Visão geral
An agent harness combining tools, memory and sandboxes for research, coding and content tasks. The repository is maintained under bytedance on GitHub. Its primary language is Python. See the [project README](https://github.com/bytedance/deer-flow#readme) for the supported workflows.
Principais recursos
- An agent harness combining tools, memory and sandboxes for research, coding and content tasks.
Requisitos, instalação e início rápido
Follow the upstream quickstart, install its documented runtime, and configure only the model providers and tools required for your first task.
[Read the upstream installation and quickstart instructions](https://github.com/bytedance/deer-flow#readme).
[Read the upstream installation and quickstart instructions](https://github.com/bytedance/deer-flow#readme).
Uso
Give the agent a narrowly scoped task with test data, review its actions and outputs, and expand tool access only as needed.
[Usage examples and configuration reference](https://github.com/bytedance/deer-flow#readme).
[Usage examples and configuration reference](https://github.com/bytedance/deer-flow#readme).
Compatibilidade do modelo e casos de uso
A compatibilidade do modelo não está especificada nos metadados do repositório.
Observações sobre licença e riscos
GitHub reports MIT for this repository. Review the upstream license file; model weights, datasets and dependencies may have separate terms.
Source review 2026-09-05: GitHub search metadata and repository README. No runtime benchmark performed. License metadata: MIT.
Lançamento e manutenção
[View upstream releases](https://github.com/bytedance/deer-flow/releases).