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
Agent framework for the JVM. Pronounced Em-BAY-bel /ɛmˈbeɪbəl/
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
Most agent frameworks are Python-centric and lack tight integration with JVM enterprise ecosystems. Embabel solves this by providing a type-safe, domain-model-driven agent framework for Java/Kotlin, allowing developers to embed LLM-driven decision-making into existing Spring-based applications without leaving the JVM. Its dynamic replanning (OODA loop) adapts to changing conditions, unlike static workflows.
部署现实
当前可用的安装信号是：Add the Maven dependency: com.embabel.agent:embabel-agent-api (latest version from MvnRepository), and follow the quick-start guide at docs.embabel.com.。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 Apache-2.0。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 sophisticated autonomous agents that interact with enterprise systems, such as customer support bots that access internal APIs, automated workflow orchestrators that adjust plans based on real-time data, and intelligent assistants that reason over domain models. The framework supports complex goal-seeking behavior with continuous reassessment, making it suitable for high-stakes automation where adaptability is critical. The ceiling includes multi-agent coordination and integration with Spring Boot microservices.
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。
embabel/embabel-agent 被追踪为 Kotlin 项目，主要属于 AI Agent, LLM Tool, AI App, 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 4.2k Star，今日 +40，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 62 天，未关闭 Issue 为 69，约占总 Star 的 1.64%。这只是采用信号，不替代工程尽调。
采用检查：411 Fork 和 4.2k Watcher 反映项目被复用和关注的程度。许可证信号：Apache-2.0。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 40。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 Apache-2.0，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
4.2k 星标
复用
411 复刻
关注
4.2k 关注者
维护
moderate
许可证
Apache-2.0
未解决 Issue
69
Embabel is a framework for authoring agentic flows on the JVM that seamlessly mix LLM-prompted interactions with code and domain models. It supports intelligent path finding towards goals and is written in Kotlin with a natural usage model from Java. It was created by the creator of Spring.
核心特性
- Sophisticated planning using a non-LLM AI algorithm for dynamic plan formulation and replanning. - Superior extensibility and reuse through dynamic planning without editing FSM definitions. - Strong typing and object orientation with domain models, plus platform abstraction and built-in testability.
AI Agent
Agent frameworks, autonomous workflows, and tool-use systems
LLM Tool
Libraries and tools for LLM apps, RAG, prompts, and evals
AI App
End-user AI applications and AI-native product examples
Automation
Workflow automation, integration glue, and orchestration
Add the Maven dependency: com.embabel.agent:embabel-agent-api (latest version from MvnRepository), and follow the quick-start guide at docs.embabel.com.63
健康评分
一般
提交活跃度
Apr 10, 2025
创建于
Aug 13, 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
embabel
GitHub 主页openclaw/openclaw
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
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.
✓
许可证
✓
Fork 情况
~ 一般
维护情况
解决的问题
Most agent frameworks are Python-centric and lack tight integration with JVM enterprise ecosystems. Embabel solves this by providing a type-safe, domain-model-driven agent framework for Java/Kotlin, allowing developers to embed LLM-driven decision-making into existing Spring-based applications without leaving the JVM. Its dynamic replanning (OODA loop) adapts to changing conditions, unlike static workflows.
能力范围
Developers can build sophisticated autonomous agents that interact with enterprise systems, such as customer support bots that access internal APIs, automated workflow orchestrators that adjust plans based on real-time data, and intelligent assistants that reason over domain models. The framework supports complex goal-seeking behavior with continuous reassessment, making it suitable for high-stakes automation where adaptability is critical. The ceiling includes multi-agent coordination and integration with Spring Boot microservices.
结论
Embabel is ideal for JVM-centric teams (especially Spring/Kotlin) that need to embed LLM-driven agentic flows into production systems with strong typing and domain modeling. It is less suitable for Python-centric AI developers or those seeking a lightweight scripting approach. The key trade-off is the learning curve of its conceptual model versus the benefits of deep JVM integration and dynamic replanning.