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 already in use. The platform addresses a common limitation in current AI agent deployments, where work often remains isolated to individual terminals and fragmented contexts, requiring custom integrations for each new workflow.
The new platform, AgentConnect OSS, allows teams to connect ACP-compatible agents such as Claude Code and Codex, assign distinct roles to each, and enable collaborative interactions through shared conversations and agent-to-agent calls. This integration brings agents into existing team conversations on platforms like Slack, Telegram, and Discord, rather than forcing users into a separate workspace.
According to the AgentConnect team, "AI agents become much more useful when they can work with the rest of the team, not just one person in one terminal. 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 regressions, and a verification agent can check results, all within the same Slack thread, with human teammates providing input and oversight.
The platform's versatility extends to support issues, enabling seamless transitions from customer-facing Telegram conversations to trusted Slack workspaces without manual context copying. Engineering teams can combine general and specialist reviewers for pull request risk assessment, with inline GitHub comments and independent check results. Additionally, scheduled and webhook-driven work can be managed in shared conversations when human intervention is required.
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 and allows work to be initiated from conversations, GitHub pull requests, webhooks, or schedules. Fine-grained access control manages agent permissions separately from session visibility, and multiple social accounts can be linked to a single member profile for consistent permissions.
AgentConnect is licensed under Apache 2.0 and can be self-hosted via Docker Compose or Kubernetes, ensuring agent execution and workspaces remain within the team's environment. The open-source nature of the platform is a significant step toward democratizing multi-agent collaboration, as it allows organizations to customize and deploy the system according to their specific needs.
The release of AgentConnect OSS marks a notable advancement in the field of AI collaboration, offering a flexible and integrated solution that could redefine how teams leverage AI agents in their daily operations. By bridging the gap between human teams and AI agents, AgentConnect aims to enhance productivity and streamline workflows across various industries.
For those interested in exploring the platform, the source code is available on GitHub, with additional information at agentconnect.md and comprehensive documentation provided for implementation.


