DeerFlowvsOpen Cowork
Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.
DeerFlow
ByteDance · Agent harness
OSSMCP
Panel
6.74 spec wins
- Reliability
- 6.2
- Usefulness
- 6.8
- Cost
- 7.2
- Longevity
- 6.7
“Serves its web UI on port 2026, so at least one line of the roadmap has a date.”
Open Cowork
OpenCowork AI · Agent harness
OSSMCP
Panel
6.50 spec wins
- Reliability
- 5.7
- Usefulness
- 6.8
- Cost
- 8.2
- Longevity
- 5.5
“Remote control lets you reach it from Feishu, so the agent working at your desk can be supervised from someone else's phone.”
Spec by spec
| Spec | DeerFlow | Open Cowork |
|---|---|---|
| Architecture | ||
| Category | Agent harness | Agent harness |
| Runs | local, sandbox | local, sandbox |
| Platforms | macos, linux, windows | macos, windows |
| Context window | not documented | not documented |
| Protocols | ||
| MCP client | Yes | Yes |
| MCP server | No | No |
| Capabilities | ||
| Runs terminal commands | Yes | Yes |
| Multi-file edits | Yes | Yes |
| Git operations | No | No |
| Browser control | Yes | YesBrowser access comes through an MCP connector, and GUI operation can drive a desktop browser directly. |
| Sandboxed execution | Yes | YesIsolation is a WSL2 VM on Windows and a Lima VM on macOS, not a container. |
| Multi-agent orchestration | Yes | No |
| Headless / CI mode | Yes | No |
| Models | ||
| Backbone | OpenAI, Anthropic, Google Gemini, Qwen, Doubao, DeepSeek, Kimi, GLM, MiniMax, OpenRouter, vLLM | Claude, OpenAI-compatible, GLM, MiniMax, Kimi, Gemini |
| Bring your own model | Yes | Yes |
| Local models | Yes | No |
| Cost | ||
| Pricing model | byok | byok |
| Starts at | $0/mo | $0/mo |
| Free tier | Yes | Yes |
| Bring your own key | Yes | Yes |
| Openness | ||
| Open source | Yes | Yes |
| License | MIT | MIT |
| GitHub stars | 83,325 | 2,179 |
Which one would each critic pick
| Critic | DeerFlow | Open Cowork | Pick |
|---|---|---|---|
| El Juez | — | — | not enough reviews |
| El Amigo | 7.0 | 7.3 | Open Cowork — Pick it if your work ends in documents and spreadsheets; pick a coding agent if it ends in a pull request. |
| El Crítico | 6.3 | 6.5 | Open Cowork — Commands run inside a WSL2 or Lima VM, and the GUI operation that drives your desktop applications does not, so the containment stops where the reach begins. |
| El Profesor | 6.5 | 6.3 | DeerFlow — Documented: a LangGraph agent with subagents, progressive memory loading, skills carrying allowed-tools policies and a plan mode with a TodoList; undocumented: any benchmark. |
| La Inversora | 6.3 | 6.5 | Open Cowork — 2,104 stars for a product positioned as the open alternative to a specific commercial one: real demand, and a strategy priced by somebody else. |
| La Jefa | 6.5 | 5.5 | DeerFlow — The backend docs include SSO.md for OIDC, an AUTH_DESIGN with per-user isolation and personal access tokens, and a multi-worker gateway that needs Postgres and Redis: self-hosted, but real. |
| El Hacker | 7.8 | 7.3 | DeerFlow — MIT, config.yaml for the runtime and extensions_config.json for MCP servers, vLLM for my own models, Claude through a Claude Code OAuth login, and stateless run endpoints I can curl. |
Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.