deer-flow vs openmake_llm
Self-hosted AI agent workflows compared
deer-flow and openmake_llm are self-hosted projects for coordinating AI models, agents, and tools across multi-step tasks. deer-flow focuses on an extensible agent runtime for long-running work, while openmake_llm emphasizes a workspace that routes among models and supports research and persistent agent tasks.
deer-flow: Orchestrate Long-Running AI Agent Tasks
DeerFlow is a self-hosted harness for AI agents that coordinate subagents, memory, tools, and sandboxes on tasks that can run from minutes to hours. It suits teams building research, coding, and content workflows that need an extensible agent runtime.
openmake_llm: Coordinate AI Models, Agents, and Tools
OpenMake is a self-hosted AI workspace that coordinates chat models, agents, and tools in one place. It suits people who want multi-step AI workflows with local or open-weight models, while keeping infrastructure and model choices under their control.
| deer-flow | openmake_llm | |
|---|---|---|
| Language | Python | TypeScript |
| License | MIT | MIT |
| Stars | 83.4k | 43 |
| Forks | 11.6k | 7 |
| Last analyzed | Oct 3, 2026 | Oct 4, 2026 |
Key differences
- deer-flow is a Python agent harness with a lead agent, delegated subagents, memory, skills, and sandbox modes; openmake_llm is a TypeScript workspace that routes requests to models assigned to roles and capabilities.
- deer-flow supports local, Docker, and Kubernetes-backed sandbox modes; openmake_llm runs agent code and MCP servers in Docker sandboxes with configurable isolation and approval policies.
- deer-flow offers a web interface, messaging channels, and a terminal workbench; openmake_llm highlights an OpenAI-compatible API and PDF or DOCX report exports.
- deer-flow lists SQLite or PostgreSQL for persistent deployments and recommends Docker; openmake_llm's installer sets up PostgreSQL and Redis, with Docker and PM2 among its stated requirements.
- deer-flow reports 83.4k stars and 11.6k forks, while openmake_llm reports 43 stars and 7 forks.
- Both projects use the MIT license, but deer-flow is written in Python and openmake_llm in TypeScript.
Choose deer-flow if you…
- need an extensible runtime for research, coding, or content tasks that can run from minutes to hours.
- want a lead agent to delegate work and use memory, skills, tools, and configurable sandbox modes.
- prefer a project with a web interface, messaging channels, and a terminal workbench.
Choose openmake_llm if you…
- want to route work across models assigned to capabilities such as planning, vision, or speech.
- need persistent agent tasks with checkpoints, approvals, parallel sub-agents, and cited research reports.
- plan to connect local or open-weight model endpoints alongside hosted providers in a self-hosted workspace.
Compare the numbers side by side, or add more projects
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.