Open Dots is an open-source, self-hosted alternative for people exploring paid AI agent products such as OpenAI Dots, Meta Muse, Grok Bot, Instinct, Manus Cue, Claude Cowork, and ChatGPT agent. The current prototype focuses on coding-agent workflows: run Claude Code tasks from Telegram or the web, review risky actions, connect GitHub, and schedule recurring prompts. Its features differ from those services; it is not a feature-for-feature replacement.

Both interfaces use the same API, sandbox, and credentials for each user.

▶ Watch the Open Dots demo on YouTube

Status: Prototype / active development. See Known limitations before running it for others.

• What it does
• Why Open Dots
• Quick start
• Using Open Dots
• Scheduling tasks
• Permission prompts
• Architecture
• Project layout
• Known limitations
• Contributing

• Run coding-agent tasks in disposable sandboxes from Telegram or a browser.
• Connect Claude through its OAuth login flow and optionally connect a user's GitHub account.
• Ask for approval before risky actions such as file writes, shell commands, and Git pushes.
• Continue completed tasks in the same Claude conversation from the web UI.
• Schedule recurring prompts and receive run results in Telegram.
• Store user credentials encrypted and manage sandbox, task, permission, and schedule records in PostgreSQL.

Open Dots gives individuals and developers an inspectable workspace they can run themselves, with coding tasks, visible approval steps, and local control over the app and its data. The web UI supports guest use without Telegram and can also link to a Telegram identity.

• uv for Python dependency management
• Node.js (20.9+) and npm, for the web UI (required by Next.js 16)
• Docker (for Postgres; not needed with the experimental SQLite option, see DATABASE_BACKEND below)
• Bash (Git Bash on Windows works fine) to use scripts/dev.sh
• A Boat API key for sandbox creation. If it belongs to a personal account that also has an org/team on a paid plan, you also need that org's id (see