open-dots
Open-source, self-hosted AI agent workspace and alternative to OpenAI Dots, Meta Muse, Grok Bot, Instinct, Manus Cue, Claude Cowork, and ChatGPT agent. MIT-licensed; includes chat, connectors, approvals, and optional computer use. Early prototype.
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Check it deeper on your machine
It has changed since its scan on 11 Nov 2026.
As a Claude Code plugin, install it and then ask Claude Code:
/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/Anil-matcha/suparagent with scanskillsafety
Or from a terminal, clone it and run it:
git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/Anil-matcha/suparagent'
It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.
Badge for your README
Markdown
[](/listings/anil-matcha--open-dots)HTML
<a href="/listings/anil-matcha--open-dots"><img src="/api/listings/anil-matcha--open-dots/badge.svg" alt="findsafeskills safety rating" /></a>Install
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
Requirements
- Node.js and npm - Python 3.10+ and pip - An inference API key and base URL for live model responses
Clone and start the API:
git clone https://github.com/Anil-matcha/open-dots.git cd open-dots/server python -m venv .venv source .venv/bin/activate python -m pip install -r requirements.txt export MODEL_API_KEY="your_api_key" export MODEL_API_BASE_URL="https://your-inference-host.example/api/v1" python run.py
The API is available at `http://127.0.0.1:8000`; interactive docs are at `/docs`.
In a second terminal, start the web client:
cd open-dots/client npm install npm run dev
Open `http://127.0.0.1:3000` and sign in with the Open Dots owner token. On first start, the server creates `.auth-token` under `DATA_DIR` (default `~/.open-dots`). Read that file locally and paste its value into the sign-in form, or use the value of `APP_AUTH_TOKEN` if you configured one. This is a separate credential from your model provider API key, which you enter in App Settings after signing in. Never commit, share, or put the owner token in a public frontend environment variable.
Browser sessions use distinct HttpOnly cookies with server-enforced expiry. Sign out revokes the current session, and restarting the API invalidates all browser sessions. Direct API clients can continue to send the owner token as a Bearer credential. Loopback requests, including container gateway and reverse-proxy traffic, must authenticate too.
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
README.md · README · 268 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.
- # Suparagent
- **A workspace for AI coworkers.**
- Create named agents, give each a job and workspace, and bring them together to
- complete real tasks. Suparagent keeps conversations, memory, routines, and
- approvals in one place. Use the desktop app or host the server yourself; the
- hosted service is a separate product.
- Bring your own engine and provider account. Suparagent does not include a model
- or model subscription.
- **[Desktop downloads](https://github.com/Anil-matcha/suparagent/releases) · [Self-hosting](docs/SELF-HOSTING.md) · [Hosted app](https://suparagent.ai) · [Watch the demo](https://youtu.be/vtFy94DfETE) · [Discord](https://discord.com/invite/zpnuBRXhKg)**
- <p align="center"><a href="https://youtu.be/vtFy94DfETE"><img src="https://i.ytimg.com/vi/vtFy94DfETE/maxresdefault.jpg" width="720"></a></p>
- <p align="center"><a href="https://youtu.be/vtFy94DfETE"><b>▶ Watch: Free Unlimited Grok Bot Alternative: Open-Source, Any Model, No Restrictions </b></a></p>
- > **Status:** Suparagent is in active development. Desktop releases, self-hosting,
- > agent computers, and newer team features are still evolving. Review
- > [known limitations](#known-limitations) before relying on them for important work.
- ## Contents
- - [Quick start](#quick-start)
- - [What you can do](#what-you-can-do)
- - [Ways to run Suparagent](#ways-to-run-suparagent)
- - [Hosted plans](#hosted-plans)
- - [Engines, data, and costs](#engines-data-and-costs)
- - [Example: prepare a weekly project briefing](#example-prepare-a-weekly-project-briefing)
- - [Scheduling tasks](#scheduling-tasks)
- - [Known limitations](#known-limitations)
- - [Guides](#guides)
- - [Support](#support)
- - [Contributing](#contributing)
- - [License](#license)
- ## Quick start
- The desktop app runs from a source checkout. It needs Node.js 22 or newer,
- [uv](https://docs.astral.sh/uv/), and at least one engine available on the
- same computer. For a CLI engine, install it and sign in before opening Open
- Duet. You can also configure an API-based engine in **Settings → Engines**.
- Docker is only needed for the optional isolated agent computers.
- ```bash
- git clone https://github.com/Anil-matcha/suparagent.git
- cd suparagent/desktop
- npm run app
- ```
- On first launch, choose an engine, workspace, and approval mode. Then:
- 1. Open **Settings → Engines** and confirm an engine is ready.
- 2. Create an agent with a name, a clear job, and a workspace.
- 3. Start a chat. Choose **Ask first** to pause for approval before actions that
- need it.
- 4. Add teammates or create a routine when you want to split up or repeat work.
- See the [Releases page](https://github.com/Anil-matcha/suparagent/releases) for
- current desktop installers and the [changelog](CHANGELOG.md) for changes.
- Installers are experimental and unsigned. The assisted update flow offers a
- SHA-256-verified installer for you to open; it does not install updates
- automatically. The release-to-release update path has not been verified end to
- end.
- ## What you can do
- <p align="center"><img src="docs/suparagent-workflow.svg" alt="A request goes to a Claude or Codex team lead, who delegates work to specialists. Teammates can share a project folder, and you review actions when approval is required." width="100%"></p>
- - **Create agents and teams.** Start with **Create by chatting** to ask your
- team lead (Chief of Staff) to propose specialists around a goal. Review and
- edit the plan card, then approve it to apply setup. Each new specialist gets
- an editable first-task draft that is not sent automatically. New specialists
- start with Ask-first permissions; app access and credentials stay under your control. Create
- agents manually with a name, role, engine, workspace, memory, and approval
- settings. A lead can delegate work to specialists or coordinate agents in
- shared rooms. Team leads can use Claude or Codex. See
- [managing agents through chat](docs/CHAT_MANAGEMENT.md)
- and [teams and delegated work](docs/TEAMS.md).
- - **Keep useful context.** Agents can save notes, recall relevant notes and
- conversations, and search their history. You can review and edit what they
- remember. See [memory](docs/MEMORY.md).
- - **Run work on a schedule.** Create routines for scheduled, webhook, or manual
- runs. Review each result and answer requests for approval; a routine never
- approves an action by itself. See [routines](docs/ROUTINES.md).
- - **Choose how much freedom agents have.** Use Ask first, Accept edits, Approve
- for me (Claude, Codex, and Cursor), or Plan only. Review tool activity and approval
- decisions in the app.
- - **Connect tools and apps.** Connect services such as GitHub, Gmail, and Google
- Calendar through your own Composio key, then grant access to selected Claude
- or Codex agents. Changes wait for your approval. Add individual tools from
- the MCP Marketplace. The MuAPI listing includes selected data research tools:
- search APIs, estimate USD cost, and make a lookup with a per-call cost cap.
- Paid calls use MuAPI credits and require approval. See
- [connected apps](docs/CONNECTED_APPS.md).
- - **See what needs your attention.** The Today view gathers approvals,
- questions, routine outcomes, engine failures, and due tasks. It can show
- read-only Gmail and calendar items. See [everyday features](docs/EVERYDAY.md).
- - **Plan and follow work.** Use a task board and calendar to assign work,
- schedule one-time runs, and review conversations and attempts. See
- [tasks and calendar](docs/TASKS.md).
- - **Reuse instructions.** Save skills and start agents from templates. Skills
- are instructions you choose for a message. See [skills](docs/SKILLS.md) and
- [templates](docs/TEMPLATES.md).
- - **Use it from your phone.** Pair the phone app with your own server to chat,
- stop an answer, allow or deny a tool call, or create and edit agents and rooms.
- See the [phone app guide](docs/MOBILE.md).
- - **Work with files and history.** Search conversations, attach text and
- images, import audio for transcription with your consent and credentials,
- browse or download workspace files, and export your history.
- ## Ways to run Suparagent
- | | Desktop app | Self-hosted server | Hosted web app | Development checkout |
- |---|---|---|---|---|
- | Best for | A personal workspace on your computer | Keeping your agents and routines available on a server you control | Using the separately operated Suparagent service | Contributing or changing Suparagent |
- | Where workspace data lives | Your computer | Your server | An account-specific hosted workspace | Your development machine or configured database |
- | Start here | [Quick start](#quick-start) | [Self-hosting guide](docs/SELF-HOSTING.md) | [suparagent.ai](https://suparagent.ai) | [Development setup](docs/SETUP.md) |
- | Main requirements | Node.js 22+, uv, and an engine | Linux server, HTTPS, Docker or Node.js and uv, and an engine | An account and an AI provider account | Node.js, uv, and Docker if you use PostgreSQL |
- | Status | Experimental | Experimental; one owner who can invite teammates | Separate hosted product | — |
- The hosted service is separate from the open-source desktop and self-hosted
- core. Hosted account, workspace, and billing data are handled by Suparagent;
- see the hosted service's [Privacy Policy](https://suparagent.ai/privacy) and
- [Terms](https://suparagent.ai/terms).
- ## Hosted plans
- The hosted preview lets you use your own Boat key for sandbox compute. Paid
- plans use compute operated by Suparagent, so you do not need to supply a Boat
- key. In both cases, you bring your AI provider account and pay that provider
- for model usage.
- | Plan | Monthly Suparagent price | Included running compute | Machine disk capacity |
- |---|---:|---:|---:|
- | Free preview | $0 | Billed to your Boat account | Small profile |
- | Starter | $15 | 100 hours per billing period | 51 GB |
- | Standard | $49 | 300 hours per billing period | 51 GB |
- | Pro | $99 | 720 hours per billing period | 111 GB |
- Paid-plan compute hours count while the sandbox is running, including idle
- time. At the limit, it stops until the next billing period or a plan change;
- compute overages are not charged. The disk value is the selected machine's
- capacity, not a separate storage quota. A stopped sandbox's disk is subject to
- the provider's retention period, so export important files before a paid plan
- ends. Paid checkout is enabled for hosted accounts; see the
- [Suparagent pricing page](https://suparagent.ai/pricing/) for current plans.
- ## Engines, data, and costs
- Connect an engine you already use: Claude Code or Codex CLI, Gemini CLI,
- Google Gemini through Antigravity, Cursor, another command-line agent using
- the Agent Client Protocol (ACP), OpenRouter, or an OpenAI-compatible API such
- as Ollama or LM Studio. Available tools vary by engine; image input and agent
- computers, for example, are not supported by every engine. See
- [engine setup and capabilities](docs/ENGINES.md).
- For desktop and self-hosted use, conversations, agent notes, routines, and
- settings are stored in that instance's local data folder or server database.
- Workspace files stay in the folders you assign to agents. API keys saved
- through Suparagent are encrypted there; command-line sign-ins remain with the
- engine installed on that machine.
- When an agent answers, the selected engine receives the prompt and the context
- needed for that turn. This can include text you attach, relevant notes, and
- workspace content the engine reads. If the engine is a hosted service, that
- information is handled under that provider's terms. You bring the provider
- account, CLI sign-in, or API key; model usage may cost money.
- ## Example: prepare a weekly project briefing
- Create a lead agent and specialists, such as a researcher and an editor. Give
- them the same project workspace, and set the lead's engine to Claude or
- Codex. Ask the lead to prepare a briefing from the notes and reports in that
- folder.
- The lead can split the request into smaller tasks and hand them to the
- specialists. Their work runs in separate conversations, then returns to the
- lead to assemble. Follow along in chat and approve actions when the settings
- require it. Once the process works well, make it a weekly routine and review
- each run in the app.
- ## Scheduling tasks
- Routines run prompts on local agents on a schedule, by webhook, or on demand.
- They run in the backend, so the backend must stay running. The original
- Telegram bot and [Boat](https://docs.boat.dev/api-keys) sandbox task flow are
- optional and separate from the agent workspace. See [backend scheduling
- details](backend/README.md#scheduling) and [environment settings](backend/.env.example).
- ## Known limitations
- - Suparagent is early and changing. The self-hosted server is experimental. One
- person owns it and can invite teammates to work in the same workspace, with
- roles and per-person permissions; everyone shares the same agents,
- conversations and memory. A self-hosted server is not a multi-organization
- service and has no workspaces to switch between; a hosted deployment can run
- several behind an account service (see
- [docs/AUTH.md](docs/AUTH.md#hosted-workspace-grants)).
- - Team delegation is new; lead agents need to use Claude or Codex.
- - The phone app has been tried on an Android emulator and an Android phone, not
- on iOS. It has no push notifications or store release.
- - Docker computers, browser tools, and the macOS native desktop preview are
- experimental and opt-in.
- - Desktop installers are unsigned and have limited platform verification. See
- [desktop setup details](docs/SETUP.md#desktop-app-from-a-source-checkout-experimental).
- - Connected apps are reached through Composio and tested against a fake
- Composio service, not yet the real service. Only Claude and Codex agents can
- use them, and changes wait for your approval.
- - The MCP Marketplace, hosted cloud computers, quiet routine results, and
- audio transcription have not had live-service or packaged-app qualification.
- ## Guides
- **Getting started**
- - [First-run setup and approvals](docs/SETUP.md)
- - [Engines and models](docs/ENGINES.md)
- - [Self-hosting](docs/SELF-HOSTING.md)
- **Agents and work**
- - [Teams and delegated work](docs/TEAMS.md)
- - [Agent settings and chat management](docs/CHAT_MANAGEMENT.md)
- - [Memory and context](docs/MEMORY.md)
- - [Routines](docs/ROUTINES.md)
- - [Tasks and calendar](docs/TASKS.md)
- - [Everyday features](docs/EVERYDAY.md): search, attachments, audio, and Today
- **Tools and customization**
- - [Connected apps](docs/CONNECTED_APPS.md)
- - [App language settings](docs/LOCALIZATION.md)
- - [Skills](docs/SKILLS.md) and [templates](docs/TEMPLATES.md)
- - [Agent computers](docs/COMPUTERS.md), [native desktop](docs/NATIVE-DESKTOP.md),
- and [browser tools](docs/BROWSER.md)
- - [Features](docs/FEATURES.md) and [capability matrix](docs/CAPABILITIES.md)
- **Project**
- - [Roadmap](docs/ROADMAP.md)
- - [Changelog](CHANGELOG.md)
- - [Phone app](docs/MOBILE.md)
- - [Contributing](docs/CONTRIBUTING.md)
- ## Support
- - Join the [Suparagent Discord community](https://discord.com/invite/zpnuBRXhKg)
- for questions and discussion.
- - Report bugs and request features in [GitHub Issues](https://github.com/Anil-matcha/suparagent/issues).
- - For hosted account or billing questions, use the contact link on
- [suparagent.ai](https://suparagent.ai/contact/).
- ## Contributing
- Issues and pull requests are welcome. Start with the
- [contributing guide](docs/CONTRIBUTING.md).
- To propose a third-party app for the in-app MCP Marketplace, add a Community
- manifest under `marketplace/plugins/community/`, regenerate
- `marketplace/catalog.json`, and submit both in a pull request. See the
- [MCP Marketplace submission guide](marketplace/plugins/README.md) for the
- manifest requirements and validation steps.
- ## License
- Suparagent is licensed under the [Apache License 2.0](LICENSE).
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.