Обзор
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.
Основные функции
- An agent harness combining tools, memory and sandboxes for research, coding and content tasks.
Требования, установка и быстрый старт
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).
Использование
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).
Совместимость моделей и варианты использования
В метаданных репозитория совместимость моделей не указана.
Лицензия и примечания о рисках
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.
Релиз и сопровождение
[View upstream releases](https://github.com/bytedance/deer-flow/releases).