mindshub vs deer-flow
Two of the top projects in Agent platforms, side by side: who leads on each score part and who each one suits, then setup, license, activity and what each review found.
mindshub
Agent workspace for knowledge work, with swappable open agent harnesses
deer-flow
Agent harness that runs sub-agents, memory and sandboxed skills for long tasks
Verdict
mindshub ranks higher, 78 to 76. Of the 3 score parts we measure for both, mindshub leads on none, deer-flow on 2 and 1 is even.
- Adoptiondeer-flow leads by 20 points, 89 to 69: a wide gap.
- FreshnessEven at 100.
- MaintenanceWe do not score mindshub on this; deer-flow has 76.
- Easy to runWe do not score mindshub on this; deer-flow has 50.
- Agent-readydeer-flow leads by 30 points, 70 to 40: a wide gap.
Pick mindshub if you are
Teams wanting a self-hostable agent workspace for research and automation
- Swappable open-source agent harnesses (Anton, Hermes) selectable from a dropdown
- Connectors for BigQuery, Postgres, Gmail, Drive, HubSpot, Notion and Linear with per-connection credentials
Pick deer-flow if you are
Engineers self-hosting a multi-agent harness for research and long-running tasks
- Interactive `make setup` wizard generates config.yaml and .env in about 2 minutes
- Web UI model registration for OpenAI, Anthropic, DeepSeek, Qwen, Doubao, Kimi, Zhipu, MiniMax
| What we compare | mindshub | deer-flow |
|---|---|---|
| Score parts, out of 100 | ||
| Adoption | 69, popular | 89, widely used |
| Freshness | 100, active | 100, active |
| Maintenance | Not scored for this kind | 76, fair |
| Easy to run | Not scored for this kind | 50, easy |
| Agent-ready | 40, minimal | 70, partly |
| Facts from GitHub and the README | ||
| Stars | 39.8k | 83.9k |
| License | MIT (permissive) | MIT (permissive) |
| Last commit | Sep 2026 | Oct 2026 |
| Last release | Apr 2026 | Sep 2026 |
| Language | Makefile | Python |
| Docker | Yes | Yes |
| GPU | Not stated | Not needed |
| arm64 or Apple Silicon | Not stated | Mentioned |
mindshub
Superproject that builds the MindsHub desktop (Electron) and web app, agent backend and data vault from git submodules. Agents handle research, reports, scheduled tasks and app or document artifacts, using the Anton (default) or Hermes harness and a model router across Claude, GPT, Gemini, DeepSeek, Qwen and Kimi. Also offered as a hosted web app and macOS/Windows installers.
Who it is for: Teams wanting a self-hostable agent workspace for research and automation
Strengths
- Swappable open-source agent harnesses (Anton, Hermes) selectable from a dropdown
- Connectors for BigQuery, Postgres, Gmail, Drive, HubSpot, Notion and Linear with per-connection credentials
- Cross-session memory, skill library and scheduled tasks included
- MIT license; deployable locally, in a VPC, on-prem or air-gapped
Weaknesses
- Linux has no installer; requires building from source with make and submodules
- Pro tier needed for all frontier models and private artifacts
- README gives no RAM, GPU or port requirements
- Bundled submodules carry their own licenses
- Compose
- Needs make, uv, Python 3.10-3.13, Electron
- Models: Claude, GPT, Gemini, DeepSeek, Qwen
deer-flow
DeerFlow 2.0 is a ByteDance agent harness where a lead agent delegates to sub-agents, backed by long-term memory, a sandboxed file system and extensible skills. It includes a web UI, a Gateway, MCP support, IM channels, scheduled tasks, a terminal UI and an embedded Python client. It is a ground-up rewrite that shares no code with v1.
Who it is for: Engineers self-hosting a multi-agent harness for research and long-running tasks
Strengths
- Interactive `make setup` wizard generates config.yaml and .env in about 2 minutes
- Web UI model registration for OpenAI, Anthropic, DeepSeek, Qwen, Doubao, Kimi, Zhipu, MiniMax
- Tracing via LangSmith, Langfuse and Monocle, plus `make doctor` and `make support-bundle`
- Many search and fetch backends: Brave, Tavily, Jina, Firecrawl, Crawl4AI, InfoQuest
Weaknesses
- README warns improper deployment carries security risks; Gateway admin equals code execution
- Local development needs Python 3.12+ and Node.js 22+
- README is dense with config detail; RAM and hardware needs are not stated
- v2 shares no code with v1; v1 users must stay on the 1.x branch
- no GPU
- Docker + Compose
- Needs LLM provider API key, Python 3.12+, Node.js 22+
- Models: OpenAI, Anthropic, DeepSeek, Qwen, Doubao
More in Agent platforms
Building with these?
We help teams pick an open-source AI stack and run it in production. Client work never changes a rank.