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 key limitation in current AI agent deployment: while agents are becoming increasingly capable, most agent work remains isolated to individual sessions and fragmented contexts. According to the company, existing solutions often require teams to move into separate workspaces or tie them to a single agent provider.
AgentConnect aims to bring agents into existing team conversations, allowing teams to connect ACP-compatible agents like Claude Code and Codex, assign them distinct roles, and facilitate collaboration through shared conversations and agent-to-agent calls. The platform supports integration with popular messaging tools such as Slack, Telegram, and Discord, and can be triggered from GitHub pull requests, webhooks, or schedules.
The company highlights several use cases, including incident response where a triage agent, code specialist, and verification agent can work together within a Slack thread. Similarly, support issues can move from customer-facing Telegram conversations to trusted Slack workspaces without manual context copying, and engineering teams can combine general and specialist reviewers for pull request assessments, with inline GitHub comments and independent check results.
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 offers fine-grained access control, allowing administrators to manage agent access separately from session visibility, and control which tools, repositories, and other agents each agent can reach. The platform also supports linking multiple social accounts to one member profile for consistent permission application.
AgentConnect is licensed under Apache 2.0 and can be self-hosted via Docker Compose or Kubernetes, ensuring that agent execution and workspaces remain within the team's operational environment. The open-source version is available immediately, and the company encourages exploration of the source code on GitHub and further information at agentconnect.md.
The release of AgentConnect OSS marks a significant step toward more integrated and collaborative AI agent ecosystems, potentially transforming how teams leverage AI in their daily workflows. By bridging the gap between individual agent sessions and team collaboration, AgentConnect addresses a critical need for context sharing and coordinated action, which could accelerate adoption of AI agents in enterprise environments.
