畜牧助手
openclaw-livestock-assistant
by antonygiomarxdev
>
安装
- kind: node必需环境变量
OPENAI_API_KEYANTHROPIC_API_KEYGOOGLE_GENERATIVE_AI_API_KEY必需命令行工具
ts-node文档
OpenClaw Livestock Assistant
Expert livestock management assistant for Spanish-speaking farmers. Responds always in Spanish. Combines AI chat with a REST API for herd record-keeping.
Capabilities
- Herd management — register and track animals (bovine, ovine, caprine, porcine, equine, poultry)
- Animal health — vaccination schedules, disease identification, treatment guidance
- Reproduction — heat detection, pregnancy tracking, birth records, genetics
- Nutrition — ration formulation, forage selection, supplementation
- Breed advice — selection by aptitude (meat / milk / wool / dual-purpose)
- REST API — persistent record-keeping via Express server on
http://localhost:3000
Starting the API Server
Before using any REST API endpoint, start the server:
bash scripts/start.sh
The server exposes /health, /api/animals, and /api/assistant — see
references/api.md for the full endpoint reference.
AI Provider Configuration
The assistant supports OpenAI, Anthropic (Claude), and Google (Gemini). Set at least one API key; the assistant auto-selects the provider.
| Provider | API key env var | Default model |
|---|---|---|
| OpenAI | OPENAI_API_KEY | gpt-5 |
| Anthropic | ANTHROPIC_API_KEY | claude-opus-4-6 |
GOOGLE_GENERATIVE_AI_API_KEY | gemini-2.5-pro |
Override explicitly via:
AI_PROVIDER=openai|anthropic|google— force a specific providerAI_MODEL=<model-id>— override the model ID for the chosen provider
AI Chat
Every interaction should be in Spanish. Use the system prompt embedded in
src/assistant/systemPrompt.ts as the agent's knowledge baseline.
Create a session before sending messages:
curl -X POST http://localhost:3000/api/assistant/sessions
# → { "sessionId": "...", "welcome": "¡Hola! Soy el Asistente de Ganadería..." }
curl -X POST http://localhost:3000/api/assistant/sessions/<sessionId>/messages \
-H "Content-Type: application/json" \
-d '{"message": "¿Cómo prevenir la mastitis en vacas lecheras?"}'
Domain References
Load these files when you need detailed reference data:
| Reference | When to read |
|---|---|
| references/breeds.md | User asks about breeds, selection, or characteristics |
| references/diseases.md | User reports symptoms, asks about prevention or treatment |
| references/nutrition.md | User asks about feeding, rations, forages, or supplementation |
| references/api.md | User wants to register animals or retrieve herd data |
Animal Status Reference
| Field | Allowed values |
|---|---|
species | bovine ovine caprine porcine equine poultry |
sex | male female |
status | active sold dead quarantine |
healthStatus | healthy sick in_treatment recovered |
reproductiveStatus | open pregnant lactating in_heat served not_applicable |
Safety Guidelines
- Never diagnose diseases definitively — always recommend a veterinarian for emergencies.
- Zoonotic diseases (e.g., Brucelosis) must be flagged immediately.
- Urgency levels:
low→medium→high→emergency. Escalate accordingly.
相关 Skills
Claude接口
by anthropics
面向接入 Claude API、Anthropic SDK 或 Agent SDK 的开发场景,自动识别项目语言并给出对应示例与默认配置,快速搭建 LLM 应用。
✎ 想把Claude能力接进应用或智能体,用claude-api上手快、兼容Anthropic与Agent SDK,集成路径清晰又省心
RAG架构师
by alirezarezvani
聚焦生产级RAG系统设计与优化,覆盖文档切块、检索链路、索引构建、召回评估等关键环节,适合搭建可扩展、高准确率的知识库问答与检索增强应用。
✎ 面向RAG落地,把知识库、向量检索和生成链路系统串联起来,做架构设计时更清晰,也更少踩坑。
智能体流程设计
by alirezarezvani
面向生产级多 Agent 编排,梳理顺序、并行、分层、事件驱动、共识五种工作流设计,覆盖 handoff、状态管理、容错重试、上下文预算与成本优化,适合搭建复杂 AI 协作系统。
✎ 帮你把多智能体流程设计、编排和自动化统一起来,复杂工作流也能更稳地落地,适合追求强控制力的团队。
相关 MCP 服务
知识图谱记忆
编辑精选by Anthropic
Memory 是一个基于本地知识图谱的持久化记忆系统,让 AI 记住长期上下文。
✎ 帮 AI 和智能体补上“记不住”的短板,用本地知识图谱沉淀长期上下文,连续对话更聪明,数据也更可控。
顺序思维
编辑精选by Anthropic
Sequential Thinking 是让 AI 通过动态思维链解决复杂问题的参考服务器。
✎ 这个服务器展示了如何让 Claude 像人类一样逐步推理,适合开发者学习 MCP 的思维链实现。但注意它只是个参考示例,别指望直接用在生产环境里。
PraisonAI
编辑精选by mervinpraison
PraisonAI 是一个支持自反思和多 LLM 的低代码 AI 智能体框架。
✎ 如果你需要快速搭建一个能 24/7 运行的 AI 智能体团队来处理复杂任务(比如自动研究或代码生成),PraisonAI 的低代码设计和多平台集成(如 Telegram)让它上手极快。但作为非官方项目,它的生态成熟度可能不如 LangChain 等主流框架,适合愿意尝鲜的开发者。