{"slug": "claude-but-open-source-one-workplace-not-five-tools-that-hate-eachother", "title": "Claude but Open-Source –> One workplace. Not five tools that hate eachother", "summary": "MindsDB has launched MindsHub Cowork, an open-source unified workspace that lets users delegate entire projects—apps, websites, research, analysis, and scheduled operations—to AI agents using any open or proprietary model. The platform includes a model router, connected data vault, memory, skills, and scheduling, and runs locally or in the cloud.", "body_md": "**The unified workspace where open-source models get things done for you.**\n\n*Make AI do actual work. Swap the model anytime — keep everything you've built.*\n\n**MindsHub Cowork** is the unified workspace where you delegate entire projects — apps, websites, research, analysis, reporting, scheduled operations — and collect finished, shareable results. Connect your data, route work to any model (open or proprietary), run open-source agents, and turn their output into web applications you can publish. It's open source and runs anywhere — your machine, your VPC, or the hosted app.\n\nThis repository is the **platform superproject**: it pulls together the desktop/web app, the agent backend, and the data engine so you can build and run the whole stack from source.\n\nPick whichever fits:\n\n**Web — nothing to install.** Openand sign in.[console.mindshub.ai](https://console.mindshub.ai/?utm_source=github&utm_medium=repo-readme&utm_campaign=minds-readme)**macOS.**[Download the desktop app](https://downloads.mindsdb.com/mindshub-cowork/mac/mindshub-cowork-latest.pkg)(`.pkg`\n\n).**Windows.**[Download the desktop app](https://downloads.mindsdb.com/mindshub-cowork/windows/mindshub-cowork-latest.exe)(`.exe`\n\n).**Linux.**[Build from source](#build-from-source).\n\nFree to start. Pro adds all frontier models and private artifacts — see [pricing](https://mindshub.ai/pricing?utm_source=github&utm_medium=repo-readme&utm_campaign=minds-readme).\n\nFor every knowledge worker — creators, strategists, and operators:\n\n**Automate** repetitive, multi-step work that involves reading and writing: reports, monitoring, recurring workflows, and scheduled operations.**Build** internal AI tools and artifacts — apps, dashboards, decks, docs, analyses — without engineering, and publish them to a live URL to share with your team.\n\n**Connected data.** A secure vault links systems like BigQuery, Postgres, Gmail, Drive, HubSpot, Notion, and Linear. Credentials stay scoped per connection — agents never see raw keys.**Model Router.** Switch between frontier models (Claude, GPT, Gemini) and open models (DeepSeek, Qwen, Kimi) without wiring up a key for each provider.**Open agents.** Run interchangeable open-source harnesses — Anton (default) and Hermes — swappable from a dropdown.**Artifacts.** Turn agent output into documents, dashboards, apps, and code, and publish to a live URL.**Memory, skills & scheduling.** Cross-session memory, a reusable skill library, and tasks that run on a schedule.\n\n**1. Clone the repository**\n\n```\ngit clone --recurse-submodules https://github.com/mindsdb/minds.git\ncd minds\n```\n\n**2. Install dependencies**\n\n```\nmake setup\n```\n\n**3. Run**\n\n| Mode | Command |\n|---|---|\n| Desktop app (Electron) with hot reload | `make dev` or `make watch` |\n| Web app in browser with hot reload | `make dev-web` |\n| Production build | `make build` |\n| Package for macOS | `make dist-mac` |\n| Package for Windows | `make dist-win` |\nBuild macOS `.app` from local uncommitted source |\n`make pack-local` |\n| Wipe all local installs + data (fresh start) | `make flush` |\n\nFresh start:`make flush`\n\nremoves the local runtime (the`cowork-server`\n\nuv tool and the`backend/*/.venv`\n\ns) and deletes app state in`~/.anton`\n\n(provider keys) and`~/.cowork`\n\n(database, hermes, projects). Use it to test the from-scratch install flow or recover from a broken install. It prompts for confirmation — pass`FORCE=1`\n\nto skip. The next`make setup`\n\nor app launch reinstalls everything.⚠️ This deletes your conversations and saved keys.\n\nThis repo is a superproject that pins each module (`frontend`\n\n, `backend/core_api`\n\n, `backend/core_agent`\n\n, `backend/data-vault`\n\n) to a commit. To work on module branches without polluting `git status`\n\nor fighting over pins:\n\n**1. Pick your branches** in a gitignored `dev.env`\n\n(copy the template):\n\n```\ncp dev.env.example dev.env      # then set REF=feat/my-thing (or per-module API_REF=…)\n```\n\n**2. make follows it** — one knob, both run paths:\n\n| Command | What it does |\n|---|---|\n`make use` |\ncheck out your `dev.env` refs across all submodules |\n`make dev` / `make watch` |\nrun the Electron app with live reload against local source |\n`make dev-web` |\nrun the web SPA with live reload against local source |\n`make server` + `make app` |\n(re)install the desktop server from the configured branch, then launch |\n`make server-local` + `make app-local` |\ninstall the desktop server from local uncommitted source, then launch |\n`make pack-local` |\nbuild the macOS `.app` from local uncommitted source (no push needed) |\n`make refs` |\nshow which refs the next run will use |\n`make baseline` |\nreset submodules to the pinned commits |\n`make pin` |\nrecord the current submodule commits as the superproject's pins (one deliberate commit) |\n\nSubmodules are configured with `ignore = all`\n\n, so your branch work never shows up as superproject changes — the parent `git status`\n\nstays clean. Pins move **only** via `make pin`\n\n. See [ CLAUDE.md](/mindsdb/mindshub/blob/main/CLAUDE.md) for the full workflow.\n\nCowork is built for flexible deployment — **cloud, VPC, on-prem, air-gapped, and hybrid** infrastructure — so you keep full control over your infrastructure, models, permissions, and data.\n\n**Ask a question**— join the[Discord community](https://mindshub.ai/discord).** Report a bug**— open a[GitHub issue](https://github.com/mindsdb/minds/issues)with reproduction steps.** Read the docs**— guides, setup, and the API at[docs.mindshub.ai](https://docs.mindshub.ai/?utm_source=github&utm_medium=repo-readme&utm_campaign=minds-readme).**Enterprise SLAs or custom deployments**—[contact the team](https://mindshub.ai/contact?utm_source=github&utm_medium=repo-readme&utm_campaign=minds-readme).\n\nCowork is open source and contributions are welcome — code, integrations, docs, bug reports, and feature ideas. Read the [docs](https://docs.mindshub.ai/?utm_source=github&utm_medium=repo-readme&utm_campaign=minds-readme) to get set up, browse [open issues](https://github.com/mindsdb/minds/issues), and say hi on [Discord](https://mindshub.ai/discord).\n\nFound a security vulnerability? Please **don't** open a public issue. Report it privately through our [security policy](https://github.com/mindsdb/minds/security).\n\nThis repository is released under the [MIT License](/mindsdb/mindshub/blob/main/LICENSE). Bundled components are governed by their own licenses — see each submodule's repository for details.", "url": "https://wpnews.pro/news/claude-but-open-source-one-workplace-not-five-tools-that-hate-eachother", "canonical_source": "https://github.com/mindsdb/mindshub", "published_at": "2026-07-13 19:45:42+00:00", "updated_at": "2026-07-13 20:05:42.865880+00:00", "lang": "en", "topics": ["ai-tools", "developer-tools", "ai-agents"], "entities": ["MindsDB", "MindsHub Cowork", "Claude", "GPT", "Gemini", "DeepSeek", "Qwen", "Kimi"], "alternates": {"html": "https://wpnews.pro/news/claude-but-open-source-one-workplace-not-five-tools-that-hate-eachother", "markdown": "https://wpnews.pro/news/claude-but-open-source-one-workplace-not-five-tools-that-hate-eachother.md", "text": "https://wpnews.pro/news/claude-but-open-source-one-workplace-not-five-tools-that-hate-eachother.txt", "jsonld": "https://wpnews.pro/news/claude-but-open-source-one-workplace-not-five-tools-that-hate-eachother.jsonld"}}