Agent Skills
› openclaw/clawhub
› convex-agent
convex-agent
GitHub为 Convex 应用集成 AI Agent 后端，支持持久化对话、工具调用及向量检索/RAG。提供安装配置、模型定义及安全密钥管理的标准化工作流与规则。
触发场景
需要为应用添加 AI 智能体功能
实现基于 RAG 的文档检索问答
配置 Convex 中的 LLM 代理后端
安装
npx skills add openclaw/clawhub --skill convex-agent -g -y
SKILL.md
Frontmatter
{
"name": "convex-agent",
"description": "Add an AI agent \/ RAG backend (@convex-dev\/agent) to the Convex app."
}
Add an AI agent / RAG backend
Install @convex-dev/agent for durable threads, message history, tool-calls, and vector search/RAG — the backend for an in-app AI agent.
Workflow
- Install @convex-dev/agent + add to convex.config.ts.
- Define the agent (model, tools, instructions); store the LLM key via the
envmicro power. - Create threads + stream messages; persist history in Convex.
- For RAG: embed docs into a vector index and retrieve in the tool.
Rules
- Keep the LLM API key in Convex env (use the
envmicro power), never client-side. - Run model calls in actions ('use node' if the SDK needs it).
- Persist threads/messages in Convex for durability + reactivity.
版本历史
- d6a8c68 当前 2026-08-20 02:43
