# mindsdb/mindshub

The unified workspace where open-source models get things done for you.

Repository: https://github.com/mindsdb/mindshub
Canonical: https://ross.abutalabs.com/products/mindshub
Homepage: https://mindshub.ai
Language: Makefile
License: MIT
License Family: permissive
Topics: ai, artificial-inteligence, agents, mcp, anton, claude, claude-cowork, codex, cowork, deepseek, glm, hermes, hermes-agent, kimi, mindsdb
Last push: 2026-08-21T23:50:38+00:00

## Health v2 (maintenance only)
Score: 88/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 98, release rhythm 68, longevity 100
- inputs: {"age_days": 2953, "days_push": 12, "days_rel": 132, "gap_med": 5, "n_releases_24m": 86}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 39649, forks 6237 (observed 2026-08-28T04:12:07.952703+00:00)

## What it is
MindsHub Cowork is an open-source AI workspace where users delegate multi-step projects (apps, reports, research, scheduled operations) to AI agents that connect to their data and produce shareable results. It also ships a unified inference API exposing Claude, GPT, Gemini, DeepSeek, Kimi and other models through OpenAI- and Anthropic-compatible endpoints on a single key.

## Use cases
- delegate projects to ai agents that connect to my data
- run open-source ai agents locally or in my vpc
- swap llm models without changing my code
- use openai sdk with claude and other models via one api key
- automate recurring reports and briefings with ai
- build and publish small web apps from ai agent output
- self-host an ai agent workspace

## When to choose
- you want a unified workspace where agents do end-to-end work on your data
- you need model-agnostic inference with OpenAI/Anthropic-compatible APIs and easy model switching
- you want open-source AI infrastructure you can run locally, in a VPC, or hosted

## When to avoid
- you need only a lightweight chatbot UI without agent orchestration or data connections
- you require a fully offline stack with no hosted inference or platform fees
- you need a minimal library to embed in an existing app rather than a full platform

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, llm-inference, chatbot, workflow-automation, rag, mcp, web-framework, data-science
- domain: artificial-intelligence, large-language-models, developer-tools, data-science, self-hosted
- platform: windows, self-hosted, python, cross-platform
- tags: ai-workspace, cowork, unified-inference-api, model-routing, openai-compatible-api, anthropic-compatible-api, desktop-app, superproject, mindsdb, ai-agents, automation, macos, linux, web-server, docker

## Member repositories
- mindsdb/mindshub (main) score 88

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:07.952703+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:24:06.797671+00:00, confidence not recorded.
  - readme: https://github.com/mindsdb/mindshub (fetched 2026-08-28T04:12:07.952703+00:00, sha 78652637fd87)
  - homepage: https://mindshub.ai (fetched 2026-08-29T07:46:43.557935+00:00, sha b17bc7a03594)
  - site_page: https://docs.mindshub.ai/inference (fetched 2026-08-29T07:46:43.560942+00:00, sha dc291b31c12c)
  - site_page: https://mindshub.ai/about (fetched 2026-08-29T07:46:43.565494+00:00, sha c4fe748db0a7)
  - site_page: https://mindshub.ai/pricing (fetched 2026-08-29T07:46:43.562860+00:00, sha bde69d6fa5d3)
- Data as of 2026-08-30T08:39:29.467469+00:00.