公开记录
软件健康报告模式 0.34.0 · 指标 2.10.0 · 2026-08-28 12:12 UTC

Kreoh / kroog

Koog is a JVM (Java and Kotlin) framework for building predictable, fault-tolerant and enterprise-ready AI agents across all platforms – from backend services to Android and iOS, JVM, and even in-browser environments. Koog is based on our AI products expertise and provides proven solutions for complex LLM and AI problems

KotlinApache-2.0★ 0 星标⑂ 0 复刻始于 2026年7月复刻在 GitHub 上查看 ↗

Kreoh/kroog 的健康指数为 100 分中的 59 分，处于「中等」区间。 其得分最高的类别是Vitality（84/100），最低的是Community & Adoption（12/100）。 最近一次更新在 14 天前。 近期的大部分工作由 6 位贡献者完成。

59
总分 / 100
中等

软件健康指数

指标归入加权类别，统一采用 1–100 量表。总体分先取类别加权平均，再依据公开记录的分布进行校准，使各等级具有百分位含义；当公开证据触发高风险司法辖区政策时，评级会按政策调整，并设置 34（存在风险）的上限。

59
卓越93-100公开记录中的最高层级（约前 5%）；基本满足所有检验标准
优秀80-92各方面均表现强劲；仅有少量不足
良好65-79健康；不足之处有限且可控
中等50-64可接受，但存在明显不足；建议进行审查
薄弱35-49多个领域存在实质性薄弱环节
存在风险20-34存在重大薄弱环节；采用时应保持审慎
危急1-19问题严重（项目被弃置、仅有单一维护者、缺乏基本工程规范）
活力社区与采用可持续性与治理工程质量安全AI 就绪度

评分画像

每条轴代表一个类别。形状比平均值更重要——健康的对象会填满整个图形，而“一峰一谷”式画像意味着某一维度的优势正掩盖另一维度的风险。

加权总体分 56 经校准后在公布的指数量表上为 59（记录校准 2026-08-02）。

所有权

Kreoh组织 · 域名已验证
1 关注者4 个公开仓库始于 2021年8月

该仓库由组织支持——共同承担、可问责的托管责任，可延续于任何单一维护者之后。

按类别列示的指标

活力

项目是否仍有生命——是否仍在编写代码，是否仍在发布版本？

84优秀 · 占总体的 21%

开发活跃度

81优秀
评分方式
28.8/36推送新近度 — 最近一次推送于 14 天前
34.6/36提交节奏 — 52 周中有 50 周有提交
18/18提交量 — 最近一年 905 次提交
0/10OpenSSF Scorecard：Maintained — project was created within the last 90 days. Please review its contents carefully
所用输入
commits_last_year905
human_commit_share1
days_since_last_push14
active_weeks_last_year50

发布纪律

88优秀
评分方式
16.2/27有发布版本 — 8 个版本标签（无 GitHub 发布版本）
36/36发布时效 — 最近一次发布版本于 14 天前
27/27发布节奏 — 约每 1.1 天发布一次
0/10OpenSSF Scorecard：Signed-Releases — 无数据
所用输入
releases_count8
latest_release_tag1.1.1-kroog.3
releases_from_tags是
days_since_latest_release14
mean_days_between_releases1.1
已排除计分（无数据或不适用）：OpenSSF Scorecard：Signed-Releases。 其余权重已重新归一化。

社区与采用

项目是否拥有用户、下载量与关注度，并具备欢迎贡献者参与的配置？

12危急 · 占总体的 17%

流行度与采用

1危急
评分方式
0/60星标 — 0 个星标
0/25复刻 — 0 个复刻
0/15关注者 — 0 位关注者
所用输入
forks0
stars0
watchers0
growth_stateunverified
growth_factor_pct100
growth_unverified_reasonno_history

社区健康

25存在风险
评分方式
0/22.5README
22.5/22.5许可证 — 可识别的许可证（Apache-2.0）
0/18CONTRIBUTING 指南
0/13.5行为准则
0/7.2议题模板
0/6.3PR 模板
所用输入
has_readme否
has_license否
readme_badges7
has_contributing否
has_issue_template否
has_code_of_conduct否
readme_badge_servicesgithub.com, shields.io
has_pull_request_template否

可持续性与治理

项目能否在其成员之外延续——巴士系数、响应能力、由谁支持，以及软件包的维护状况？

76良好 · 占总体的 23%

维护者韧性（巴士系数）

92优秀
评分方式
48.6/54巴士系数 — 6 位贡献者贡献了半数提交
19.5/22.5提交分布 — 头号贡献者编写了 14% 的提交
13.5/13.5贡献者广度 — 98 位贡献者
10/10OpenSSF Scorecard：Contributors — project has 18 contributing companies or organizations
所用输入
bus_factor6
contributors_sampled98
top_contributor_share0.135

议题与 PR 响应能力

67良好
评分方式
0/42议题解决 — 没有议题或无数据
30/30PR 接受 — 已裁定的 PR 中 1/1 已合并
0/13Newcomer PR acceptance — 30 天内没有首次贡献者的 PR 得到裁决
0/15OpenSSF Scorecard：Code-Review — Found 0/30 approved changesets -- score normalized to 0
所用输入
merged_prs1
open_issues0
closed_issues0
prs_merged_7d0
prs_decided_7d0
prs_merged_30d0
prs_decided_30d0
issue_closed_ratio—
closed_unmerged_prs0
first_time_authors_30d0
first_time_prs_merged_30d0
first_time_prs_decided_30d0
已排除计分（无数据或不适用）：议题解决, Newcomer PR acceptance。 其余权重已重新归一化。

所有权与托管责任

67良好
评分方式
30/30所有权背书 — 组织持有
20/20已验证域名
2.2/25所有者影响力 — Kreoh 有 1 位关注者
15.1/25既往记录 — 4 个公开仓库，账户约 5 年
所用输入
followers1
owner_typeOrganization
is_verified是
owner_loginKreoh
public_repos4
account_age_days1,826

工程质量

基础的工程与文档实践是否到位？

57中等 · 占总体的 19%

工程实践

68良好
评分方式
24/24CI 工作流 — 23 个工作流
24/24存在测试
0/16Linter 配置
0/9.6Pre-commit 钩子
6.4/6.4.editorconfig
0/20OpenSSF Scorecard：CI-Tests — 无数据
所用输入
has_ci是
has_tests是
has_editorconfig是
has_linter_config否
has_precommit_config否
已排除计分（无数据或不适用）：OpenSSF Scorecard：CI-Tests。 其余权重已重新归一化。

文档

40薄弱
评分方式
0/30README
25/25文档目录
15/15文档 / 主页站点 — https://docs.koog.ai
0/10仓库描述
0/10主题标签
0/10Wiki
所用输入
topics—
has_wiki否
homepagehttps://docs.koog.ai
docs_sitehttps://docs.koog.ai
has_readme否
has_docs_dir是
has_description否

安全

可见的安全与供应链实践是否稳固，且不存在未解决的高风险司法辖区暴露？

29存在风险 · 占总体的 16%

安全态势

29存在风险
评分方式
0/7.5Binary-Artifacts — binaries present in source code
0/7.5Branch-Protection — branch protection not enabled on development/release branches
0/2.5CI-Tests — 无数据
0/2.5CII-Best-Practices — no effort to earn an OpenSSF best practices badge detected
0/7.5Code-Review — Found 0/30 approved changesets -- score normalized to 0
2.5/2.5Contributors — project has 18 contributing companies or organizations
10/10Dangerous-Workflow — no dangerous workflow patterns detected
7.5/7.5Dependency-Update-Tool — update tool detected
0/5Fuzzing — project is not fuzzed
2.5/2.5许可证 — license file detected
0/7.5Maintained — project was created within the last 90 days. Please review its contents carefully
5/5Packaging — packaging workflow detected
0/5Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 0
0/5SAST — no SAST tool detected
0/5Security-Policy — security policy file not detected
0/7.5Signed-Releases — 无数据
0/7.5Token-Permissions — detected GitHub workflow tokens with excessive permissions
0/7.5Vulnerabilities — 23 existing vulnerabilities detected
所用输入
sourceopenssf_scorecard
checks_evaluated16
scorecard_versionv5.5.0
checks_inconclusive2
scorecard_aggregate2.9
已排除计分（无数据或不适用）：CI-Tests, Signed-Releases。 其余权重已重新归一化。

AI 就绪度

该仓库在多大程度上具备与 AI 编码代理协同开发与维护的条件？权重刻意设小（4%）：代理工具链是一项真实的维护信号，但完全不具备的仓库仍可达到 100/100。

84优秀 · 占总体的 4%

AI 代理上下文与指引

100卓越
评分方式
45/45代理指令 — AGENTS.md, CLAUDE.md, GEMINI.md, a2a/CLAUDE.md, examples/simple-examples/CLAUDE.md
15/15机器可读文档（llms.txt） — 项目网站提供 llms.txt（https://docs.koog.ai/llms.txt）
40/40可读的提交历史 — 100 次人类提交中有 99 次说明了意图（结构化标题或解释性正文）
所用输入
has_llms_txt是
llms_txt_urlhttps://docs.koog.ai/llms.txt
legible_history_share0.99
agent_instruction_filesAGENTS.md, CLAUDE.md, GEMINI.md, a2a/CLAUDE.md, examples/simple-examples/CLAUDE.md
agent_instruction_max_bytes10,564

验证循环（构建 / 测试 / 类型检查）

61中等
评分方式
12.6/18一条命令的引导启动 — a2a/a2a-client/build.gradle.kts, a2a/a2a-core/build.gradle.kts, a2a/a2a-server/build.gradle.kts（工具链约定，无任务运行器）
22/22自动化测试
0/11Lint / 格式化配置
11/11静态类型检查 — examples/koog-js-example/webApp/tsconfig.json
10/10可复现环境 — devcontainer, Dockerfile, lockfile
0/10已体现的代理实践 — 最近 100 次提交中没有代理编写的提交
5/8自动化维护 — 已配置依赖自动化，但在抽样提交中未观察到
0/10OpenSSF Scorecard：Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 0
所用输入
has_nix否
has_tests是
lockfilesuv.lock
has_dockerfile是
typed_language是
bootstrap_files—
has_devcontainer是
has_linter_config否
typecheck_configsexamples/koog-js-example/webApp/tsconfig.json
agent_commit_share0
toolchain_manifestsa2a/a2a-client/build.gradle.kts, a2a/a2a-core/build.gradle.kts, a2a/a2a-server/build.gradle.kts, a2a/a2a-test/build.gradle.kts, a2a/a2a-transport/a2a-transport-client-jsonrpc-http/build.gradle.kts, a2a/a2a-transport/a2a-transport-core-jsonrpc/build.gradle.kts, a2a/a2a-transport/a2a-transport-server-jsonrpc-http/build.gradle.kts, a2a/test-tck/a2a-test-server-tck/build.gradle.kts, agents/agents-cli/build.gradle.kts, agents/agents-core/build.gradle.kts, agents/agents-ext/build.gradle.kts, agents/agents-features/agents-features-a2a-client/build.gradle.kts, agents/agents-features/agents-features-a2a-core/build.gradle.kts, agents/agents-features/agents-features-a2a-server/build.gradle.kts, agents/agents-features/agents-features-acp/build.gradle.kts, agents/agents-features/agents-features-chat-history-aws/build.gradle.kts, agents/agents-features/agents-features-chat-history-jdbc/build.gradle.kts, agents/agents-features/agents-features-chat-memory-sql/build.gradle.kts, agents/agents-features/agents-features-event-handler/build.gradle.kts, agents/agents-features/agents-features-longterm-memory-aws/build.gradle.kts, agents/agents-features/agents-features-longterm-memory/build.gradle.kts, agents/agents-features/agents-features-memory/build.gradle.kts, agents/agents-features/agents-features-opentelemetry/build.gradle.kts, agents/agents-features/agents-features-persistence-jdbc/build.gradle.kts, agents/agents-features/agents-features-snapshot/build.gradle.kts, agents/agents-features/agents-features-sql/build.gradle.kts, agents/agents-features/agents-features-tokenizer/build.gradle.kts, agents/agents-features/agents-features-trace/build.gradle.kts, agents/agents-mcp-metadata/build.gradle.kts, agents/agents-mcp-server/build.gradle.kts, agents/agents-mcp/build.gradle.kts, agents/agents-planner/build.gradle.kts, agents/agents-test/build.gradle.kts, agents/agents-tools/build.gradle.kts, agents/agents-utils/build.gradle.kts, build.gradle.kts, convention-plugin-ai/build.gradle.kts, docs/build.gradle.kts, embeddings/embeddings-base/build.gradle.kts, embeddings/embeddings-llm/build.gradle.kts, examples/acp-agent/build.gradle.kts, examples/code-agent/step-01-minimal-agent/build.gradle.kts, examples/code-agent/step-02-add-execution-tool/build.gradle.kts, examples/code-agent/step-03-add-observability/build.gradle.kts, examples/code-agent/step-04-add-subagent/build.gradle.kts, examples/code-agent/step-05-history/build.gradle.kts, examples/demo-compose-app/androidApp/build.gradle.kts, examples/demo-compose-app/build.gradle.kts, examples/demo-compose-app/commonApp/build.gradle.kts, examples/demo-compose-app/desktopApp/build.gradle.kts, examples/demo-compose-app/webApp/build.gradle.kts, examples/devoxx-belgium-2025/build.gradle.kts, examples/javaone-2026/build.gradle.kts, examples/koog-agentcore-runtime/build.gradle.kts, examples/koog-java-api-example/build.gradle.kts, examples/koog-js-example/build.gradle.kts, examples/koog-js-example/koogelis/build.gradle.kts, examples/simple-examples-java/build.gradle.kts, examples/simple-examples-java/buildSrc/build.gradle.kts, examples/simple-examples/build.gradle.kts, examples/simple-examples/buildSrc/build.gradle.kts, examples/spring-ai-java/pom.xml, examples/spring-ai-kotlin/build.gradle.kts, examples/spring-boot-java/pom.xml, examples/spring-boot-kotlin/build.gradle.kts, examples/spring-io-2026/java/pom.xml, examples/spring-io-2026/kotlin/build.gradle.kts, examples/trip-planning-example/build.gradle.kts, http-client/http-client-core/build.gradle.kts, http-client/http-client-java/build.gradle.kts, http-client/http-client-ktor/build.gradle.kts, http-client/http-client-okhttp/build.gradle.kts, http-client/http-client-spring-webclient/build.gradle.kts, http-client/http-client-test/build.gradle.kts, integration-tests/build.gradle.kts, koog-agents-additions/build.gradle.kts, koog-agents/build.gradle.kts, koog-bedrock-agentcore-runtime/build.gradle.kts, koog-ktor/build.gradle.kts, koog-spring-ai-v2/build.gradle.kts, koog-spring-ai-v2/koog-spring-ai-v2-common/build.gradle.kts, koog-spring-ai-v2/koog-spring-ai-v2-starter-chat-memory/build.gradle.kts, koog-spring-ai-v2/koog-spring-ai-v2-starter-model-chat/build.gradle.kts, koog-spring-ai-v2/koog-spring-ai-v2-starter-model-embedding/build.gradle.kts, koog-spring-ai-v2/koog-spring-ai-v2-starter-vector-store/build.gradle.kts, koog-spring-ai/build.gradle.kts, koog-spring-ai/koog-spring-ai-common/build.gradle.kts, koog-spring-ai/koog-spring-ai-starter-chat-memory/build.gradle.kts, koog-spring-ai/koog-spring-ai-starter-model-chat/build.gradle.kts, koog-spring-ai/koog-spring-ai-starter-model-embedding/build.gradle.kts, koog-spring-ai/koog-spring-ai-starter-vector-store/build.gradle.kts, koog-spring-boot-starter/build.gradle.kts, prompt/prompt-cache/prompt-cache-files/build.gradle.kts, prompt/prompt-cache/prompt-cache-model/build.gradle.kts, prompt/prompt-cache/prompt-cache-redis/build.gradle.kts, prompt/prompt-executor/prompt-executor-cached/build.gradle.kts, prompt/prompt-executor/prompt-executor-clients/build.gradle.kts, prompt/prompt-executor/prompt-executor-clients/prompt-executor-anthropic-client/build.gradle.kts, prompt/prompt-executor/prompt-executor-clients/prompt-executor-bedrock-client/build.gradle.kts, prompt/prompt-executor/prompt-executor-clients/prompt-executor-dashscope-client/build.gradle.kts, prompt/prompt-executor/prompt-executor-clients/prompt-executor-deepseek-client/build.gradle.kts, prompt/prompt-executor/prompt-executor-clients/prompt-executor-google-client/build.gradle.kts, prompt/prompt-executor/prompt-executor-clients/prompt-executor-litert-client/build.gradle.kts, prompt/prompt-executor/prompt-executor-clients/prompt-executor-mistralai-client/build.gradle.kts, prompt/prompt-executor/prompt-executor-clients/prompt-executor-ollama-client/build.gradle.kts, prompt/prompt-executor/prompt-executor-clients/prompt-executor-openai-client-base/build.gradle.kts, prompt/prompt-executor/prompt-executor-clients/prompt-executor-openai-client/build.gradle.kts, prompt/prompt-executor/prompt-executor-clients/prompt-executor-openrouter-client/build.gradle.kts, prompt/prompt-executor/prompt-executor-llms-all/build.gradle.kts, prompt/prompt-executor/prompt-executor-managed-execution/build.gradle.kts, prompt/prompt-executor/prompt-executor-model/build.gradle.kts, prompt/prompt-llm/build.gradle.kts, prompt/prompt-markdown/build.gradle.kts, prompt/prompt-model/build.gradle.kts, prompt/prompt-processor/build.gradle.kts, prompt/prompt-structure/build.gradle.kts, prompt/prompt-tokenizer/build.gradle.kts, prompt/prompt-xml/build.gradle.kts, rag/rag-base/build.gradle.kts, rag/rag-vector/build.gradle.kts, serialization/serialization-core/build.gradle.kts, serialization/serialization-jackson/build.gradle.kts, serialization/serialization-test/build.gradle.kts, skills-api-consumer-test/build.gradle.kts, skills/build.gradle.kts, test-utils/build.gradle.kts, utils/build.gradle.kts
dependency_bot_commit_share0

面向模型的代码可读性

100卓越
评分方式
45/45可类型检查的代码 — Kotlin（静态类型）
54.8/55可控的文件大小 — 采样的 1,905 个源文件中有 7 个超过 60KB
所用输入
primary_languageKotlin
largest_source_bytes103,789
source_files_sampled1,905
oversized_source_files7

机器可读接口

100卓越
评分方式
0/40API 模式（OpenAPI/GraphQL/proto） — 不适用于此类软件
0/20MCP 服务器 — 不适用于此类软件
40/40可运行示例 — example, examples, notebooks
所用输入
example_dirsexample, examples, notebooks
has_mcp_signal否
api_schema_files—
interfaces_expected_of—
已排除计分（无数据或不适用）：API 模式（OpenAPI/GraphQL/proto）, MCP 服务器。 其余权重已重新归一化。

关键数据

0GitHub 星标
98贡献者
905最近 12 个月提交数
14距最近推送天数
8发布版本数
6巴士系数（bus factor）
0开放议题
Maven, PyPI软件包生态系统数

数据采集警告

  • Community profile unavailable
  • Could not fetch pypi package 'test-python-a2a-server' from its registry
  • GitHub dependency-graph SBOM unavailable (404); the dependency graph may be disabled for this repository

更多细节

OpenSSF Scorecard 2.9 / 10
2.9综合

来自开源项目 OpenSSF Scorecard 的独立、工具无关的安全评估。每项检查奖励的是安全实践本身，而非特定供应商的工具。Scorecard 无法判定的检查项标记为 不适用，并从安全评分中剔除（绝不按零分计）。Scorecard v5.5.0 · 2026-08-28 12:12 UTC

0Binary-Artifactsbinaries present in source code
0Branch-Protectionbranch protection not enabled on development/release branches
不适用CI-Testsno pull request found
0CII-Best-Practicesno effort to earn an OpenSSF best practices badge detected
0Code-ReviewFound 0/30 approved changesets -- score normalized to 0
10Contributorsproject has 18 contributing companies or organizations
10Dangerous-Workflowno dangerous workflow patterns detected
10Dependency-Update-Toolupdate tool detected
0Fuzzingproject is not fuzzed
10Licenselicense file detected
0Maintainedproject was created within the last 90 days. Please review its contents carefully
10Packagingpackaging workflow detected
0Pinned-Dependenciesdependency not pinned by hash detected -- score normalized to 0
0SASTno SAST tool detected
0Security-Policysecurity policy file not detected
不适用Signed-Releasesno releases found
0Token-Permissionsdetected GitHub workflow tokens with excessive permissions
0Vulnerabilities23 existing vulnerabilities detected
直接依赖 2
注册表软件包版本约束清单文件
PyPIa2a-sdk==0.3.22a2a/test-python-a2a-server/pyproject.toml
PyPIuvicorn==0.35.0a2a/test-python-a2a-server/pyproject.toml
全部依赖 未采集

本报告未能采集到解析后的依赖集合：GitHub dependency-graph SBOM unavailable (404); the dependency graph may be disabled for this repository

原始 JSON 报告 机器可读

反馈

发现这份报告有不准确之处，或有想法要分享？错误的测量、未识别的工具、建议、疑问——都欢迎提出。每条消息都会被阅读并得到回复。

登录过程中消息不会丢失。

相关记录

与 Kreoh/kroog 共享目录标签或生态系统的已检测仓库。 并排阅读 →

100ray-project/rayRay is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.卓越100microsoft/onnxruntimeONNX Runtime: cross-platform, high performance ML inferencing and training accelerator卓越100risingwavelabs/risingwaveEvent streaming platform for agentic AI. Continuously ingest, transform, and serve event streams in real time, at scale.卓越100apache/airflowApache Airflow - A platform to programmatically author, schedule, and monitor workflows卓越99NVIDIA/cudfcuDF - GPU DataFrame Library 卓越99datahub-project/datahubThe Context Platform for your Data and AI Stack卓越

评分是信号，而非担保。 评分反映的是 GitHub 上公开可见的实践——不是代码审计，也不是安全保证。

缺失数据将被剔除并重新归一化权重，绝不按零分计。方法论已版本化并公开：指标 v2.10.0、模式 v0.34.0—— 完整方法论 · 指标知识库.

单项结果在整体记录中的位置： 汇总统计.