chadbyte/clay

A self-hosted workspace where people and coding agents work together across projects, sessions, and providers.

What it solves

Clay Studio provides a self-hosted, shared workspace for managing multiple local coding agents. It eliminates the need to switch between different CLI tools and prevents the loss of context between sessions, allowing teams to collaborate in real-time on the same project using various AI providers.

How it works

Clay Studio runs as a daemon on your local machine, acting as a bridge between your browser and the coding-agent runtimes installed on your system. It detects locally installed agents (such as Claude Code, GitHub Copilot CLI, and others) and exposes them via a web interface. It uses a common session interface called YOKE to maintain continuity across different providers and stores session and project knowledge in portable JSONL and Markdown files on disk.

Who it’s for

Developers and teams who use multiple AI coding agents and want a centralized, persistent, and self-hosted environment to manage their work, collaborate with teammates, and maintain full control over their infrastructure and data.

Highlights

  • Multi-Agent Integration: Supports a wide range of coding agents including Claude Code, Codex, Grok Build, and GitHub Copilot CLI.
  • Real-time Collaboration: Features live sessions with presence, cursors, mentions, and handoffs for human-teammates.
  • Persistent AI Mates: Create AI collaborators with unique identities, instructions, and memory.
  • Cross-Provider Continuity: Maintains project instructions and session context across different AI vendors.
  • Coded-Centric Tools: Integrated file browsing, diff inspection, terminal access, and MCP server connectivity.
  • Self-Hosted Privacy: No project traffic is relayed through a cloud; data stays on your machine except when sent to the model provider.
  • Flexible Deployment: Accessible via desktop browser or PWA on mobile with push notifications for approvals.

Related

  • Project
    qaml-ai/camelAI

    An AI coding assistant that provides persistent workspaces with connected data and the ability to build and deploy applications directly from the chat environment.

  • Project
    openteams-lab/openteams

    A local-first AI desktop app that provides a shared workspace for multiple coding agents to collaborate, plan, and execute tasks without interfering with each other.

  • Project
    Team-Commonly/commonly

    An open-source workspace for collaborating with AI agents from any runtime, providing them with persistent identity and shared project memory to eliminate redundant context-setting.

  • Project
    openagents-org/openagents

    An open-source collaborative OS for AI agents that provides a unified workspace where multiple agents can share threads, files, and a browser to work together.

  • Project
    alookai/alook

    A collaborative platform that gives local AI coding agents persistent identities and shared rooms, allowing teams to interact with them as if they were team members.