Rank
70
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
Traction
No public download signal
Freshness
Updated 2d ago
Crawler Summary
与腾讯云 ADP (AI Dialog Platform) 平台进行 HTTP SSE 流式对话对接 --- name: adp-integration description: 与腾讯云 ADP (AI Dialog Platform) 平台进行 HTTP SSE 流式对话对接 version: 1.0.0 author: xiaoyuan-no1-888 tags: - adp - ai-agent - sse - chat - integration category: integration --- ADP 平台对接 Skill 📚 文档导航 - **$1** - 完整的 ADP HTTP SSE 对接 API 文档 - 包含所有请求参数、返回事件、错误码的详细说明 - 来源:https://www.tencentcloud.com/zh/document/product/1254/69979 - 如需查询 API 细节,请查看此文档 --- 📋 Skill 概述 本 Skill 提供了与腾讯云 ADP(AI Dia Capability contract not published. No trust telemetry is available yet. Last updated 4/15/2026.
Freshness
Last checked 4/15/2026
Best For
adp-integration is best for general automation workflows where OpenClaw compatibility matters.
Not Ideal For
Contract metadata is missing or unavailable for deterministic execution.
Evidence Sources Checked
editorial-content, GITHUB OPENCLEW, runtime-metrics, public facts pack
与腾讯云 ADP (AI Dialog Platform) 平台进行 HTTP SSE 流式对话对接 --- name: adp-integration description: 与腾讯云 ADP (AI Dialog Platform) 平台进行 HTTP SSE 流式对话对接 version: 1.0.0 author: xiaoyuan-no1-888 tags: - adp - ai-agent - sse - chat - integration category: integration --- ADP 平台对接 Skill 📚 文档导航 - **$1** - 完整的 ADP HTTP SSE 对接 API 文档 - 包含所有请求参数、返回事件、错误码的详细说明 - 来源:https://www.tencentcloud.com/zh/document/product/1254/69979 - 如需查询 API 细节,请查看此文档 --- 📋 Skill 概述 本 Skill 提供了与腾讯云 ADP(AI Dia
Public facts
4
Change events
1
Artifacts
0
Freshness
Apr 15, 2026
Capability contract not published. No trust telemetry is available yet. Last updated 4/15/2026.
Trust score
Unknown
Compatibility
OpenClaw
Freshness
Apr 15, 2026
Vendor
Xiaoyuanno1
Artifacts
0
Benchmarks
0
Last release
Unpublished
Key links, install path, and a quick operational read before the deeper crawl record.
Summary
Capability contract not published. No trust telemetry is available yet. Last updated 4/15/2026.
Setup snapshot
git clone https://github.com/XiaoyuanNO1/adp-integration-skill.gitSetup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.
Everything public we have scraped or crawled about this agent, grouped by evidence type with provenance.
Vendor
Xiaoyuanno1
Protocol compatibility
OpenClaw
Handshake status
UNKNOWN
Crawlable docs
6 indexed pages on the official domain
Merged public release, docs, artifact, benchmark, pricing, and trust refresh events.
Extracted files, examples, snippets, parameters, dependencies, permissions, and artifact metadata.
Extracted files
0
Examples
6
Snippets
0
Languages
typescript
Parameters
python
from adp_client import create_client
# 创建客户端(需要提供 AppKey)
client = create_client(
app_key="YOUR_APP_KEY",
session_id="user_session_001", # 可选,默认自动生成
visitor_biz_id="user_001" # 可选,默认自动生成
)python
# 发送消息并获取回复
response = client.chat("你好,请介绍一下自己")
print(response)
# 记得关闭连接
client.close()python
# 实时接收 AI 回复
for event in client.chat_stream("讲一个故事"):
if event.event_type == "reply":
print(event.reply_content, end="", flush=True)
elif event.event_type == "token_stat":
print(f"\n[Token 统计: {event.data}]")
client.close()python
# 自动保持上下文
client.chat("我今年17岁")
response = client.chat("我可以开户炒股吗?") # AI 会记住你的年龄
print(response)
client.close()python
# 设置角色指令
client.set_system_role("你是一个专业的金融顾问,请用专业术语回答问题")
response = client.chat("什么是股票?")
print(response)
client.close()python
client = create_client(
app_key: str, # 必需:ADP 应用密钥
session_id: str = None, # 可选:会话 ID(2-64字符)
visitor_biz_id: str = None, # 可选:访客 ID
streaming_throttle: int = 5, # 可选:流式回复频率(默认5,建议≤100)
incremental: bool = False, # 可选:是否增量输出
model_name: str = None, # 可选:指定模型(如 DeepSeek-V3)
custom_variables: dict = None # 可选:自定义参数(工作流场景)
)Full documentation captured from public sources, including the complete README when available.
Docs source
GITHUB OPENCLEW
Editorial quality
ready
与腾讯云 ADP (AI Dialog Platform) 平台进行 HTTP SSE 流式对话对接 --- name: adp-integration description: 与腾讯云 ADP (AI Dialog Platform) 平台进行 HTTP SSE 流式对话对接 version: 1.0.0 author: xiaoyuan-no1-888 tags: - adp - ai-agent - sse - chat - integration category: integration --- ADP 平台对接 Skill 📚 文档导航 - **$1** - 完整的 ADP HTTP SSE 对接 API 文档 - 包含所有请求参数、返回事件、错误码的详细说明 - 来源:https://www.tencentcloud.com/zh/document/product/1254/69979 - 如需查询 API 细节,请查看此文档 --- 📋 Skill 概述 本 Skill 提供了与腾讯云 ADP(AI Dia
name: adp-integration description: 与腾讯云 ADP (AI Dialog Platform) 平台进行 HTTP SSE 流式对话对接 version: 1.0.0 author: xiaoyuan-no1-888 tags:
本 Skill 提供了与腾讯云 ADP(AI Dialog Platform)平台的完整对接能力,支持通过 HTTP SSE(Server-Sent Events)协议进行流式对话交互。
核心功能:
from adp_client import create_client
# 创建客户端(需要提供 AppKey)
client = create_client(
app_key="YOUR_APP_KEY",
session_id="user_session_001", # 可选,默认自动生成
visitor_biz_id="user_001" # 可选,默认自动生成
)
# 发送消息并获取回复
response = client.chat("你好,请介绍一下自己")
print(response)
# 记得关闭连接
client.close()
# 实时接收 AI 回复
for event in client.chat_stream("讲一个故事"):
if event.event_type == "reply":
print(event.reply_content, end="", flush=True)
elif event.event_type == "token_stat":
print(f"\n[Token 统计: {event.data}]")
client.close()
# 自动保持上下文
client.chat("我今年17岁")
response = client.chat("我可以开户炒股吗?") # AI 会记住你的年龄
print(response)
client.close()
# 设置角色指令
client.set_system_role("你是一个专业的金融顾问,请用专业术语回答问题")
response = client.chat("什么是股票?")
print(response)
client.close()
create_client() - 创建客户端client = create_client(
app_key: str, # 必需:ADP 应用密钥
session_id: str = None, # 可选:会话 ID(2-64字符)
visitor_biz_id: str = None, # 可选:访客 ID
streaming_throttle: int = 5, # 可选:流式回复频率(默认5,建议≤100)
incremental: bool = False, # 可选:是否增量输出
model_name: str = None, # 可选:指定模型(如 DeepSeek-V3)
custom_variables: dict = None # 可选:自定义参数(工作流场景)
)
chat() - 简单对话response = client.chat(
message: str, # 必需:消息内容
request_id: str = None # 可选:请求 ID(用于消息追踪)
) -> str
返回:完整的 AI 回复文本
chat_stream() - 流式对话for event in client.chat_stream(
message: str, # 必需:消息内容
request_id: str = None # 可选:请求 ID
):
# 处理事件
pass
返回:ChatMessage 事件流(迭代器)
set_system_role() - 设置角色指令client.set_system_role(role: str)
close() - 关闭连接client.close()
| 属性 | 类型 | 说明 |
|------|------|------|
| event_type | str | 事件类型:reply、reference、token_stat、thought、error |
| data | dict | 原始事件数据 |
| reply_content | str | 回复内容(仅 reply 事件) |
| is_final | bool | 是否为最终回复 |
| record_id | str | 消息唯一 ID |
| is_evil | bool | 是否命中敏感内容 |
| reply_method | int | 回复方式(1=大模型,2=未知问题等) |
reply - 回复事件(核心)包含 AI 的回复内容,支持流式输出。
if event.event_type == "reply":
print(event.reply_content)
if event.is_final:
print("回复完成")
reference - 参考来源事件包含 AI 回复的参考来源信息。
if event.event_type == "reference":
print(f"参考来源: {event.data}")
token_stat - Token 统计事件包含 Token 使用统计信息。
if event.event_type == "token_stat":
print(f"Token 统计: {event.data}")
thought - 思考事件(DeepSeek-R1 专属)包含模型的思考过程(仅 DeepSeek-R1 模型)。
if event.event_type == "thought":
print(f"思考过程: {event.data}")
error - 错误事件包含错误信息。
if event.event_type == "error":
print(f"错误: {event.data}")
from adp_client import create_client
def customer_service_bot(app_key, user_id):
"""客服机器人"""
client = create_client(
app_key=app_key,
visitor_biz_id=user_id
)
print("客服机器人已启动,输入 'quit' 退出")
while True:
user_input = input("用户: ")
if user_input.lower() == 'quit':
break
response = client.chat(user_input)
print(f"客服: {response}\n")
client.close()
def streaming_chat(app_key, message):
"""实时流式输出"""
client = create_client(app_key=app_key)
print("AI: ", end="", flush=True)
for event in client.chat_stream(message):
if event.event_type == "reply":
print(event.reply_content, end="", flush=True)
print() # 换行
client.close()
def financial_advisor(app_key):
"""金融顾问助手"""
client = create_client(app_key=app_key)
# 设置专业角色
client.set_system_role(
"你是一个专业的金融顾问,拥有10年以上的投资经验。"
"请用专业但易懂的语言回答用户的金融问题。"
)
while True:
question = input("请问: ")
if not question:
break
answer = client.chat(question)
print(f"\n顾问: {answer}\n")
client.close()
def batch_qa(app_key, questions):
"""批量问答"""
client = create_client(app_key=app_key)
results = []
for q in questions:
try:
answer = client.chat(q)
results.append({
"question": q,
"answer": answer,
"status": "success"
})
except Exception as e:
results.append({
"question": q,
"answer": None,
"status": "error",
"error": str(e)
})
client.close()
return results
client = create_client(
app_key="YOUR_KEY",
model_name="DeepSeek-V3" # 指定模型
)
client = create_client(
app_key="YOUR_KEY",
streaming_throttle=10 # 每10个字返回一次(默认5)
)
client = create_client(
app_key="YOUR_KEY",
incremental=True # 启用增量输出
)
# 增量模式下,每次只返回新增的内容
for event in client.chat_stream("讲个故事"):
if event.event_type == "reply":
print(event.reply_content, end="", flush=True)
client = create_client(
app_key="YOUR_KEY",
custom_variables={
"user_level": "vip",
"language": "zh-CN"
}
)
from adp_client import create_client
client = create_client(app_key="YOUR_KEY")
try:
response = client.chat("你好")
print(response)
except Exception as e:
if "401" in str(e):
print("认证失败,请检查 AppKey")
elif "timeout" in str(e).lower():
print("请求超时,请稍后重试")
else:
print(f"发生错误: {e}")
finally:
client.close()
重要:ADP 平台返回的内容是 UTF-8 编码,adp_client.py 已经正确处理了编码问题。
# adp_client.py 中已经正确设置了编码
response = requests.post(
url,
json=payload,
headers={"Content-Type": "application/json; charset=utf-8"},
stream=True,
timeout=30
)
# SSE 流式数据使用 UTF-8 解码
for line in response.iter_lines(decode_unicode=True):
# decode_unicode=True 确保正确解码 UTF-8
if line:
# 处理中文等多字节字符
...
如果你在使用过程中仍然遇到乱码,可以尝试以下方法:
方法 1:确保终端支持 UTF-8
import sys
import io
# 设置标准输出为 UTF-8
sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='utf-8')
# 然后正常使用
client = create_client(app_key="YOUR_KEY")
response = client.chat("你好")
print(response) # 不会乱码
client.close()
方法 2:显式编码转换(通常不需要)
# 如果返回的内容是 bytes 类型(正常情况下不会)
if isinstance(response, bytes):
response = response.decode('utf-8')
print(response)
方法 3:文件写入时指定编码
# 将对话结果保存到文件
client = create_client(app_key="YOUR_KEY")
response = client.chat("你好")
# 写入文件时指定 UTF-8 编码
with open("chat_result.txt", "w", encoding="utf-8") as f:
f.write(response)
client.close()
| 问题现象 | 可能原因 | 解决方案 |
|---------|---------|---------|
| 中文显示为 \u4e2d\u6587 | JSON 未正确解码 | 使用 json.loads() 而非 eval() |
| 中文显示为 ??? 或乱码 | 终端不支持 UTF-8 | 设置终端编码或使用方法 1 |
| 部分中文乱码 | 多字节字符被截断 | 确保使用 decode_unicode=True |
| 写入文件后乱码 | 文件编码不是 UTF-8 | 使用 open(..., encoding='utf-8') |
from adp_client import create_client
client = create_client(app_key="YOUR_KEY")
# 测试中文处理
test_messages = [
"你好",
"测试中文编码",
"emoji 测试 😊🎉",
"特殊字符:©®™€£¥"
]
for msg in test_messages:
response = client.chat(msg)
print(f"问: {msg}")
print(f"答: {response}")
print(f"编码: {response.encode('utf-8')}") # 查看字节编码
print("-" * 50)
client.close()
import requests
# 修改默认超时时间
client = create_client(app_key="YOUR_KEY")
# 在 chat_stream 中,超时设置为 30 秒
# 运行完整测试套件
python3 test_adp.py
# 运行交互式演示
python3 quick_start.py
# 测试特定问题
python3 test_stock_question.py
本 Skill 实现了完整的 SSE(Server-Sent Events)协议解析,特别处理了 ADP 平台的特殊格式:
data: 字段可能跨多行,后续行不带 data: 前缀is_from_self=true),需要过滤HTTP Request → SSE Stream → Event Parser → Message Handler → User
↓ ↓ ↓ ↓
POST /chat event:reply parse JSON filter self return
data:{...} extract messages content
session_id 和 visitor_biz_idis_evil 字段,过滤敏感内容import os
# 推荐:从环境变量读取
app_key = os.environ.get("ADP_APP_KEY")
client = create_client(app_key=app_key)
try:
response = client.chat("你好")
# 检查敏感内容
if hasattr(response, 'is_evil') and response.is_evil:
print("内容包含敏感信息")
finally:
client.close()
https://wss.lke.tencentcloud.com/v1/qbot/chat/sseadp_client.py - 核心客户端库test_adp.py - 完整测试套件quick_start.py - 快速开始示例README.md - 项目说明from contextlib import contextmanager
from adp_client import create_client
@contextmanager
def adp_session(app_key):
"""上下文管理器,自动管理连接"""
client = create_client(app_key=app_key)
try:
yield client
finally:
client.close()
# 使用
with adp_session("YOUR_KEY") as client:
response = client.chat("你好")
print(response)
# 自动关闭连接
import asyncio
from concurrent.futures import ThreadPoolExecutor
def chat_task(app_key, message):
"""单个对话任务"""
client = create_client(app_key=app_key)
try:
return client.chat(message)
finally:
client.close()
async def batch_chat_async(app_key, messages):
"""异步批量对话"""
loop = asyncio.get_event_loop()
with ThreadPoolExecutor(max_workers=5) as executor:
tasks = [
loop.run_in_executor(executor, chat_task, app_key, msg)
for msg in messages
]
results = await asyncio.gather(*tasks)
return results
# 使用
messages = ["问题1", "问题2", "问题3"]
results = asyncio.run(batch_chat_async("YOUR_KEY", messages))
import logging
from adp_client import create_client
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)
def logged_chat(app_key, message):
"""带日志的对话"""
client = create_client(app_key=app_key)
try:
logger.info(f"发送消息: {message}")
response = client.chat(message)
logger.info(f"收到回复: {response[:100]}...")
return response
except Exception as e:
logger.error(f"对话失败: {e}")
raise
finally:
client.close()
# 推荐:复用同一个客户端进行多次对话
client = create_client(app_key="YOUR_KEY")
for i in range(10):
response = client.chat(f"问题 {i+1}")
print(response)
client.close() # 最后统一关闭
# 对于长文本,使用流式输出可以更快地看到结果
for event in client.chat_stream("写一篇长文章"):
if event.event_type == "reply":
print(event.reply_content, end="", flush=True)
本 Skill 提供了与 ADP 平台的完整对接能力,经过充分测试,可直接用于生产环境。支持简单对话、流式响应、多轮对话、自定义角色等功能,满足各种对话场景需求。
关键特性:
开始使用吧!🚀
Machine endpoints, protocol fit, contract coverage, invocation examples, and guardrails for agent-to-agent use.
Contract coverage
Status
missing
Auth
None
Streaming
No
Data region
Unspecified
Protocol support
Requires: none
Forbidden: none
Guardrails
Operational confidence: low
curl -s "https://xpersona.co/api/v1/agents/xiaoyuanno1-adp-integration-skill/snapshot"
curl -s "https://xpersona.co/api/v1/agents/xiaoyuanno1-adp-integration-skill/contract"
curl -s "https://xpersona.co/api/v1/agents/xiaoyuanno1-adp-integration-skill/trust"
Trust and runtime signals, benchmark suites, failure patterns, and practical risk constraints.
Trust signals
Handshake
UNKNOWN
Confidence
unknown
Attempts 30d
unknown
Fallback rate
unknown
Runtime metrics
Observed P50
unknown
Observed P95
unknown
Rate limit
unknown
Estimated cost
unknown
Do not use if
Every public screenshot, visual asset, demo link, and owner-provided destination tied to this agent.
Neighboring agents from the same protocol and source ecosystem for comparison and shortlist building.
Rank
70
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
Traction
No public download signal
Freshness
Updated 2d ago
Rank
70
AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs
Traction
No public download signal
Freshness
Updated 6d ago
Rank
70
Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!
Traction
No public download signal
Freshness
Updated 6d ago
Rank
70
The Frontend for Agents & Generative UI. React + Angular
Traction
No public download signal
Freshness
Updated 23d ago
Contract JSON
{
"contractStatus": "missing",
"authModes": [],
"requires": [],
"forbidden": [],
"supportsMcp": false,
"supportsA2a": false,
"supportsStreaming": false,
"inputSchemaRef": null,
"outputSchemaRef": null,
"dataRegion": null,
"contractUpdatedAt": null,
"sourceUpdatedAt": null,
"freshnessSeconds": null
}Invocation Guide
{
"preferredApi": {
"snapshotUrl": "https://xpersona.co/api/v1/agents/xiaoyuanno1-adp-integration-skill/snapshot",
"contractUrl": "https://xpersona.co/api/v1/agents/xiaoyuanno1-adp-integration-skill/contract",
"trustUrl": "https://xpersona.co/api/v1/agents/xiaoyuanno1-adp-integration-skill/trust"
},
"curlExamples": [
"curl -s \"https://xpersona.co/api/v1/agents/xiaoyuanno1-adp-integration-skill/snapshot\"",
"curl -s \"https://xpersona.co/api/v1/agents/xiaoyuanno1-adp-integration-skill/contract\"",
"curl -s \"https://xpersona.co/api/v1/agents/xiaoyuanno1-adp-integration-skill/trust\""
],
"jsonRequestTemplate": {
"query": "summarize this repo",
"constraints": {
"maxLatencyMs": 2000,
"protocolPreference": [
"OPENCLEW"
]
}
},
"jsonResponseTemplate": {
"ok": true,
"result": {
"summary": "...",
"confidence": 0.9
},
"meta": {
"source": "GITHUB_OPENCLEW",
"generatedAt": "2026-04-17T03:33:28.745Z"
}
},
"retryPolicy": {
"maxAttempts": 3,
"backoffMs": [
500,
1500,
3500
],
"retryableConditions": [
"HTTP_429",
"HTTP_503",
"NETWORK_TIMEOUT"
]
}
}Trust JSON
{
"status": "unavailable",
"handshakeStatus": "UNKNOWN",
"verificationFreshnessHours": null,
"reputationScore": null,
"p95LatencyMs": null,
"successRate30d": null,
"fallbackRate": null,
"attempts30d": null,
"trustUpdatedAt": null,
"trustConfidence": "unknown",
"sourceUpdatedAt": null,
"freshnessSeconds": null
}Capability Matrix
{
"rows": [
{
"key": "OPENCLEW",
"type": "protocol",
"support": "unknown",
"confidenceSource": "profile",
"notes": "Listed on profile"
}
],
"flattenedTokens": "protocol:OPENCLEW|unknown|profile"
}Facts JSON
[
{
"factKey": "docs_crawl",
"category": "integration",
"label": "Crawlable docs",
"value": "6 indexed pages on the official domain",
"href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
"sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
"sourceType": "search_document",
"confidence": "medium",
"observedAt": "2026-04-15T05:03:46.393Z",
"isPublic": true
},
{
"factKey": "vendor",
"category": "vendor",
"label": "Vendor",
"value": "Xiaoyuanno1",
"href": "https://github.com/XiaoyuanNO1/adp-integration-skill",
"sourceUrl": "https://github.com/XiaoyuanNO1/adp-integration-skill",
"sourceType": "profile",
"confidence": "medium",
"observedAt": "2026-04-15T02:12:32.377Z",
"isPublic": true
},
{
"factKey": "protocols",
"category": "compatibility",
"label": "Protocol compatibility",
"value": "OpenClaw",
"href": "https://xpersona.co/api/v1/agents/xiaoyuanno1-adp-integration-skill/contract",
"sourceUrl": "https://xpersona.co/api/v1/agents/xiaoyuanno1-adp-integration-skill/contract",
"sourceType": "contract",
"confidence": "medium",
"observedAt": "2026-04-15T02:12:32.377Z",
"isPublic": true
},
{
"factKey": "handshake_status",
"category": "security",
"label": "Handshake status",
"value": "UNKNOWN",
"href": "https://xpersona.co/api/v1/agents/xiaoyuanno1-adp-integration-skill/trust",
"sourceUrl": "https://xpersona.co/api/v1/agents/xiaoyuanno1-adp-integration-skill/trust",
"sourceType": "trust",
"confidence": "medium",
"observedAt": null,
"isPublic": true
}
]Change Events JSON
[
{
"eventType": "docs_update",
"title": "Docs refreshed: Sign in to GitHub · GitHub",
"description": "Fresh crawlable documentation was indexed for the official domain.",
"href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
"sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
"sourceType": "search_document",
"confidence": "medium",
"observedAt": "2026-04-15T05:03:46.393Z",
"isPublic": true
}
]Sponsored
Ads related to adp-integration and adjacent AI workflows.