關於這個工具
Threadplane 幫助 Angular 開發者將 AI 代理整合到 Angular 應用中。它提供 @threadplane/chat 和 @threadplane/langgraph 等套件,支援串流回應、工具呼叫渲染以及代理建構的 UI(A2UI)。 開發者可以透過 provideAgent({ url: 'http://localhost:8000/agent' }) 設定代理,並使用 <chat [agent]="agent" [views]="analyticsViews" /> 等元件在應用中嵌入聊天介面。 Threadplane 支援 LangGraph 代理的部署,可透過 CLI(langgraph deploy --project my-agent)或 LangSmith UI 完成。它適用於企業場景,包括合規、分析和客戶支援。
功能與使用情境
- providers: [provideAgent({ url: 'http://localhost:8000/agent' })], + import { provideAgent } from '@threadplane/langgraph'--> <chat [agent]="agent" [views]="analyticsViews" /> Field report The last-mile gap in Angular AI--push # Deploy via CLI (alternative to the LangSmith UI) pip install langgraph-cli langgraph deploy --project my-agent The CLI watches your repository and builds a container image on LangGraph Cloud', }, { label: 'How agents pick tools', value: 'Show me how an agent decides which tool to use', description: 'Agent emits a render spec', description: 'Explains tool-selection reasoning', description: 'Watch tokens arrive incrementally — the simplest @threadplane/chat integration" ) async def generate(state: MessagesState) -> dict: reply = await llm" A2UI A2UI is a wire protocol for agent-built interfaces" return {"refund_id": refund_id, "messages": [AIMessage(content=msg)]} def route_after_approval(state: RefundState) -> str: return "issue" if state""" llm = ChatOpenAI(model="gpt-5-mini", streaming=True) async def generate(state: MessagesState) -> dict: """Generate a response using the full message history""" llm = ChatOpenAI(model="gpt-5-mini", streaming=True) async def generate(state: MessagesState) -> dict: """Generate a response with conversation history preserved
快速事實
提供公開 API
支援自架
使用分析
價格模式
價格模式
免費
定價驗證於 2026年10月17日官方定價頁