deployed with Docker Compose or Kubernetes, ensuring that agent execution and workspaces remain within the team's environment. The platform is now available, and interested parties can explore the source code on GitHub, learn more at agentconnect.md, or read the documentation.
This launch is significant because it addresses a critical gap in AI agent adoption: the lack of team collaboration. By integrating agents into existing communication tools, AgentConnect enables organizations to leverage AI capabilities more effectively, potentially improving incident response times, support efficiency, and code review processes. The open-source nature and self-hosting options also provide flexibility and control for enterprises concerned about data privacy and vendor lock-in.
