Blog
Articles from ThreadPlane
Writing on agent UI for Angular — production patterns, design choices, and what we're shipping.
Featured
Build an AWS Strands Agent UI in Angular with AG-UI
Connect an AWS Strands agent to an Angular chat over AG-UI SSE with Threadplane, then prepare the same server for optional AgentCore deployment.
Angular Chat App Tutorial with LangChain and LangGraph
Build a multi-thread Angular chat app on LangGraph: a conversation sidebar, server-titled threads, and bookmarkable URLs that survive a refresh.
Angular Chat App Tutorial with AG-UI
Build an Angular chat app on AG-UI where the browser owns its own tools — action, view, and ask client tools rendering real components inline, plus agent-shared state.
Agentic UI in Angular: Production Patterns After the Demo
Production patterns for agentic UI in Angular: signals, tool progress, approvals, durable threads, constrained generative UI, and recovery.
Threadplane Earns a Grade A for Trust
An independent tracker scored Threadplane's supply-chain trust at 82.8/100 — a Grade A, #7 of 75 agent frameworks, and the only Angular agent framework on the board. Here's the work behind the grade, and why it matters for agent frameworks specifically.
Human-in-the-Loop AG-UI Agents in Angular
Build a human-in-the-loop AG-UI agent in Angular — the same chat-approval-card composition from the LangGraph version, wired to an AG-UI-fronted LangGraph backend via @threadplane/ag-ui.
Human-in-the-Loop LangGraph Agents in Angular
Build a human-in-the-loop LangGraph agent in Angular — pause runs before money moves with a structured approval dialog from @threadplane/chat and @threadplane/langgraph.
Build Fullstack Agentic Angular Apps Using AG-UI
A practical, signal-native walkthrough for wiring any AG-UI backend (LangGraph, CrewAI, Mastra, Pydantic AI, Microsoft Agent Framework) to a production Angular chat UI.
Build a Streaming Chat UI in Angular with LangGraph
Step-by-step tutorial for shipping a production streaming chat in Angular — signal-native, design-system-friendly, and wired to a LangGraph backend.