# copilotkit/opendots

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/copilotkit-opendots).**

_How this analysis was created: the description and tags below were written by an AI model that read this project's README and public documentation pages; stars, license and language come straight from the GitHub API. The model does not read the source code._

6,461 stars · 949 forks · TypeScript · MIT

## Links

- GitHub: https://github.com/CopilotKit/OpenDots
- Homepage: https://www.copilotkit.ai/opendots
- awesome-repositories: https://awesome-repositories.com/repository/copilotkit-opendots.md

## Description

OpenDots is a platform for hosting long-lived AI agents, called dots, that keep running over time instead of living inside a single short chat. Each agent gets its own sandboxed computer with a browser, files, and a terminal that persist across restarts, with permission checks, an action record, and the option for a human to take over. The same AI coworker carries one conversation across written chat, real-time voice calls, and Slack, and a workspace of shared spaces and nested pages sits alongside it.

People stay in control of what agents do. The chat interface streams agent activity live, with read-only tool calls running automatically and write actions pausing on an approval card until the user approves or declines. Users can watch the agent's computer inside the conversation. Specialist agents can be defined with their own name, role, instructions, and permitted tools, and external tool servers and connected apps can be attached per agent with per-tool toggles. Recurring instructions can run as scheduled background turns on the server, with pause, retry, and review states after failures.

Around that core, the workspace lets users write pages in a visual editor with slash commands and autosave that rejects stale edits, chat with a page's context, and turn approved agent drafts into editable pages. Agents can research public web topics through a read-only browsing service that runs in its own container, and research can be switched off entirely. Voice calls use WebRTC with captions and a timeline of receipts. Conversation history and user preferences are stored in a configured deployment, hosted or local. Usage telemetry can be turned off through environment flags. The app can be run locally with a Node setup and containers, and the AI model provider is set through an API key and model name in environment settings.

## Tags

### Artificial Intelligence & ML

- [Persistent Agent Hosting](https://awesome-repositories.com/f/artificial-intelligence-ml/persistent-agent-hosting.md) — Hosts long-lived AI agents that keep running over time, each on its own dedicated computer rather than in a short chat. ([source](https://github.com/copilotkit/opendots#readme))
- [Agent Computers](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-computers.md) — Provides each agent its own isolated browser, files, and terminal that persist across restarts, with permissions and human takeover. ([source](https://github.com/copilotkit/opendots#readme))
- [Agent Sandboxed Computers](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-sandboxed-computers.md) — Give each assistant its own browser profile, files, and shell, with human takeover, permission checks, and a record of every action taken. ([source](https://github.com/copilotkit/opendots#readme))
- [Human-in-the-Loop Oversight](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agentic-workflows/human-in-the-loop-oversight.md) — Shows a live view of the agent's computer and a review card in the conversation so users can watch and approve actions. ([source](https://github.com/copilotkit/opendots#readme))
- [Tool Execution Approvals](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-action-frameworks/action-approval-gates/tool-execution-approvals.md) — Pauses the conversation on an approval card for write-type tool calls and drafts, continuing only after the user approves or declines. ([source](https://github.com/copilotkit/opendots#readme))
- [Agent Configuration](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-configuration.md) — Defines specialist agents with their own name, role, instructions, and permitted tools so each handles focused work under user control. ([source](https://github.com/copilotkit/opendots#readme))
- [Agent Tool Server Connections](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-tool-server-connections.md) — Attaches external tool servers such as email, calendar, and code hosts to an agent, with per-agent tool toggles and approval for writes. ([source](https://github.com/copilotkit/opendots#readme))
- [Voice Agents](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/conversational-voice-interaction/voice-agents.md) — Offers a continuous chat timeline plus live voice calls with captions and mute controls while a compute agent handles longer tasks. ([source](https://github.com/copilotkit/opendots#readme))
- [Connected App Tools](https://awesome-repositories.com/f/artificial-intelligence-ml/connected-app-tools.md) — Attaches connected apps and external tool servers to each agent with per-tool toggles, requiring owner approval for write actions. ([source](https://github.com/copilotkit/opendots#readme))
- [Conversation Threads](https://awesome-repositories.com/f/artificial-intelligence-ml/language-model-orchestration/conversation-management/conversation-threads.md) — Keeps one persistent conversation thread that follows the user across written chat, voice calls, and Slack.
- [Model Context Protocol Servers](https://awesome-repositories.com/f/artificial-intelligence-ml/model-context-protocol-servers.md) — Attaches external tool servers to each agent over the Model Context Protocol, with per-agent toggles for exposed tools.
- [Specialist Personas](https://awesome-repositories.com/f/artificial-intelligence-ml/persona-management-systems/specialist-personas.md) — Saves named specialist AI coworkers with their own role instructions and per-assistant permissions for research and memory. ([source](https://github.com/copilotkit/opendots#readme))
- [Web Research Agents](https://awesome-repositories.com/f/artificial-intelligence-ml/web-research-agents.md) — Lets agents discover and read up to five public web sources for a topic or extract supplied URLs, saving each source with its link. ([source](https://github.com/copilotkit/opendots#readme))

### Part of an Awesome List

- [Agent Platforms](https://awesome-repositories.com/f/awesome-lists/ai/agent-platforms.md) — Hosts long-lived AI agents that keep running over time, each with its own dedicated computer, memory, and permissions instead of a short chat.

### Development Tools & Productivity

- [Approval Interfaces](https://awesome-repositories.com/f/development-tools-productivity/human-in-the-loop-interfaces/approval-interfaces.md) — Streams agent activity live in chat and shows approval cards before write actions so people stay in control of what agents do.
- [Editor Slash Commands](https://awesome-repositories.com/f/development-tools-productivity/slash-command-interfaces/editor-slash-commands.md) — Provides a visual page editor with slash commands for inserting content blocks, plus autosave that rejects stale edits. ([source](https://github.com/copilotkit/opendots#readme))

### DevOps & Infrastructure

- [Agent Computer Environments](https://awesome-repositories.com/f/devops-infrastructure/agent-computer-environments.md) — Gives each agent an isolated browser, files, and terminal that persist across restarts, with permission checks, action records, and human takeover.

### Networking & Communication

- [Multi-Channel AI Deployments](https://awesome-repositories.com/f/networking-communication/conversational-channel-integrations/multi-channel-ai-deployments.md) — Carries one AI coworker conversation across written chat, real-time voice calls, and Slack so the same agent follows the user between channels.
- [Cross-Channel Agent Conversations](https://awesome-repositories.com/f/networking-communication/slack-integrations/cross-channel-agent-conversations.md) — Carries one AI coworker's conversation between written chat, real-time voice calls, and Slack so the agent follows the user. ([source](https://github.com/copilotkit/opendots#readme))
- [WebRTC Agent Calls](https://awesome-repositories.com/f/networking-communication/real-time-voice-and-video-communication/mesh-voice-calls/webrtc-agent-calls.md) — Handles real-time voice calls over WebRTC with time-bounded sessions, captions, hangup control, and a timeline of receipts. ([source](https://github.com/copilotkit/opendots#readme))
- [Slack Integrations](https://awesome-repositories.com/f/networking-communication/slack-integrations.md) — Connects the agent to Slack workspaces, restricted by workspace and user allowlists, so users can mention it and continue in threads. ([source](https://github.com/copilotkit/opendots#readme))

### Business & Productivity Software

- [Nested Page Libraries](https://awesome-repositories.com/f/business-productivity-software/nested-page-libraries.md) — Stores working documents as nested pages in shared spaces with a searchable library, grid and list views, and stale-edit protection. ([source](https://github.com/copilotkit/opendots#readme))
- [Shared Human-Agent Workspaces](https://awesome-repositories.com/f/business-productivity-software/shared-human-agent-workspaces.md) — Provides shared spaces with nested pages where people organize documents and work alongside specialist AI assistants that research, draft, and edit.
- [Workspace Spaces and Pages](https://awesome-repositories.com/f/business-productivity-software/workspace-spaces-and-pages.md) — Lets users create shared spaces, write nested pages, and configure AI assistants locally in the browser before connecting external services. ([source](https://github.com/copilotkit/opendots#readme))

### User Interface & Experience

- [Agent Interaction Streams](https://awesome-repositories.com/f/user-interface-experience/ui-event-streams/agent-interaction-streams.md) — Streams agent messages, tool calls, and state to the interface so activity and approval cards render inline as work happens.