Markdown chat
Rich Markdown rendering in assistant responses.
'use client'import { useMemo } from 'react'import { useChat, ChatContainer, InputBar } from '@agentskit/react'import '@/styles/agentskit-theme.css'import { createMockAdapter, initialAssistant } from './_shared/mock-adapter'import { MdRenderer } from './_shared/md-renderer'const TURNS = [ { text: `## Styling options in AgentsKitYou can pick from three styling modes:1. **Headless** — use the hooks and style with your design system2. **Default theme** — \`import '@/styles/agentskit-theme.css'\` for the tokenised CSS3. **Custom CSS** — target \`data-ak-*\` attributes directly| Mode | Lines | Output || --- | --- | --- || headless | ~20 | fully custom || theme | 1 | branded defaults || data-ak | a few | anywhere in between |> The \`Markdown\` component ships with support for GFM tables, task lists, and inline code.`, }, { text: `### Inline formatting- **Bold** and *italic* text- \`inline code\` with proper spacing- [Links](https://agentskit.io) that keep their styling- ~~strikethrough~~ when you need it\`\`\`tsconst muted = 'var(--color-fd-muted-foreground)'\`\`\``, },]export function MarkdownChat() { const adapter = useMemo(() => createMockAdapter(TURNS, 130), []) const chat = useChat({ adapter, initialMessages: [ initialAssistant( 'Ask me for a styled response — I stream full GitHub-flavoured Markdown.', ), ], }) return ( <div data-ak-example className="flex h-[520px] flex-col overflow-hidden rounded-lg border border-ak-border bg-ak-surface" > <ChatContainer className="flex-1 space-y-3 p-4"> {chat.messages.map((m) => ( <div key={m.id} data-ak-message data-ak-role={m.role} className="rounded-lg bg-ak-midnight/40 p-3"> <MdRenderer content={m.content} /> </div> ))} </ChatContainer> <InputBar chat={chat} /> </div> )}Basic chat
Streaming chat with a mock adapter. Zero config, runs in-browser.
streamingchatTool use
Tool-calling agent that browses a mocked product catalog.
toolschatRAG
Retrieval-augmented chat with inline source citations.
ragchatCode assistant
Code-aware chat with syntax-highlighted output.
codechatSupport bot
Chat with escalation, memory, and confirmation gates.
supportmemorytoolsMulti-agent
Planner + worker + reviewer topology.
multi-agentMulti-model
Switch providers on the fly in a single conversation.
multi-modelchatAgent actions
Streaming UI with live tool-call visualization.
toolsstreamingshadcn/ui chat
AgentsKit styled with shadcn/ui tokens.
chatdesign-systemMaterial UI chat
AgentsKit styled with MUI components.
chatdesign-systemSandbox runner
Agent-emitted code runs isolated in E2B / WebContainer.
sandboxtoolscodeObservability trace
Live span tree with tokens, latency, cost. Exports to LangSmith / OTEL.
observabilityproductionPersistent memory
Cross-session recall with sqlite, redis, or lancedb backends.
memorypersistenceEval suite
Run regression tests, track accuracy / latency / cost in CI.
evalproductionciSlack integration
Agent posts to Slack via @agentskit/tools.
integrationstoolsInk terminal
Same controller, rendered in your terminal via Ink.
inkcliterminalSkill swap
Hot-swap personas mid-conversation: researcher, critic, planner.
skillspromptsRuntime ReAct
Standalone agent runtime — no UI required. ReAct loop with tools + memory.
runtimemulti-agentProvider fanout
Same prompt across openai, anthropic, gemini, ollama. Compare quality + cost.
adaptersmulti-modelRAG with citations
Retrieve top-k chunks with scores and inline cite refs.
ragcitations