AgentConnect today announced the launch of its open-source platform designed to enable teams and multiple AI agents to work together across the communication and development tools they already use. The platform aims to address a common limitation in current AI agent workflows, where sessions are isolated to individual terminals and context remains fragmented, hindering effective team collaboration.
According to the company, AI agents have become increasingly capable, but most agent work still begins and ends with one person. Existing solutions that add a team layer often require moving work into a separate dedicated workspace or tie users to a single agent provider. AgentConnect seeks to change this by bringing agents directly into existing team conversations, allowing teams to connect Claude Code, Codex, and other ACP-compatible agents, assign each a distinct role, 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.”
The platform's practical applications are broad. For incident response, a team can deploy a triage agent to inspect context, a code specialist to trace a suspected regression, and a verification agent to check proposed results, all within the same Slack thread where human teammates can add context and follow the process. Similarly, support issues can transition from a customer-facing Telegram conversation to 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 per team, allowing configuration of distinct models, workspaces, memory, MCP servers, skills, repository access, and sandbox policies for each agent. The platform integrates with Slack, Telegram, and Discord, and can initiate work from conversations, GitHub pull requests, webhooks, or schedules, enabling seamless workflow across trusted messaging workspaces. Fine-grained access control is another highlight, letting administrators manage agent access separately from session visibility, control which tools, repositories, and other agents each agent can reach, and link multiple social accounts to one member profile for consistent permission application.
Being open source under the Apache 2.0 license, AgentConnect can be self-hosted using Docker Compose or Kubernetes, ensuring that agent execution and workspaces remain within the team's own environment. This addresses concerns about data privacy and control, which are critical for many enterprises.
The launch of AgentConnect has significant implications for the industry. By integrating AI agents into existing team collaboration tools, it lowers the barrier to adopting multi-agent workflows. Teams can now leverage specialized agents without disrupting their current communication habits, potentially increasing productivity and reducing context switching. For business and technology leaders, this platform offers a way to scale AI usage across teams while maintaining governance through fine-grained access control. The open-source nature also allows organizations to customize and extend the platform to fit their specific needs, fostering innovation and community-driven development.
AgentConnect OSS is available today. The source code can be explored and the project starred on GitHub, and more information is available at agentconnect.md or in the documentation. As AI agents become more integral to business operations, platforms like AgentConnect could redefine how teams collaborate with AI, making multi-agent workflows a standard practice.
