Memory across sessions
Cowork remembers your schemas, preferences, and past decisions — and lets you manage what it keeps.
Describe your task and get back finished, shareable work — documents, dashboards, reports, apps, and more.
MindsHub Cowork is the unified workspace where open-source agents get work done for you.
Chat is fine for a question and an answer. Real knowledge work isn't a transcript — it needs your data connected, the right model for each step, somewhere for results to live, and a way to share them.
Open-source agents deserve a powerful workspace. MindsHub Cowork brings it to them — and pushes it further: data through a secure vault, the model you choose, artifacts you can publish, and work you can hand off.
Point Cowork at the systems your work lives in — BigQuery, Postgres, Gmail, Drive, HubSpot, Notion, Linear — from one connectors directory. Credentials go into a vault, scoped per connection. The agent uses them at runtime but never sees a raw key.
The Model Router comes pre-wired, so there are no per-provider API keys to set up. Pick a planning model and a coding model from a dropdown — frontier models from Anthropic, OpenAI, and Google, or cost-effective open-source LLMs like DeepSeek, Qwen, and Kimi — and switch anytime. Your agent, history, and memory stay put.
Cowork runs on interchangeable open-source agent harnesses — Anton and Hermes today, with more on the way. Pick the one that fits your work from a dropdown and keep the same workspace, data, and artifacts. One interface; the engine underneath is yours to choose.
Cowork turns an agent's output into things you can use — documents, dashboards, apps, code — not a scrolling transcript. Keep them in the workspace, or publish to a live URL to share with anyone.
Group work into projects, pin what matters, and share published artifacts with your team by link. Cowork is built for handing work back and forth — not a private transcript only you can see.
Cowork remembers your schemas, preferences, and past decisions — and lets you manage what it keeps.
Teach reusable skills once; the agent recalls them when the work fits, instead of relearning every time.
Set a cadence and Cowork runs the work on schedule — daily briefings, weekly summaries, recurring audits.
Openness isn't a slogan here; it's how the platform works. Use commercial and open models side by side, switch providers without rewriting anything, and keep the memory and skills you build along the way.
Pick the model that fits the job — reasoning, coding, vision, long context, or fast, low-cost drafts — and switch anytime from a dropdown.
Most people meet them through Cowork — and can swap them anytime. Builders run them standalone, native harness and all.
Cowork is the workspace you see; underneath, a managed runtime does the work. You brief a task, an open-source agent harness runs it, the Model Router sends each step to the right model, and a credentials vault lets the agent reach your data and tools without ever seeing a raw key — all on MindsHub's always-on infrastructure.
Routes each step to the right LLM by cost, latency, and capability.
Protected reproducible execution environment.
Long-term, cross-run recall — facts, preferences, prior outcomes.
Choose which categories of cookies and similar technologies you allow us to use on this site. You can change these choices at any time via the Cookie preferences link in the footer.
Required for the site to work — the anonymous session cookie that lets us measure aggregate traffic. Always on.
Anonymous usage measurement (PostHog server-side). Helps us understand which pages are useful.
Click-ID attribution to ad platforms (Google, X, LinkedIn) and identified events so we can measure ad performance.
California, Virginia, Colorado, Connecticut, Utah, and other US state privacy laws give you the right to opt out of the “sale” or “sharing” of your personal information for cross-context behavioral advertising. We don’t sell your information for money, but we do share identifiers with our advertising partners to measure ad performance. You can opt out here.
See our Privacy Notice and Cookie Policy for full detail.