📄 工具详情 ⚙️ 安装教程 📚 使用教程
能力标签
🔌 MCP🤖 Agent🔄 工作流🌐 翻译🐳 Docker🔗 REST API🧠 Claude✨ GPT⛓ LangChain
HealthClawGuardrails
⚙️
Agent工作流

HealthClawGuardrails

基于 Python · 无代码搭建完整 AI 自动化流程
⭐ 20 Stars 🍴 4 Forks 💻 Python 📄 MIT 🏷 AI 8.0分
8.0AI 综合评分
healthaihealthcarepythonsecurity
⬇ 下载源码 ZIP ⚙️ 配置说明 📺 TG 频道
✦ AI Skill Hub 推荐

HealthClawGuardrails 是 AI Skill Hub 本期精选Agent工作流之一。综合评分 8.0 分，整体质量较高。我们强烈推荐将其纳入你的 AI 工具库，帮助提升工作效率。

📚 深度解析

HealthClawGuardrails 是一套完整的 AI Agent 自动化工作流方案。随着 AI 能力的不断提升，基于 Agent 的自动化工作流正在成为提升个人和团队效率的核心方式。区别于传统的 RPA 自动化（模拟鼠标键盘操作），AI Agent 工作流通过理解任务意图、动态规划执行路径，能够处理更复杂的非结构化任务。

HealthClawGuardrails 工作流的设计遵循"最小配置，最大复用"原则：核心逻辑已经封装好，用户只需配置自己的 API Key 和业务参数即可快速上手。工作流内置错误处理和重试机制，在网络波动或 API 限速等情况下仍能稳定运行，适合作为生产环境的自动化基础设施。

在实际部署时，建议先在测试环境中运行 3-5 次，验证各个环节的输出结果符合预期，再部署到生产环境。AI Skill Hub 评分 8.0 分，是同类 Agent 工作流中的精选推荐。

📋 工具概览

HealthClawGuardrails 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排，将复杂的多步骤任务拆解为清晰的自动化流程，实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成，适合构建数据处理管线、业务自动化和 AI 辅助决策系统。

GitHub Stars
⭐ 20
开发语言
Python
支持平台
Windows / macOS / Linux
维护状态
轻量级项目，按需更新
开源协议
MIT
AI 综合评分
8.0 分
工具类型
Agent工作流
Forks
4

📖 中文文档

以下内容由 AI Skill Hub 根据项目信息自动整理，如需查看完整原始文档请访问底部「原始来源」。

HealthClawGuardrails 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排，将复杂的多步骤任务拆解为清晰的自动化流程，实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成，适合构建数据处理管线、业务自动化和 AI 辅助决策系统。

📌 核心特色
  • 可视化 Agent 工作流编排，无需编写复杂代码
  • 支持多步骤自动化任务链，实现全流程无人值守
  • 与外部 API、数据库和第三方服务无缝集成
  • 内置错误处理与自动重试机制，保障稳定运行
  • 提供可复用的自动化模板，快速在同类场景部署
🎯 主要使用场景
  • 自动化日常重复性工作，将精力集中于创造性任务
  • 构建数据采集 → 处理 → 输出的完整自动化管线
  • 实现跨平台、跨系统的数据流转和业务协同
以下安装命令基于项目开发语言和类型自动生成，实际以官方 README 为准。
安装命令
# 方式一：pip 安装（推荐）
pip install healthclawguardrails

# 方式二：虚拟环境安装（推荐生产环境）
python -m venv .venv
source .venv/bin/activate  # Windows: .venv\Scripts\activate
pip install healthclawguardrails

# 方式三：从源码安装（获取最新功能）
git clone https://github.com/aks129/HealthClawGuardrails
cd HealthClawGuardrails
pip install -e .

# 验证安装
python -c "import healthclawguardrails; print('安装成功')"
📋 安装步骤说明
  1. 访问 GitHub 仓库获取工作流文件
  2. 在对应平台（Dify / Flowise / Make 等）中找到「导入工作流」功能
  3. 上传工作流文件
  4. 按照提示配置必要的环境变量和 API Key
  5. 运行测试确认流程正常后投入使用
以下用法示例由 AI Skill Hub 整理，涵盖最常见的使用场景。
常用命令 / 代码示例
# 命令行使用
healthclawguardrails --help

# 基本用法
healthclawguardrails input_file -o output_file

# Python 代码中调用
import healthclawguardrails

# 示例
result = healthclawguardrails.process("input")
print(result)
以下配置示例基于典型使用场景生成，具体参数请参照官方文档调整。
配置示例
# healthclawguardrails 配置文件示例（config.yml）
app:
  name: "healthclawguardrails"
  debug: false
  log_level: "INFO"

# 运行时指定配置文件
healthclawguardrails --config config.yml

# 或通过环境变量配置
export HEALTHCLAWGUARDRAILS_API_KEY="your-key"
export HEALTHCLAWGUARDRAILS_OUTPUT_DIR="./output"
📑 README 深度解析 真实文档 完整度 84/100 查看 GitHub 原文 →
以下内容由系统直接从 GitHub README 解析整理，保留代码块、表格与列表结构。

简介

<img src=".github/assets/healthclaw-logo.png" alt="HealthClaw — AI-Powered Healthcare Intelligence" width="440">

What's new in v1.5.0 — Security Hardening + SDC Forms

Two threads landed since v1.4.0: a read-authentication hardening pass on the guardrail core, and HL7 Structured Data Capture (SDC) support so the project can populate and extract healthcare forms the standard, interoperable way.

SDC form round-trip — implements the two halves of HL7 SDC:

OperationWhat it doesMechanisms (v1)
POST /r6/fhir/Questionnaire[/<id>]/$populateQuestionnaire + subject → pre-filled QuestionnaireResponseexpression-based (initialExpression FHIRPath) + observation-based (item.code LOINC)
POST /r6/fhir/QuestionnaireResponse/$extractcompleted QuestionnaireResponse → transaction Bundleobservation-based (observationExtract) + definition-based (definitionExtract)
  • Pure, Flask-free transform engines in r6/sdc/ (expressions.py, populate.py, extract.py); the route layer owns auth, audit, step-up, and store I/O.
  • $populate is read-shaped (tenant-read-authenticated + AuditEvent); $extract reuses the existing write path — step-up + per-resource $validate on commit, with ?dryRun=true to preview the Bundle without committing.
  • Two new MCP tools — questionnaire_populate (read) and questionnaire_extract (write) — so an agent can fill and extract forms end-to-end.
  • A seeded healthclaw-intake demo Questionnaire shows the full populate → complete → extract loop.

Security hardening — X-Tenant-Id reads are now authenticated, not just tenant-scoped: non-public tenants must present a tenant-bound step-up token or a matching SMART bearer (a bare header gets 401). Plus a public-tenant-aware token-mint guard, the SMART OAuth service advertised in /metadata, and dependency CVE bumps (PyJWT, npm advisories).

Deliberate compliance postures (documented in CLAUDE.md and the design spec): - $populate returns unredacted PHI by design — a form must hold real data, and the read-auth gate is the compensating control. An optional ?redaction= opt-in is a tracked follow-up. - $extract commit is treated as an ingest-class operation (like Bundle/$ingest-context): step-up + $validate gate the write; it is exempt from the per-resource X-Human-Confirmed gate.

What's new in v1.4.0 — Multi-Connector Health Data Pipeline

One Telegram bot. All your health records. Every major source, automatically.

The v1.4.0 release wires five distinct health data pipelines into HealthClaw — each with its own auth model, transport, and data format — and exposes them as unified Telegram slash commands so you never leave the chat.

SourceCoverageTransportTelegram command
**Fasten TEFCA**Nationwide — all QHINs (hospitals, EHRs, labs) via CLEAR/ID.meWebhook push/connect
**HealthEx**Lab + clinical aggregatorMCP Streamable HTTP pull/export
**Health Bank One**Identity-verified records + insurance contextMCP Streamable HTTP pull/hbo-connect, /hbo-pull
**Flexpa**200+ payers/insurers (CMS-9115 mandate)SmartHealthConnect bridge/flexpa-connect
**Health Skillz (Epic)**Epic MyChart + major patient portalsSmartHealthConnect bridge/epic-connect
**MEDENT**Small-practice EHR (SMART on FHIR direct)Direct SMART on FHIR pull/medent-connect, /medent-pull
Where the code lives: Fasten (webhook + NDJSON ingest), HealthEx / Health Bank One (MCP-client OAuth pull), and MEDENT (SMART-on-FHIR pull) have working connector code in this repo. Flexpa and Health Skillz (Epic) run their payer/portal OAuth pull in the separate SmartHealthConnect service; this repo provides the guardrailed /shc/ingest receiver that those pulls post into — not the payer OAuth client itself. Ingested claims/coverage data is stored, validated, and audited; cost/denial/coverage-gap analytics are not implemented (payer data is retained, not analyzed).

New infrastructure:

  • /shc/ingest endpoint — SmartHealthConnect bridge receives FHIR bundles from Flexpa and Health Skillz pulls, applies the full guardrail stack, fires Telegram notification
  • /shc/medent/callback broker — MEDENT's OAuth validator requires a public HTTPS redirect URI; Railway acts as the callback broker so the Mac mini agent can still drive the flow
  • scripts/medent_oauth.py — SMART on FHIR Patient Standalone Launch (Dynamic Client Registration + PKCE + token caching + auto-refresh)
  • scripts/export_medent_fhir.py — Pulls US Core R4 resources from any MEDENT practice, redacts PHI in-process
  • Telegram: all 6 new commands deployed to all 7 OpenClaw personas (Sally, Mary, Dom, Kristy, Joe, Ronny, Shervin)

What's new in v1.3.0 — Wearables

Heart rate, HRV, SpO2, steps, sleep, BP, glucose, body weight — from Garmin, Oura, Polar, Suunto, Whoop, Fitbit, Strava, Ultrahuman — flow into HealthClaw as FHIR Observations with correct LOINC codes and device Provenance. Compiled Truth timelines now include wearable-sourced data; SmartHealthConnect's healthy-habits + diet-exercise skills read them through the same fhir_search they already use.

  • Open Wearables sidecar (the-momentum/open-wearables, MIT) runs under a new wearables docker-compose profile. It owns per-provider OAuth; we own the FHIR mapping.
  • r6/wearables/mapper.py translates 13 metrics to LOINC + UCUM FHIR Observations. Unknown fields fall through with code.text — no data loss.
  • Daemon poller syncs every WEARABLES_POLL_INTERVAL (default 900s), posts through /Bundle/$ingest-context with step-up + X-Agent-Id: wearable-sync.
  • wearables_sync_status MCP tool (16 tools total) returns connection status + _meta.ui.resourceUri pointing at the new Connection Manager MCP App.
  • MCP App at /r6/fhir/mcp-apps/wearables/ — cards per provider: connect / re-auth / sync / view.

Quick start: OPEN_WEARABLES_URL=http://open-wearables:8000 docker-compose --profile wearables up -d.

Install dependencies

uv sync

Playwright end-to-end tests (UI + API, requires Flask on :5000)

cd e2e && npm ci && npx playwright install --with-deps chromium && npm test cd e2e && npm run test:headed # headed browser cd e2e && npm run test:ui # interactive UI mode ```

What's new in v1.2.0 — Compiled Truth

Every other health tool shows you data. HealthClaw shows you the trail.

  • GET /<type>/<id>/$compiled-truth — returns current redacted resource + curation state + quality score + full Provenance timeline (newest first).
  • fhir_compiled_truth MCP tool — agents call this before making resource-specific claims; responses carry _meta.ui.resourceUri pointing to an embeddable review surface.
  • MCP App at /r6/fhir/mcp-apps/compiled-truth/<type>/<id> — focused HTML page: current data, evidence timeline, approve / re-evaluate actions. Zero install.
  • Activated schema — curation_state (raw → in_review → curated) and quality_score (0.0–1.0) now persisted on every resource.
  • .health-context.yaml — single declaration of jurisdiction, audience, regulations, defaults. Read by the guardrail stack; mirrored in SmartHealthConnect.

Install as a Claude Plugin

HealthClaw ships as a Claude Code plugin marketplace. Two plugins are available:

```bash

Install the FHIR guardrail plugin (this repo)

claude plugin install healthclaw-guardrails@healthclaw-marketplace

Install the personal-health companion plugin (SmartHealthConnect)

claude plugin install smarthealthconnect@healthclaw-marketplace ```

PluginSkillsSource
healthclaw-guardrailscuratr, fasten-connect, fhir-r6-guardrails, fhir-upstream-proxy, healthex-export, phi-redaction[aks129/HealthClawGuardrails](https://github.com/aks129/HealthClawGuardrails)
smarthealthconnectcare-completion, diet-exercise, healthy-habits, kids-health, medication-refills, research-monitor[aks129/SmartHealthConnect](https://github.com/aks129/SmartHealthConnect)

Each skill is auto-discoverable — Claude loads it when your prompt matches the skill's trigger phrases (e.g. "check my care gaps", "redact this bundle", "run Curatr on my conditions").

Not on Claude/MCP? The same 23 guardrailed tools run on OpenAI, Gemini, LangChain, or plain HTTP via the framework-neutral bridge in adapters/ — see Recipe: run HealthClaw tools on any agent framework. Guardrails stay server-side, so no framework can bypass them.

Docker

```bash docker-compose up -d --build

Railway Deploy

```bash

5. Deploy — MUST run from the shl-server directory

cd services/shl-server && railway up --service shl-server

Quick Start

```bash

Quick Start (local)

```bash

Guardrail Demo

The 6-step demo at /r6/fhir/demo/agent-loop shows the full guardrail sequence:

  1. PHI Redaction — Agent reads a patient, receives redacted data
  2. $validate Gate — Agent proposes an Observation, validated before write
  3. Permission Deny — No Permission rule exists, access denied with reasoning
  4. Permission Permit — Permit rule created, re-evaluation succeeds
  5. Step-up + Human-in-the-loop — Write requires both token and human confirmation
  6. Commit + Audit — Write succeeds, full audit trail generated

Add to services/agent-orchestrator/.env or export:

export SHL_SERVER_URL=http://localhost:8000 ```

Without SHL_SERVER_URL, shl_generate returns an explicit simulation stub (simulated: true) — never a fake link.

3. Configure the SHL server

railway variables --service shl-server \ --set BASE_URL=<public-url-of-shl-server> \ --set DB_PATH=/data/db.sqlite

Environment Variables

VariableRequiredDefaultDescription
STEP_UP_SECRETProduction—HMAC-SHA256 signing secret
FHIR_UPSTREAM_URLNo—Upstream FHIR server (enables proxy mode)
SQLALCHEMY_DATABASE_URIProductionsqlite:///mcp_server.dbDatabase connection
SESSION_SECRETNo(dev key)Flask session secret
FHIR_UPSTREAM_TIMEOUTNo15Upstream request timeout (seconds)
FHIR_LOCAL_BASE_URLNo—Local URL for response URL rewriting

4. Set up Fasten Connect (optional)

```bash

.env additions

FASTEN_PUBLIC_KEY=<key> FASTEN_PRIVATE_KEY=<key> FASTEN_WEBHOOK_SECRET=<secret> FASTEN_CURATR_SCAN=true # auto-run Curatr after each import ```

Records arrive via webhook at /r6/fasten/webhook and are stored under the patient's canonical tenant ID.

6. Telegram bot (optional)

TELEGRAM_BOT_TOKEN=<token> TENANT_ID=my-patient \
FHIR_BASE_URL=http://localhost:5000/r6/fhir \
python openclaw/bot.py

Commands: /health, /conditions, /labs, /curatr, /curatr fix, /approve.

Or via Docker Compose:

docker-compose --profile openclaw up -d

7. Use Medplum as the backing FHIR store (optional)

Set in .env (leave FHIR_UPSTREAM_URL empty):

MEDPLUM_BASE_URL=https://api.medplum.com/fhir/R4
MEDPLUM_CLIENT_ID=<id>
MEDPLUM_CLIENT_SECRET=<secret>

All guardrails apply to Medplum responses identically to local SQLite mode. Access tokens are cached in Redis (key medplum:access_token; falls back to in-process cache when Redis is unavailable).

---

API Endpoints

EndpointMethodDescription
/r6/fhir/metadataGETCapabilityStatement
/r6/fhir/healthGETLiveness probe (reports upstream status)
/r6/fhir/{type}POSTCreate resource (requires step-up)
/r6/fhir/{type}GETSearch resources
/r6/fhir/{type}/{id}GETRead resource (redacted)
/r6/fhir/{type}/{id}PUTUpdate resource (requires step-up + ETag)
/r6/fhir/{type}/$validatePOSTValidate resource
/r6/fhir/Questionnaire[/{id}]/$populatePOSTSDC — pre-fill a QuestionnaireResponse from a subject
/r6/fhir/QuestionnaireResponse/$extractPOSTSDC — extract a transaction Bundle (?dryRun=true to preview)
/r6/fhir/{type}/{id}/$deidentifyGETHIPAA Safe Harbor de-identification
/r6/fhir/Observation/$statsGETObservation statistics
/r6/fhir/Observation/$lastnGETMost recent observations
/r6/fhir/Permission/$evaluatePOSTR6 access control evaluation
/r6/fhir/SubscriptionTopic/$listGETSubscription topic discovery
/r6/fhir/Bundle/$ingest-contextPOSTBundle ingestion + context envelope
/r6/fhir/context/{id}GETRetrieve context envelope
/r6/fhir/AuditEventGETSearch audit events
/r6/fhir/AuditEvent/$exportGETExport audit trail (NDJSON/Bundle)
/r6/fhir/demo/agent-loopPOST6-step guardrail demo
/r6/fhir/oauth/**OAuth 2.1 + PKCE + SMART discovery
/r6/fhir/{type}/{id}/$curatr-evaluateGETEvaluate resource data quality (Curatr)
/r6/fhir/{type}/{id}/$curatr-apply-fixPOSTApply patient-approved fixes with Provenance

Comparison

FeatureThis ProjectAWS HealthLake MCPMedplum MCPRaw FHIR API
Works with any FHIR serverYesHealthLake onlyMedplum onlyN/A
PHI redaction on readsYesNoNoNo
Immutable audit trailYesCloudTrail (separate)PartialNo
Step-up auth for writesYesIAM (separate)Medplum authNo
Human-in-the-loopYesNoNoNo
Permission $evaluate (R6)YesNoNoNo
Setup time10 seconds30+ minutes15+ minutesVaries
🎯 aiskill88 AI 点评 A 级 2026-07-03

开源AI安全层，保护临床数据安全，代码质量高

📚 实用指南（长尾问题）
适合谁
  • 需要 HealthClawGuardrails 解决具体问题的开发者与运营人员
最佳实践
  • 先在测试环境跑通最小用例，再接入生产数据
常见错误
  • API key 直接提交到 git 仓库（请用 .env 并加入 .gitignore）
  • Python 依赖冲突：建议用 venv / uv 隔离环境
部署方案
  • 云端托管：可放在 Vercel / Railway / Fly.io 等 PaaS 平台
相关搜索
HealthClawGuardrails 中文教程HealthClawGuardrails 安装报错怎么办HealthClawGuardrails 与同类工具对比HealthClawGuardrails 最佳实践HealthClawGuardrails 适合谁用

⚡ 核心功能

👥 适合谁
  • 需要 HealthClawGuardrails 解决具体问题的开发者与运营人员
⭐ 最佳实践
  • 先在测试环境跑通最小用例，再接入生产数据
⚠️ 常见错误
  • API key 直接提交到 git 仓库（请用 .env 并加入 .gitignore）
  • Python 依赖冲突：建议用 venv / uv 隔离环境

👥 适合人群

自动化工程师和运维人员项目经理和业务分析师希望减少重复性工作的专业人士数字化转型团队

🎯 使用场景

  • 自动化日常重复性工作，将精力集中于创造性任务
  • 构建数据采集 → 处理 → 输出的完整自动化管线
  • 实现跨平台、跨系统的数据流转和业务协同

⚖️ 优点与不足

✅ 优点
  • +MIT 协议，可免费商用
  • +大幅减少重复性人工操作
  • +可视化流程，清晰直观
  • +可扩展性强，支持复杂场景
⚠️ 不足
  • −初始配置和调试需投入一定时间
  • −强依赖外部服务的稳定性
  • −复杂场景需具备一定技术基础
⚠️ 使用须知

AI Skill Hub 为第三方内容聚合平台，本页面信息基于公开数据整理，不对工具功能和质量作任何法律背书。

建议在沙箱或测试环境中充分验证后，再部署至生产环境，并做好必要的安全评估。

📄 License 说明

✅ MIT 协议 — 最宽松的开源协议之一，可自由商用、修改、分发，仅需保留版权声明。

🔗 相关工具推荐

LLM资源合集（精选）
精选100+可直接运行的AI Agent和RAG应用集合。包含完整工作流示例、智能代理框架和检索增强生成系统。适合AI开
LangChain AI开发框架
Agent工作流
ai-agents-for-beginners Agent工作流
微软官方开源项目，提供12堂系统课程学习AI智能体框架。涵盖工作流设计、RAG检索增强、多智能体协作等核心技能。适合AI
n8n AI工作流自动化
Agent工作流
🧩 你可能还需要
基于当前 Skill 的能力图谱，自动补全的工具组合
natively-cluely-ai-assistant — Claude Skill 中文使用文档
免费开源的AI面试助手，实时转录，隐蔽模式，局部RAG，BYOK。无订阅，防止数据泄露。
技能寻求者
MCP · Agent · 工作流
gptme Agent工作流
MCP · Agent · 工作流
LEANN AI技能包
MCP · Agent · 工作流
Synthadoc
MCP · Agent · 工作流
kb-arena开源AI工作流
kb-arena是开源的AI工作流，用于Benchmark 9 retrieval architectures（向量、上下文、QnA、知识图

❓ 常见问题 FAQ

请参考官方文档
💡 AI Skill Hub 点评

经综合评估，HealthClawGuardrails 在Agent工作流赛道中表现稳健，质量优秀。如果你已有明确的使用需求，可以直接上手体验；如果还在评估阶段，建议对比同类工具后再做决策。

⬇️ 获取与下载
⬇ 下载源码 ZIP

✅ MIT 协议 · 可免费商用 · 直接从 aiskill88 服务器下载，无需跳转 GitHub

📚 深入学习 HealthClawGuardrails
查看分步骤安装教程和完整使用指南，快速上手这款工具
⚙️ 安装教程 📚 使用教程
🌐 原始信息
原始名称 HealthClawGuardrails
原始描述 开源AI工作流：The security layer between AI agents and clinical data. A healthclaw.io open sou。⭐20 · Python
Topics healthaihealthcarepythonsecurity
GitHub https://github.com/aks129/HealthClawGuardrails
License MIT
语言 Python
🔗 原始来源
🐙 GitHub 仓库  https://github.com/aks129/HealthClawGuardrails 🌐 官方网站  https://www.healthclaw.io

收录时间：2026-07-03 · 更新时间：2026-07-03 · License：MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。

📺 订阅 AI Skill Hub Daily Telegram 频道
每天 8 条精选 AI Skill、MCP、Agent 与自动化工具推送
加入频道 →