隐私与广告选择
Git-Stars 会使用必要存储来保障网站运行。可选分析和广告测量脚本默认不加载，只有在你同意后，Google 等合作伙伴才可能按要求使用 Cookie 或类似标识符。 隐私政策
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.
这个仓库详情页已经具备足够的原创分析、来源证据和同类对比，可以作为 Git-Stars 的可索引评测页。
100
评测分
解决的问题
DeerFlow solves the challenge of building reliable long-horizon AI agents that can maintain context, use tools, and execute multi-step tasks without losing track. It provides a production-ready harness with built-in memory, sandboxing, and sub-agent orchestration, reducing the complexity of assembling these components from scratch.
部署现实
当前可用的安装信号是：make setup。这只能作为起点，正式使用前建议让 Codex 或 Claude 检查 README、环境变量、运行时版本和部署目标。
商业可用性
当前记录的许可证是 MIT。这是重要的商业使用信号，但仍应核验许可证全文、依赖许可证、模型/API 条款和商标限制。
能力上限
Developers can build autonomous research assistants, coding agents, and creative content generators that operate over extended periods. Real-world use cases include automated deep research reports, software development tasks, and complex data analysis. The ceiling is high: with sub-agents, memory, and sandboxing, it can handle tasks that require planning, tool use, and iterative refinement, potentially replacing human effort in many knowledge-work scenarios.
Git-Stars 是独立产品，不隶属于 GitHub 或该项目。 分析可能由 AI 辅助生成，依据公开仓库元数据和 README 的短摘要。 我们不镜像完整 README、文档、Issue 或社媒评论。
bytedance/deer-flow 被追踪为 Python 项目，主要属于 AI Agent, LLM Tool, Automation 方向。这个评估结合公开 GitHub 元数据、分类信号、短来源摘要和 Git-Stars 编辑规则，而不是复制项目文档。
增长检查：该仓库目前有 79k Star，今日 +209，本周 +0，本月 +0。这些窗口用于区分持续采用信号和短期曝光峰值。
维护检查：当前活跃度为 一般；最近一次推送距今 74 天，未关闭 Issue 为 939，约占总 Star 的 1.19%。这只是采用信号，不替代工程尽调。
采用检查：11k Fork 和 79k Watcher 反映项目被复用和关注的程度。许可证信号：MIT。商业或内部使用前请核验许可证兼容性。
适用判断：当你需要「AI 原型、LLM 工作流和 Agent 类应用」时，这个项目更值得评估；如果「需要法律审查、安全审计或生产 SLA 保证」，则需要谨慎。
来源检查：Git-Stars 当前为这份报告保留了 2 个明确来源引用，近期增长信号为 209。最终安装、安全和版本信息仍应以原始 GitHub 仓库为准。
原创分析
充分已经具备问题、能力和结论层面的原创判断。
来源
充分已附带仓库元数据和 README/来源引用。
许可证
充分已记录 MIT，可作为评估依据。
维护
充分仓库元数据中可以看到近期活跃信号。
同类对比
充分已有足够相近项目用于对比。
热度
79k 星标
复用
11k 复刻
关注
79k 关注者
维护
moderate
许可证
MIT
未解决 Issue
939
DeerFlow is an open-source super agent harness that orchestrates sub-agents, memory, and sandboxes to perform a wide range of tasks, powered by extensible skills. It is a ground-up rewrite of the original Deep Research framework, offering advanced features like context engineering, long-term memory, and integration with coding agents.
核心特性
- Orchestrates sub-agents, memory, and sandboxes for versatile task execution - Extensible skills system, including Claude Code integration - Includes a setup wizard, Docker deployment, and support for multiple LLM providers and tracing tools
AI Agent
Agent frameworks, autonomous workflows, and tool-use systems
LLM Tool
Libraries and tools for LLM apps, RAG, prompts, and evals
Automation
Workflow automation, integration glue, and orchestration
make setup80
健康评分
一般
提交活跃度
May 7, 2025
创建于
Aug 1, 2026
最近提交
每日同步积累数据后，Star 历史将在此显示。
复刻
未解决
关注者
bytedance
GitHub 主页obra/superpowers
An agentic skills framework & software development methodology that works.
affaan-m/ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
NousResearch/hermes-agent
The agent that grows with you
mattpocock/skills
Skills for Real Engineers. Straight from my .agents directory.
multica-ai/andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
✓
许可证
✓
Fork 情况
~ 一般
维护情况
解决的问题
DeerFlow solves the challenge of building reliable long-horizon AI agents that can maintain context, use tools, and execute multi-step tasks without losing track. It provides a production-ready harness with built-in memory, sandboxing, and sub-agent orchestration, reducing the complexity of assembling these components from scratch.
能力范围
Developers can build autonomous research assistants, coding agents, and creative content generators that operate over extended periods. Real-world use cases include automated deep research reports, software development tasks, and complex data analysis. The ceiling is high: with sub-agents, memory, and sandboxing, it can handle tasks that require planning, tool use, and iterative refinement, potentially replacing human effort in many knowledge-work scenarios.
结论
DeerFlow is ideal for developers and organizations seeking a robust, open-source framework for building long-horizon AI agents. It offers a comprehensive feature set but requires careful deployment and resource planning. The key trade-off is between its powerful automation capabilities and the need for responsible use and infrastructure investment.