How to use OpenDots: what you can do with it

3 use cases

• Run your own always-on AI coworker app from a template

  Clone OpenDots, start the dev server, connect Intelligence and a model, and start chatting with a Dot.

  • REPO CopilotKit/OpenDots
  • Work and operations
  • Intermediate
  View prompt

  Set up CopilotKit/OpenDots locally with the local Docker Intelligence evaluation, add my model key from the environment, create one Dot for <role>, and confirm a chat works end to end.

  Share Email me this

• Approve what an agent does before it saves or sends

  Let a Dot browse in its isolated computer and pause on a human review card before acting.

  • REPO CopilotKit/OpenDots
  • Work and operations
  • Intermediate
  View prompt

  In CopilotKit/OpenDots, configure a Dot so every save or send needs my approval, then run <task> and show me the review card flow.

  Share Email me this

• Bring your OpenDots agent into Slack

  Connect Slack through the channels setup so the same agent answers there with shared threads.

  • REPO CopilotKit/OpenDots
  • Work and operations
  • Intermediate
  View prompt

  Following CopilotKit/OpenDots' Setup docs, connect my Slack workspace to a Dot, list the Slack permissions it requests, and test one message round trip.

  Share Email me this

Quick start with OpenDots

1. Check you have what it needs: Node.js 24 and npm; An OpenAI-compatible model key; CopilotKit Intelligence (hosted, local Docker evaluation, or licensed self-hosted).
2. Open CopilotKit/OpenDots on GitHub and read the README and license.
3. git clone https://github.com/CopilotKit/OpenDots.git, then cd OpenDots and npm ci
4. Run cp .env.example .env and npm run dev, then open http://127.0.0.1:5173
5. For hosted Intelligence run npx copilotkit@latest login and npx copilotkit@latest project select
6. Add OPENAI_API_KEY and OPENAI_MODEL to .env and restart; do not run copilotkit onboard in this folder

These steps come from our top use case, Run your own always-on AI coworker app from a template, which also has a copy-paste agent prompt.

Using the Deduped MCP, get the setup steps for CopilotKit/OpenDots

claude mcp add --transport http deduped https://dedupedai.com/mcp

OpenDots alternatives · Best AI repos for Work and operations

About this repo

• Who it is forDevelopers and startups who want to build their own always-on agent product rather than start from scratch.
• Why it is hot6k stars, launched 26 days ago, talked about in 2 AI sources we track
• LanguageTypeScript
• Sourcegithub.com/CopilotKit/OpenDots · Back to Hot repos

Requirements

• Node.js 24 and npm
• An OpenAI-compatible model key
• CopilotKit Intelligence (hosted, local Docker evaluation, or licensed self-hosted)

Related repos

• Trended earlier REPO tangency-labs/solidcraft Solidcraft SolidCraft is an open-source parametric 3D CAD application written in pure Rust, with desktop, browser, headless CLI and MCP server versions.
• Trended earlier REPO googleworkspace/cli Google Workspace CLI gws is one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin and every other Google Workspace API, built for people and AI agents. It builds its commands at runtime from Google's Discovery Service, returns structured JSON, adds helper commands such as +send, +triage and +agenda, and ships 100+ agent skills. The README notes it is not an officially supported Google product and expects breaking changes before v1.0.
• Trended earlier REPO langgenius/dify Dify Dify is an open-source platform for building LLM apps. It combines a visual workflow canvas, a RAG pipeline that ingests PDFs and slides, agents with their own sandbox, support for hundreds of models, a prompt IDE, observability and a backend-as-a-service API, so a team can go from prototype to production in one workspace. It runs in Dify Cloud or self-hosted with Docker Compose.