AgentConnect today announced the release of its open-source platform designed to facilitate collaboration between teams and multiple AI agents within the communication and development tools they already use. This launch addresses a growing challenge in the AI industry: while agents are becoming increasingly capable, their work often remains siloed to individual terminals, leading to fragmented context and duplicated efforts. By integrating agents into existing team conversations, AgentConnect aims to make AI agents more useful and accessible to entire teams.
The platform allows teams to connect ACP-compatible agents such as Claude Code and Codex, assign distinct roles to each agent, and enable collaboration through shared conversations and agent-to-agent calls. This approach moves beyond the traditional model where one person interacts with an agent in isolation, instead fostering a more integrated and efficient workflow. For instance, during incident response, a triage agent can inspect context, a code specialist can trace regressions, and a verification agent can check results, all within the same Slack thread where human teammates can add context and redirect efforts.
AgentConnect's versatility extends to various use cases, including customer support, where issues can transition from a Telegram conversation to a trusted Slack workspace seamlessly. Engineering teams can also benefit by combining general and specialist reviewers for pull requests, with inline GitHub comments and independent check results. Scheduled and webhook-driven tasks can continue in shared conversations when human input is required, ensuring continuity and transparency.
Key features of AgentConnect include the ability to configure multiple agents with distinct models, workspaces, memory, MCP servers, skills, repository access, and sandbox policies. The platform supports integration with Slack, Telegram, and Discord, and can initiate work from conversations, GitHub pull requests, webhooks, or schedules. Fine-grained access control allows administrators to manage agent access separately from session visibility, ensuring security and compliance. Importantly, AgentConnect is open source under the Apache 2.0 license and can be self-hosted via Docker Compose or Kubernetes, giving teams full control over their data and execution environment.
The announcement underscores the importance of collaborative AI in modern workplaces. By enabling agents to work alongside humans in existing tools, AgentConnect reduces context switching and enhances productivity. This is particularly relevant as organizations increasingly adopt AI agents for complex tasks, but struggle with coordination and oversight. AgentConnect's open-source nature also fosters community innovation and transparency, which are critical for building trust in AI systems.
AgentConnect OSS is available today, with the source code and documentation accessible on GitHub and agentconnect.md. The platform's launch is a significant step toward more integrated and team-oriented AI collaboration, potentially setting a precedent for future AI tool development. As AI agents become more prevalent, platforms like AgentConnect will be essential in bridging the gap between individual capabilities and team dynamics.
