Deploy Now

SaaS Alternative

Zapier Claude Microsoft Copilot ChatGPT

Categories

Productivity AI Automation Machine Learning Artificial Intelligence Data Integration Agent Platform

Stars

39,679

Forks

6,239

Watchers

444

Developer links

Last Updated: 09-01-2026
Share on X

MindsHub

Backed by $50M+ from Benchmark, Y Combinator, and NVIDIA with 800+ contributors and 39,000+ GitHub stars, MindsHub Cowork is the unified AI workspace where open-source models handle entire projects — research, reporting, internal tools, scheduled operations — and return finished, shareable deliverables. The platform runs two interchangeable open-source agent harnesses, Anton and Hermes, swappable from a dropdown without losing context. A built-in Model Router pre-wires 25+ models spanning Anthropic Claude, OpenAI GPT, Google Gemini, DeepSeek, Qwen, Kimi, Grok, and MindsHub Air with automatic failover — no per-provider API keys required. A secure credentials vault connects BigQuery, PostgreSQL, Salesforce, HubSpot, Zendesk, Gong, Gmail, Google Drive, Notion, Linear, Stripe, and Slack, keeping secrets scoped per connection so agents never see raw keys. Agent output becomes publishable artifacts — documents, dashboards, apps, and code — each deployable to a live shareable URL. Cross-session persistent memory, a reusable skill library, and a background scheduler supporting hourly, daily, and weekly cadences enable autonomous recurring workflows. The architecture separates a React/Vite frontend (shipping as both Electron desktop app and web SPA) from a FastAPI backend with a versioned REST API at /api/v1 covering conversations, projects, artifacts, schedules, and connectors. Self-host via Docker Compose with nginx on port 3000 and the API on port 26866, or deploy on-prem, in a VPC, or air-gapped. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

MindsHub
MindsHub
MindsHub
MindsHub
MindsHub

Benefits

  • Route Any Model Instantly
  • Switch between 25+ AI models including Claude, GPT, Gemini, DeepSeek, Qwen, and Kimi from a single dropdown with automatic provider failover and no per-provider API key management required.
  • Secure Data Vault Connections
  • Connect BigQuery, PostgreSQL, Salesforce, HubSpot, Zendesk, Gmail, Google Drive, Notion, Linear, and Stripe through a scoped credentials vault where agents never access raw secrets.
  • Publish Artifacts to Live URLs
  • Transform agent output into documents, dashboards, interactive apps, and code artifacts, then publish each to a shareable live URL for team collaboration without additional infrastructure.
  • Self-Host with Full Control
  • Deploy via Docker Compose with nginx serving the web SPA on port 3000 and the FastAPI backend on port 26866, supporting cloud, VPC, on-prem, air-gapped, and hybrid deployments.

Features

  • Model Router
  • Pre-wired access to 25+ models from Anthropic, OpenAI, Google, DeepSeek, Qwen, Kimi, xAI, and MindsHub Air with automatic failover and smart model selection.
  • Open Agent Harnesses
  • Run interchangeable open-source agents Anton and Hermes, swappable via dropdown, each implementing the HarnessProvider protocol for streaming responses, skill sync, and memory.
  • Scheduled Workflows
  • Background scheduler supports once, hourly, daily, and weekly cadences with tracked runs, enabling autonomous recurring operations like daily briefings and weekly summaries.
  • Connected Data Vault
  • Secure vault linking BigQuery, PostgreSQL, Salesforce, HubSpot, Zendesk, Gong, Gmail, Drive, Notion, Linear, and Slack with scoped credentials per connection.
  • REST API
  • Versioned REST API at /api/v1 exposes endpoints for conversations, projects, artifacts, schedules, connectors, memory, skills, and publishing operations.
  • Docker Deployment
  • Docker Compose stack with separate API and web containers, health checks, SQLite-backed persistence, and support for cloud, VPC, on-prem, and air-gapped environments.