awesome-repositories.com
Blog
MCP
awesome-repositories.com

Discover the best open-source repositories with AI-powered search.

ExploreCurated searchesOpen-source alternativesSelf-hosted softwareBlogSitemap
ProjectMCP serverAboutHow we rankPress
LegalPrivacyTerms
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
sandbox-quantum avatar

sandbox-quantum/switch

0
View on GitHub↗
www.switchagents.ai↗

Switch

Switch is a self-hosted platform where people and AI agents share chat rooms. Agents built on different coding-agent harnesses, models or providers can join a room as teammates, and the system runs and coordinates their sessions on a laptop, over SSH, or on remote machines. Rooms can be bridged to channels on Slack, Microsoft Teams, Discord, Telegram and Mattermost, so teammates address agents in the tools they already use.

Agent sessions are launched through native SDK or protocol adapters, with providers such as Claude Code, Codex, Cursor and OpenCode driven through one shared session interface. An MCP server gives every session room tools for reading, posting and coordinating, and agents can be started on a schedule or automatically when someone addresses them. Governance is built in: administrators control who can message which agent and in which rooms, each agent sees only the rooms it has joined, and messages (including text extracted from attachments) are screened and blocked or redacted before delivery. Workspace isolation is enforced in the database, and messages are routed through ordered PostgreSQL rows.

Beyond the core, the project provides a web dashboard and desktop app for managing agents, rooms, users and workspaces. It also offers reusable room templates, external references attached to rooms, connections to services such as GitHub, Google Workspace and Atlassian, message retention and erasure controls, and health and activity monitoring. The repository also contains load-testing tooling for measuring chat capacity. The server can be deployed with Docker or Helm.

Features

  • Coding Agent Orchestrators - Coordinates coding agents from different harnesses and models, managing their sessions and routing work whether they run on a laptop, remote host or server.
  • AI Coding Agent Platforms - Provides a self-hosted platform where people and AI coding agents share chat rooms and agents join as teammates.
  • Agent Chat Platform Bridges - Bridges rooms to Slack, Teams, Discord, Telegram and Mattermost channels so people and agents talk in familiar tools, including multi-file attachments.
  • Agent Harnesses - Launches each agent session through native SDK or protocol adapters, driving harnesses like Claude Code, Codex, Cursor and OpenCode via one interface.

AI search

Explore more awesome repositories

Describe what you need in plain English — the AI ranks thousands of curated open-source projects by relevance.

Start searching with AI
4,232 stars·329 forks·Python·1 view
  • Human-Agent Chat Channels - Brings AI agents into Slack, Teams, Discord, Telegram and Mattermost channels so people and agents share one conversation, decisions and documents.
  • Agent Governance - Governs who can message which agent and in which rooms, screens messages for policy violations and tracks usage for organizational oversight.
  • Harness Adapter Contracts - Launches each agent session through a native SDK or protocol adapter so different coding-agent harnesses share one session interface.
  • Harness-Agnostic Agent Participation - Allows agents from any harness, model or provider to join a room as teammates, on a laptop or a server.
  • MCP Tool Servers - Runs an MCP server that gives every agent session tools for reading, posting and coordinating in shared rooms.
  • PostgreSQL Message Buses - Stores messages as ordered PostgreSQL rows and routes each to its addressed agents in the same transaction, using commit notifications to wake listeners.
  • Message Routing Pipelines - Uses PostgreSQL as the internal message bus, storing ordered messages and routing them to addressees without a separate queueing system.
  • Self-Hosted Agent Servers - Runs the whole agent platform on your own servers so team context stays in-house and agents or models can be swapped freely.
  • Policy Violation Blocking - Screens every message before delivery, blocking or redacting content that violates policy, notifying senders and letting admins tune the rules.
  • Agent Access Controls - Lets administrators decide who can message which agent and in which rooms, enforcing permissions for AI agents.
  • Recurring Agent Scheduling - Starts and drives agent sessions on a defined schedule so background work proceeds without anyone launching sessions by hand.
  • Agent Fleet Monitoring Dashboards - Offers a management API and web dashboard so operators can oversee agents, rooms and platform resources.
  • Agent Management Consoles - Provides a desktop console with guided onboarding, agent and room lists, inline chat, and a local control interface for managing agents programmatically.
  • Agent Onboarding Endpoints - Registers external AI agents with a backend service so they can be managed centrally and connected to team chat tools.
  • Agent Provider Integrations - Runs several coding-agent providers as agents with per-agent model, reasoning, instructions and provider login settings that remain editable.
  • Agentic Workflow Automation - Lets agents triage bug and feature requests, reproduce issues, file tickets, build fixes and deploy changes across linked channels.
  • Coding Agent Integrations - Connects Claude Code, Codex, OpenCode, Antigravity and Cursor backends and drives them all through one shared session interface.
  • Session-Based Agent Managers - Shows all local coding-agent sessions in one desktop app with each agent's rooms, working directory, identity and scheduling configuration.
  • Local-First Agent Controllers - Provides a desktop app and local control interface that manage agent sessions on the user's machine, with controllers reaching SSH and remote hosts.
  • Agent and Room Administration Dashboards - Offers a web dashboard to create and administer rooms, AI agents and user accounts without editing configuration by hand.
  • Agent Memberships - Adds AI agents to chat rooms as members alongside people, controlling which rooms each agent joins and sees.
  • Room Templates - Packages rooms with channels, agents and references into templates that people or agents can publish, search and run to create new rooms.
  • Data Tenant Isolators - Enforces workspace separation inside the database so each workspace sees only its own records, even if application code fails.
  • On-Demand Agent Session Starts - Starts an agent session automatically when someone addresses an agent in chat that has no live session running.
  • Remote Run Controllers - Enrolls local, SSH or cloud machines with a controller that runs managed agents, supports sleep and wake, and installs as a service.
  • Workspace Member Management - Supports multiple workspaces per person with sign-up, invitations, roles and usage budgets, with tenant isolation enforced in the database.
  • Reliable Message Delivery - Stores each message in an ordered Postgres table, wakes listeners on commit and routes to addressed agents in one transaction.
  • Remote Agent Session Hosting - Runs agent sessions on SSH hosts or remote machines through the same persistent host used locally, so work continues while the laptop sleeps.
  • Self-Hosted Agent Management Dashboards - Provides a web dashboard and desktop app for creating and administering agents, rooms, users and workspaces on your own infrastructure.
  • Self-Hosted Workspace Deployments - Ships Docker, Helm and local-server deployment of the full team workspace with a single address, feature flags and an SMTP relay.
  • Multi-Bot Team Chats - Lets people ask agents questions in a bridged team chat room where they already work, with access limited to chosen users.
  • Access-Controlled Rooms - Controls which people can talk to which agent in which rooms, and limits each agent to seeing only the rooms it has joined.
  • Membership Management - Handles room creation, YAML-based configuration, and participant membership so humans and agents collaborate in structured rooms.
  • Room Templates - Offers preconfigured room layouts bundling channels and agents so new workspaces start with a working setup.
  • Message Sending Policies - Screens every outgoing and incoming message, including text extracted from attachments, and blocks or redacts content before delivery.
  • Agent Role and Tool Configurations - Assigns each agent a role, instructions and connected tools such as Google Workspace, Jira or GitHub, limited to its rooms.
  • Session Message Redactions - Screens outgoing and incoming messages, including text extracted from attached documents and PDFs, redacting or blocking content and telling the sender what changed.

    • Star history

    Star history chart for sandbox-quantum/switchStar history chart for sandbox-quantum/switch

    How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.

    Projects sharing features with Switch

    These projects share indexed features with Switch. Shared tags can include platform or build tooling; verify the primary use case before treating a result as a replacement.
    • omnigent-ai/omnigentomnigent-ai avatar

      omnigent-ai/omnigent

      11,273View on GitHub↗

      Omnigent is a policy-governed orchestrator for coding agents. It runs several agent harnesses, such as Claude Code and Codex, together in one session, and a single harness identifier decides which agent handles a session, so teams can swap agents without rewriting their definitions. Sub-agents can each use their own harness, model, prompt, and sandbox inheritance, which lets one agent review another's work or split a task with it. Every agent action passes through layered policies set at the server, agent, and session levels. Each policy function allows, denies, or abstains, and a denial stop

      Pythonagent-frameworkagent-governanceagent-orchestration
      View on GitHub↗11,273
    • cursor/cookbookcursor avatar

      cursor/cookbook

      4,158View on GitHub↗

      This repository is a collection of example projects and guides for building with Cursor's coding agents. The samples cover running agents from TypeScript code against local workspaces or cloud runtimes, streaming their output live, and launching them from a terminal. Other examples include a cloud agent kanban dashboard, a task graph orchestrator, an app-prototyping chat, and a realtime voice intake demo. Several samples go beyond a basic quickstart. The kanban dashboard lists cloud agents as cards grouped by status, repository, or branch, previews their artifacts, and launches new agents fro

      TypeScript
      View on GitHub↗4,158
    • opactorai/claudableopactorai avatar

      opactorai/Claudable

      4,055View on GitHub↗

      Claudable is an AI-driven integrated development environment and full-stack application builder. It functions as a code generation platform that transforms text descriptions into functional source code and user interface components using large language models and command-line artificial intelligence agents. The system integrates a cloud deployment pipeline that synchronizes local changes with remote repositories and publishes applications to live hosting environments. It further distinguishes itself by combining these automation workflows with a single interface for managing the entire develo

      TypeScriptagentclaudeclaude-code
      View on GitHub↗4,055
    • ekkolearnai/ekko-studioEKKOLearnAI avatar

      EKKOLearnAI/ekko-studio

      11,715View on GitHub↗

      Ekko Studio is a self-hosted AI agent workspace that runs several agents together in shared chats and keeps sessions and data on the user's own machine. It streams replies, tool traces, and generated-file previews across persistent sessions, and it hosts group rooms where multiple agents answer when mentioned. It also detects, installs, configures, and launches third-party command-line coding agents from one interface, with built-in terminals, session history, a workspace picker, and file diffs. Beyond chat, the workspace includes a visual canvas for building runnable agent workflows with con

      TypeScriptagentai-agentchat-ui
      View on GitHub↗11,715
    Compare all 30 related projects→

    Frequently asked questions

    What does sandbox-quantum/switch do?

    Switch is a self-hosted platform where people and AI agents share chat rooms. Agents built on different coding-agent harnesses, models or providers can join a room as teammates, and the system runs and coordinates their sessions on a laptop, over SSH, or on remote machines. Rooms can be bridged to channels on Slack, Microsoft Teams, Discord, Telegram and Mattermost, so teammates address agents in the tools they already use.

    What are the main features of sandbox-quantum/switch?

    The main features of sandbox-quantum/switch are: Coding Agent Orchestrators, AI Coding Agent Platforms, Agent Chat Platform Bridges, Agent Harnesses, Human-Agent Chat Channels, Agent Governance, Harness Adapter Contracts, Harness-Agnostic Agent Participation.

    Which projects share features with sandbox-quantum/switch?

    Projects with overlapping indexed features include: omnigent-ai/omnigent — Omnigent is a policy-governed orchestrator for coding agents. It runs several agent harnesses, such as Claude Code and… cursor/cookbook — This repository is a collection of example projects and guides for building with Cursor's coding agents. The samples… opactorai/claudable — Claudable is an AI-driven integrated development environment and full-stack application builder. It functions as a… ekkolearnai/ekko-studio — Ekko Studio is a self-hosted AI agent workspace that runs several agents together in shared chats and keeps sessions… harnessrouter/harnessrouter — HarnessRouter is a self-hosted gateway that routes coding-agent tasks to interchangeable agent harnesses through a… builderz-labs/mission-control — Mission Control is a self-hosted web dashboard that acts as a control plane for autonomous AI coding agents. It lets…