Token导航 LogoToken导航TokenDH.com
开发敏感数据github未标认证来源可访问许可证需确认审计异常

omi-api-integrationOMI API 集成

Agent Skill

用于辅助 API 设计、接口文档、请求响应结构和服务集成说明。它适合让 Agent 梳理 endpoint、生成 OpenAPI 草稿、检查字段命名、整理错误码或辅助前后端联调。使用时需要确认真实业务语义、鉴权方式、分页和错误处理规则;涉及生成接口文档时,应避免凭空补字段,最好从现有代码、schema 或接口样例中提取事实。

总安装

259

周安装

11

GitHub Stars

7,896

下载量

91
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:omi-api-integration(OMI API 集成)
来源仓库:https://github.com/basedhardware/omi
仓库路径:skills/omi-api-integration
安装命令:
npx skills add https://github.com/basedhardware/omi --skill omi-api-integration
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/basedhardware/omi --skill omi-api-integration

简介

用于辅助 API 设计和接口文档编写。

  • 适合梳理 endpoint、生成 OpenAPI 草稿和检查字段命名。
  • 可整理错误码和辅助前后端联调。
  • 安装命令:npx skills add https://github.com/basedhardware/omi --skill omi-api-integration
  • 需确认真实业务语义,避免凭空补字段或忽略鉴权规则

SKILL.md

Omi API Integration Skill

This skill provides guidance for integrating with Omi APIs, including Developer API, MCP server, and webhook integrations.

When to Use

Use this skill when:

  • Building integrations with Omi
  • Using the Developer API
  • Setting up MCP server
  • Creating webhook integrations
  • Working with OAuth flows

Key Patterns

Developer API

Base URL: https://api.omi.me/v1/dev

Authentication: Bearer token with omi_dev_ prefix

Getting API Key

  1. Open Omi app
  2. Settings → Developer → Create Key
  3. Copy key immediately (won't be shown again)

Making Requests

import requests

headers = {
    "Authorization": "Bearer omi_dev_your_key_here"
}

# Get memories
response = requests.get(
    "https://api.omi.me/v1/dev/user/memories",
    headers=headers,
    params={"limit": 10}
)

memories = response.json()

Available Endpoints

  • GET /v1/dev/user/memories - Get memories
  • POST /v1/dev/user/memories - Create memory
  • POST /v1/dev/user/memories/batch - Create up to 25 memories
  • GET /v1/dev/user/conversations - Get conversations
  • POST /v1/dev/user/conversations - Create conversation
  • GET /v1/dev/user/action-items - Get action items
  • POST /v1/dev/user/action-items - Create action item

MCP Server

Purpose: Enable AI assistants (like Claude) to interact with Omi data

Hosted MCP Server (SSE)

URL: https://api.omi.me/v1/mcp/sse

Authentication: Bearer token with omi_mcp_ prefix

Available Tools

  • get_memories - Retrieve memories
  • create_memory - Create a memory
  • edit_memory - Edit a memory
  • delete_memory - Delete a memory
  • get_conversations - Retrieve conversations

Configuration

{
  "mcpServers": {
    "omi": {
      "url": "https://api.omi.me/v1/mcp/sse",
      "apiKey": "omi_mcp_your_key_here"
    }
  }
}

Webhook Integrations

Memory Creation Webhook

Trigger: When a memory is created

Endpoint: POST /webhook/memory-created

Payload:

{
  "id": "memory_id",
  "content": "Memory content",
  "category": "personal",
  "user_id": "user_uid",
  "created_at": "2024-01-01T00:00:00Z"
}

Real-time Transcript Webhook

Trigger: As transcript segments arrive

Endpoint: POST /webhook/transcript

Payload:

{
  "text": "Transcript segment",
  "timestamp": 1234567890,
  "conversation_id": "conv_id",
  "user_id": "user_uid"
}

OAuth Integration

Google OAuth

  1. Create OAuth 2.0 Client in Google Cloud Console
  2. Configure authorized origins and redirect URIs
  3. Use client ID and secret in app

Apple OAuth

  1. Create App ID with Sign In with Apple
  2. Create Services ID
  3. Create private key (.p8 file)
  4. Configure in Firebase Console

Common Tasks

Creating an Integration

  1. Set up webhook endpoint
  2. Register webhook URL in app configuration
  3. Handle webhook payloads
  4. Process and react to events

Using Developer API

  1. Generate API key in Omi app
  2. Store key securely (environment variable)
  3. Make authenticated requests
  4. Handle rate limits (100/min, 10,000/day)

Setting Up MCP

  1. Generate MCP API key in Omi app
  2. Configure MCP client (Claude Desktop, etc.)
  3. Use tools to interact with Omi data

Related Documentation

The docs/ folder is the single source of truth for all user-facing documentation, deployed at docs.omi.me.

  • API Overview: docs/doc/developer/api/overview.mdx - View online
  • API Endpoints: docs/api-reference/ - View online
  • Memories API: docs/doc/developer/api/memories.mdx - View online
  • Conversations API: docs/doc/developer/api/conversations.mdx - View online
  • Action Items API: docs/doc/developer/api/action-items.mdx - View online
  • MCP: docs/doc/developer/MCP.mdx - View online
  • Plugin Development: docs/doc/developer/apps/Introduction.mdx - View online
  • OAuth: docs/doc/developer/apps/Oauth.mdx - View online

Related Cursor Resources

Rules

  • .cursor/rules/backend-api-patterns.mdc - Backend API patterns
  • .cursor/rules/backend-architecture.mdc - Backend architecture
  • .cursor/rules/plugin-development.mdc - Plugin development patterns
  • .cursor/rules/web-nextjs-patterns.mdc - Web API integration

Subagents

  • .cursor/agents/backend-api-developer/ - Uses this skill for API development
  • .cursor/agents/plugin-developer/ - Uses this skill for plugin integration
  • .cursor/agents/web-developer/ - Uses this skill for web integration
  • .cursor/agents/sdk-developer/ - Uses this skill for SDK development

Commands

  • /backend-setup - Uses this skill for API setup
  • /create-plugin - Uses this skill for plugin integration
  • /update-api-docs - Uses this skill for API documentation

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

36.85%
按下载量换算34

Claude

29.72%
按下载量换算27

Cursor

16.84%
按下载量换算15

Gemini CLI

8.64%
按下载量换算8

安全审计

Gen Agent Trust Hub

未通过

Socket

通过

Snyk

未通过

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills