From 790e5f269cddb218d7c31df51ba0d1772b4de2f4 Mon Sep 17 00:00:00 2001 From: Vincent Grobler Date: Fri, 29 May 2026 22:01:33 +0100 Subject: [PATCH] feat: add golden path quickstart --- README.md | 84 ++++++------- docs/first-agent-system.md | 113 +++++++++++++++++ docs/mint.json | 3 +- docs/quickstart.md | 4 + src/components/dashboard/DemoBanner.tsx | 117 ++++++++++++++---- .../onboarding/OnboardingWizard.tsx | 52 ++++---- src/db/demoWorkspace.ts | 48 +++---- src/hooks/useDemoWorkspace.ts | 2 + 8 files changed, 305 insertions(+), 118 deletions(-) create mode 100644 docs/first-agent-system.md diff --git a/README.md b/README.md index d32d6838..a8b80fd8 100644 --- a/README.md +++ b/README.md @@ -2,11 +2,11 @@ CrewForm -### Form your AI crew +### The open control plane for interoperable AI agents -**Open-source AI Agent Orchestration Platform β€” with all 3 agentic protocols** +**Self-hostable agent orchestration runtime with MCP + A2A + AG-UI** -The first platform with native **MCP** (Tools) + **A2A** (Agent-to-Agent) + **AG-UI** (Frontend Streaming) +CrewForm helps teams build, run, and observe multi-agent systems across tools, agents, models, memory, workflows, and frontends β€” without vendor lock-in. [![License: AGPL v3](https://img.shields.io/badge/License-AGPL_v3-blue.svg)](https://www.gnu.org/licenses/agpl-3.0) [![CI](https://github.com/CrewForm/crewform/actions/workflows/ci.yml/badge.svg)](https://github.com/CrewForm/crewform/actions/workflows/ci.yml) @@ -34,7 +34,7 @@ The first platform with native **MCP** (Tools) + **A2A** (Agent-to-Agent) + **AG
CrewForm Visual Workflow Builder -

Build AI agent pipelines visually β€” drag, connect, and watch them execute in real-time.

+

Design, run, and observe protocol-native agent workflows from one visual runtime.

@@ -82,7 +82,7 @@ The first platform with native **MCP** (Tools) + **A2A** (Agent-to-Agent) + **AG ## πŸ”Œ Protocols & Standards -CrewForm is the **first platform with native support for all three agentic protocols**: +CrewForm is a self-hostable runtime with native support for the three protocols that matter for interoperable agent systems: | Protocol | Direction | What It Does | |---|---|---| @@ -90,7 +90,7 @@ CrewForm is the **first platform with native support for all three agentic proto | **A2A** (Agent-to-Agent Protocol) | ↔️ Bidirectional | **Consume:** Delegate tasks to external A2A agents. **Publish:** Expose your agents for other AI systems to call. Cross-framework agent interop. | | **AG-UI** (Agent-User Interface) | πŸ“‘ Streaming | Real-time SSE event streaming from agent to frontend. Supports text deltas, tool calls, state transitions, and rich interactions (approval, confirmation, choices). | -> **Why this matters:** Most platforms support zero or one protocol. CrewForm gives your agents access to thousands of tools (MCP), cross-framework interop (A2A), and real-time UI streaming (AG-UI) β€” all out of the box. +> **Why this matters:** Most platforms create isolated agent workflows. CrewForm gives your agents access to external tools (MCP), cross-framework agent interop (A2A), and real-time frontend streaming (AG-UI) β€” all from one runtime layer. ## ✨ Features at a Glance @@ -275,23 +275,19 @@ npx crewform pull ## Why CrewForm? -CrewForm gives you everything you need to orchestrate multi-agent AI workflows β€” a visual UI, team management, real-time monitoring, and an agent marketplace β€” while you keep full control of your API keys, your data, and your infrastructure. - -- πŸ–₯️ **UI-First** β€” Create, configure, and monitor agents from a visual interface. No code required to get started -- πŸ”‘ **BYOK (Bring Your Own Key)** β€” Connect your own LLM provider keys. Pay your provider directly at their standard rates, zero markup -- 🏠 **Self-Hostable** β€” Deploy on your own infrastructure with Docker. Your data stays with you -- πŸ”€ **3 Orchestration Modes** β€” Pipeline (sequential), Orchestrator (brain + workers), and Collaboration (multi-agent discussion) -- πŸ”Œ **MCP Protocol** β€” Connect agents to thousands of external tool servers, **and** expose your agents as MCP tools for Claude Desktop, Cursor, and other MCP clients -- 🀝 **A2A Protocol** β€” Agent-to-Agent interoperability β€” expose agents to external AI systems and delegate tasks to remote agents -- πŸ–₯️ **AG-UI Protocol** β€” Real-time SSE event streaming for frontend integration β€” the standard for agent-to-UI communication -- πŸ“š **Knowledge Base (RAG)** β€” Upload docs (TXT, MD, CSV, JSON), auto-chunk and embed with pgvector, then search via agents -- πŸͺ **Agent Marketplace** β€” Browse and install community-built agent templates, or publish your own -- πŸ“‹ **Workflow Templates** β€” Bundle agents, teams, and triggers into reusable blueprints with `{{variable}}` placeholders; install with one click -- ⚑ **Integrations Ecosystem** β€” Zapier (7,000+ apps), Discord, Slack, Telegram, Email, webhooks, and output routes -- πŸ”’ **Secure by Default** β€” AES-256-GCM key encryption, Row-Level Security, GDPR-ready -- πŸ“Š **Built-in Analytics** β€” Track token usage, costs, and performance per agent and task +CrewForm is built as agent infrastructure, not just another workflow canvas. It gives you the runtime layer around multi-agent systems: protocols, execution, observability, deployment, memory, APIs, and visual operations. + +- πŸ”Œ **Protocol-native runtime** β€” Use MCP as a client and server, delegate across A2A, and stream agent state to frontends with AG-UI +- πŸ–₯️ **Visual control plane** β€” Design, run, debug, and monitor agents, teams, handoffs, tool calls, and execution state from a visual UI +- 🏠 **Infrastructure ownership** β€” Self-host with Docker, bring your own LLM keys, use local models with Ollama, and avoid hosted model markup +- πŸ“‘ **Runtime observability** β€” Trace LLM calls, tool usage, team runs, costs, failures, and handoffs with OpenTelemetry and Langfuse +- πŸ”€ **Flexible orchestration** β€” Run single-agent tasks, fixed pipelines, brain-and-worker orchestrators, or multi-agent collaboration threads +- πŸ“š **Knowledge and memory** β€” Add RAG, pgvector search, team memory, output templates, and file artifacts to agent workflows +- ⚑ **Integration surface** β€” Expose agents through REST APIs, webhooks, chat widgets, Zapier, messaging channels, MCP, and A2A +- πŸ”’ **Secure workspace model** β€” Encrypted API keys, Row-Level Security, workspaces, RBAC, audit logs, and usage controls +- πŸ“¦ **Portable workflows** β€” Export/import agents and teams, install templates, and package repeatable systems for clients or internal teams -CrewForm is the **first platform with all three agentic protocols** β€” MCP (tools) + A2A (agents) + AG-UI (frontend). Built for developers and teams who want production-ready AI agent orchestration. +The result is a shared control plane for teams moving from isolated agent experiments to reliable agent systems they can operate. ## How It Works @@ -310,30 +306,33 @@ CrewForm supports 4 execution modes β€” choose the right one for your workflow: ## Who It's For -### πŸ§‘ Solo User β€” Freelancer / Indie Hacker +### Platform Engineering Teams -Pick agents from the marketplace (or build your own) and throw tasks at them β€” "Research competitors for X", "Write a blog post about Y", "Review this code". Agents work in the background; you get results. +Give your organization a shared runtime for internal agents, model access, tool connections, memory, workflows, observability, and deployment. -**Daily loop:** Dispatch tasks β†’ review results β†’ ship to clients. +**Best for:** internal AI platforms, self-hosted agent infrastructure, compliance-conscious environments, and shared model/tool governance. -### πŸ‘₯ Small Team β€” Agency / Startup +### AI Product Teams -Set up a shared workspace with a crew of agents matching your workflow β€” a Researcher, a Coder, a Writer, a QA agent. Tasks get assigned, agents run in pipeline or collaboration mode, results land in one place. +Add agent workflows to real products without rebuilding orchestration, streaming, tool use, memory, and runtime APIs from scratch. -**Daily loop:** Create task β†’ assign to agent β†’ agent does the legwork β†’ human reviews β†’ done. +**Best for:** embedded copilots, agent-powered SaaS features, customer-facing automations, chat widgets, and AG-UI progress streams. -### 🏒 Enterprise β€” Agency / Multi-Tenant +### Consultancies and Agencies -Each client gets their own workspace. Custom agents built around their tools and data. Analytics show which agents perform, which cost most, where to optimise. BYOK means you control API spend. +Deploy repeatable, client-owned AI systems with isolated workspaces, reusable templates, BYOK cost control, transparent traces, and production handoff paths. ---- +**Best for:** client automation projects, AI transformation teams, multi-tenant delivery, and packaged workflow templates. + +### AI Builders and Developers -> **The core habit CrewForm builds:** I have a task β†’ I assign it to an agent β†’ I review the output. It becomes as natural as assigning work in Slack β€” the difference is the agent actually does the work. +Move from scripts and prototypes to managed agent systems with visual operations, deployment, APIs, tracing, and protocol integrations. + +**Best for:** LangGraph/CrewAI-style prototypes becoming products, MCP/A2A demos, local model workflows, and multi-agent experiments. + +--- -**Where it really shines:** -- Repetitive but complex tasks (reports, summaries, code reviews) -- Multi-step workflows with handoffs between skills (research β†’ write β†’ format) -- Teams that want AI leverage without every member needing prompt engineering skills +> **The core shift CrewForm supports:** move from isolated agent experiments to a shared runtime your team can deploy, observe, and operate. ## Key Features @@ -408,6 +407,7 @@ CrewForm uses an **open-core** model: a free Community Edition under AGPL-3.0 an | Guide | Description | |-------|-------------| | [Quick Start](https://docs.crewform.tech/quickstart) | Get running in under 5 minutes | +| [Run Your First Agent System](https://docs.crewform.tech/first-agent-system) | Golden-path demo: add one key, run a real pipeline, inspect the output | | [Agents Guide](https://docs.crewform.tech/agents) | Models, system prompts, and agent lifecycle | | [Pipeline Teams](https://docs.crewform.tech/pipeline-teams) | Multi-agent sequential workflows | | [Orchestration Teams](https://docs.crewform.tech/orchestration-teams) | Brain agent with delegation trees | @@ -549,33 +549,33 @@ CrewForm integrates with **Zapier** (7,000+ apps), messaging channels (**Discord
How does CrewForm differ from CrewAI or LangGraph? -CrewForm is a **visual, UI-first platform** β€” you create agents, teams, and tasks through a web interface with no Python required. CrewAI and LangGraph are code-first libraries. CrewForm also includes built-in billing, RBAC, marketplace, messaging channels, MCP protocol support, RAG knowledge base, A2A agent-to-agent interop, AG-UI real-time streaming, and a production-ready self-hosted deployment. CrewForm is the **first platform to support all three agentic protocols** (MCP + A2A + AG-UI). +CrewAI and LangGraph are code-first orchestration libraries. CrewForm is a self-hostable control plane around agent systems: visual orchestration, task execution, workspaces, billing, RBAC, marketplace/templates, messaging channels, RAG, observability, REST APIs, and production deployment. It also treats interoperability as a core runtime concern with native MCP, A2A, and AG-UI support.
## How CrewForm Compares | Capability | CrewForm | Others | |---|---|---| -| **Visual UI** | βœ… Drag-and-drop canvas + live execution | Often code-only or basic flow editors | +| **Visual Control Plane** | βœ… Drag-and-drop canvas + live execution | Often code-only or basic flow editors | | **Multi-Agent Teams** | βœ… 3 modes β€” Pipeline, Orchestrator, Collaboration | Usually single-mode or code-defined | | **MCP Protocol** | βœ… Client + Server (bidirectional) | Typically client-only or unsupported | | **A2A Protocol** | βœ… Bidirectional (consume + publish) | Not supported | | **AG-UI Protocol** | βœ… SSE + rich interactions | Not supported | -| **All 3 Protocols** | βœ… MCP + A2A + AG-UI β€” native | Zero or one | +| **Protocol-Native Runtime** | βœ… MCP + A2A + AG-UI β€” native | Usually zero or one | | **LLM Providers** | βœ… 16 + Ollama (local) | Often limited or requires plugins | | **BYOK (zero markup)** | βœ… Your keys, your cost | Often limited providers or markup fees | | **Local Models (Ollama)** | βœ… Native, fully air-gapped | Varies | | **RAG / Knowledge Base** | βœ… Hybrid search + retrieval tester | Sometimes available, often requires plugins | | **Chat Widget** | βœ… One script tag, streaming, domain security | Rare β€” usually requires custom dev | | **Observability** | βœ… OTLP + Langfuse | Sometimes available | -| **Fan-Out (Parallel)** | βœ… Built-in branching + merge | Rare in UI-first platforms | +| **Fan-Out (Parallel)** | βœ… Built-in branching + merge | Rare in visual tools | | **Agent Marketplace** | βœ… Browse, install, publish | Rare in open-source tools | | **Workflow Templates** | βœ… Variable-driven blueprints with one-click install | Not available | | **Data Portability** | βœ… JSON export/import for agents and teams | Usually locked to platform | | **Self-Hosting** | βœ… One-command Docker Compose | Often cloud-only or complex setup | | **Open Source** | βœ… AGPL-3.0 | Varies | -> **CrewForm is the only platform with all three agentic protocols** (MCP + A2A + AG-UI) β€” giving your agents access to thousands of tools, cross-framework interop, and real-time UI streaming out of the box. +> CrewForm combines native MCP, A2A, and AG-UI with a visual runtime, self-hosting, BYOK, knowledge, APIs, and observability so teams can operate interoperable agent systems instead of stitching isolated tools together. ## License @@ -606,7 +606,7 @@ You can use, modify, and distribute the Community Edition freely. Enterprise fea
-**CrewForm** β€” Form your AI crew ⚑ +**CrewForm** β€” The open control plane for interoperable AI agents [Website](https://crewform.tech) Β· [Docs](https://docs.crewform.tech) Β· [Discord](https://discord.gg/TAFasJCTWs) Β· [Twitter](https://twitter.com/CrewFormHQ) diff --git a/docs/first-agent-system.md b/docs/first-agent-system.md new file mode 100644 index 00000000..df49ee70 --- /dev/null +++ b/docs/first-agent-system.md @@ -0,0 +1,113 @@ +--- +title: 'Run Your First Agent System' +description: 'Use the golden-path Research Brief demo to run a real multi-agent workflow in CrewForm.' +--- + +# Run Your First Agent System + +This is the fastest way to see CrewForm work end-to-end. You will set up one provider key, activate the prebuilt Research Brief Pipeline, run a real team workflow, and inspect the output. + + + The demo uses the normal CrewForm execution path. It creates real agents, a real pipeline team, and a real team run that is picked up by the task runner. + + +## What You Will Run + +The golden-path demo creates a 3-step pipeline: + +| Step | Agent | What It Does | +|---|---|---| +| Research | Research Analyst | Builds market context, findings, trends, assumptions, and verification notes | +| Analyze | Data Analyst | Prioritizes insights, opportunities, risks, and recommended structure | +| Write Brief | Content Writer | Produces a polished markdown executive brief | + +Default prompt: + +```text +Research the market for AI customer support tools and produce a short executive brief. +``` + +## 1. Start CrewForm + +Use the hosted app: + +```text +https://app.crewform.tech +``` + +Or run locally: + +```bash +git clone https://github.com/CrewForm/crewform.git +cd crewform +npm install +cp .env.example .env.local +npm run dev +``` + +The task runner must also be running for real execution: + +```bash +cd task-runner +npm install +cp .env.example .env +# Add SUPABASE_URL / VITE_SUPABASE_URL and SUPABASE_SERVICE_ROLE_KEY +npm run dev +``` + +## 2. Add One Provider Key + +Open **Settings β†’ LLM Setup** and add an active OpenAI key. + +The demo agents use `gpt-4o-mini` by default so the run is fast and low-cost. You can change the models later from the agent configuration pages. + +## 3. Activate the Demo Workspace + +Return to **Dashboard** and choose **Activate Demo Workspace**. + +CrewForm will create: + +- 5 demo agents +- 1 Research Brief Pipeline team +- Team membership and pipeline step wiring + +The demo data is removable from the dashboard banner at any time. + +## 4. Run the Demo + +After the demo is active, choose **Run Demo** from the dashboard banner. + +CrewForm will create a real `team_run` and open the run detail page. You should see: + +- Current pipeline step +- Agent handoffs +- Running/completed status +- Final markdown output +- Token and cost totals when the run completes + +## 5. Inspect the Result + +When the run finishes, review: + +- The final executive brief +- Step-by-step messages +- Token usage and estimated cost +- Any error or retry details if a step failed + +From there, open the team page to customize the prompt, agents, model, tools, or pipeline steps. + +## Troubleshooting + +| Problem | What To Check | +|---|---| +| The **Run Demo** button says **Add OpenAI Key** | Add and activate an OpenAI provider key in Settings | +| The run stays pending | Make sure the task runner is running and connected to Supabase | +| The run fails immediately | Check that your provider key is valid and the selected model is available | +| The output is too generic | Add more detail to the run prompt or enable tools/knowledge sources | + +## Next Steps + +- [Pipeline Teams](/pipeline-teams) β€” Understand how fixed multi-agent workflows execute +- [Visual Workflow Builder](/visual-workflow-builder) β€” Edit and observe the workflow on the canvas +- [Observability](/observability) β€” Add Langfuse or an OTLP backend for traces +- [API Reference](/api-reference) β€” Trigger runs from scripts and external systems diff --git a/docs/mint.json b/docs/mint.json index 40804814..1e8e0c0f 100644 --- a/docs/mint.json +++ b/docs/mint.json @@ -48,6 +48,7 @@ "group": "Getting Started", "pages": [ "quickstart", + "first-agent-system", "cli", "self-hosting", "coolify-deployment", @@ -112,4 +113,4 @@ "discord": "https://discord.gg/TAFasJCTWs", "x": "https://twitter.com/CrewFormHQ" } -} \ No newline at end of file +} diff --git a/docs/quickstart.md b/docs/quickstart.md index 3211d375..99965f29 100644 --- a/docs/quickstart.md +++ b/docs/quickstart.md @@ -2,6 +2,10 @@ Get CrewForm running locally in under 5 minutes. + + Want the fastest product tour after setup? Follow [Run Your First Agent System](/first-agent-system) to activate the Research Brief demo and run a real multi-agent pipeline. + + ## Prerequisites - **Node.js** 20+ diff --git a/src/components/dashboard/DemoBanner.tsx b/src/components/dashboard/DemoBanner.tsx index b4411569..3d26ceba 100644 --- a/src/components/dashboard/DemoBanner.tsx +++ b/src/components/dashboard/DemoBanner.tsx @@ -2,10 +2,24 @@ // Copyright (C) 2026 CrewForm import { useState } from 'react' -import { Bot, Users, Sparkles, Trash2, Loader2, AlertTriangle, X, Key } from 'lucide-react' +import { Bot, Sparkles, Trash2, Loader2, AlertTriangle, X, Key, Play, GitBranch } from 'lucide-react' import { useDemoWorkspace } from '@/hooks/useDemoWorkspace' +import { useApiKeys } from '@/hooks/useApiKeys' +import { useAuth } from '@/hooks/useAuth' +import { useWorkspace } from '@/hooks/useWorkspace' +import { useCreateTeamRun } from '@/hooks/useCreateTeamRun' import { useNavigate } from 'react-router-dom' +const GOLDEN_PATH_PROMPT = `Research the market for AI customer support tools and produce a short executive brief. + +Focus on: +- buyer pains and adoption drivers +- major solution categories +- opportunities for a self-hostable, interoperable agent platform +- risks and assumptions we should validate next + +Write the final brief for a product and go-to-market team.` + /** * Dashboard banner for activating or removing the demo workspace. * @@ -17,11 +31,16 @@ export function DemoBanner() { const { isDemoSeeded, isDemoDismissed, + demoTeamId, seedDemo, removeDemo, isSeeding, isRemoving, } = useDemoWorkspace() + const { workspaceId } = useWorkspace() + const { user } = useAuth() + const { keys, isLoading: isLoadingKeys } = useApiKeys(workspaceId) + const createRun = useCreateTeamRun() const navigate = useNavigate() const [showConfirmRemove, setShowConfirmRemove] = useState(false) @@ -39,6 +58,36 @@ export function DemoBanner() { } } + const hasOpenAiKey = keys.some( + (key) => key.provider.toLowerCase() === 'openai' && key.is_active && key.is_valid, + ) + + const handleRunDemo = async () => { + setError(null) + + if (!hasOpenAiKey) { + navigate('/settings') + return + } + + if (!workspaceId || !user?.id || !demoTeamId) { + setError('Demo team is not ready yet. Try refreshing the page.') + return + } + + try { + const run = await createRun.mutateAsync({ + team_id: demoTeamId, + workspace_id: workspaceId, + input_task: GOLDEN_PATH_PROMPT, + created_by: user.id, + }) + navigate(`/teams/${demoTeamId}/runs/${run.id}`) + } catch (err) { + setError(err instanceof Error ? err.message : 'Failed to start the demo run') + } + } + const handleRemove = async () => { setError(null) try { @@ -61,7 +110,7 @@ export function DemoBanner() {

Remove all demo data?

- This will permanently delete 5 demo agents and the Content Research Pipeline team. + This will permanently delete 5 demo agents and the Research Brief Pipeline team. Your own agents and data will not be affected.

@@ -99,27 +148,44 @@ export function DemoBanner() {
-

Demo workspace active

-

- 5 demo agents + 1 pipeline team loaded.{' '} +

Research Brief demo ready

+

+ Run a real 3-step pipeline and watch CrewForm create an executive brief.{' '}

- +
+ + +
{error && ( @@ -152,20 +218,21 @@ export function DemoBanner() {

- Try CrewForm with demo agents + Run your first agent system

- Populate your workspace with 5 pre-configured agents and a pipeline team - to see what CrewForm can do. You'll still need to{' '} + Set up a golden-path Research Brief Pipeline with pre-configured agents. + Add one OpenAI key, run a real team workflow, then inspect the live run and output. + You can{' '} - {' '}to run tasks. + {' '}or set up the demo now.

{/* What you get */} @@ -174,14 +241,14 @@ export function DemoBanner() {

5 AI Agents

-

Research, Write, Code Review, Data, Email

+

Research, Analysis, Writing, Code, Email

- +
-

1 Pipeline Team

-

Research β†’ Write β†’ Email

+

Research Brief Pipeline

+

Research β†’ Analyze β†’ Write Brief

@@ -202,7 +269,7 @@ export function DemoBanner() { {isSeeding ? 'Setting up…' : 'Activate Demo Workspace'} - One-click removable anytime + Creates real agents and a real team, removable anytime diff --git a/src/components/onboarding/OnboardingWizard.tsx b/src/components/onboarding/OnboardingWizard.tsx index 9825ad65..f366ed9b 100644 --- a/src/components/onboarding/OnboardingWizard.tsx +++ b/src/components/onboarding/OnboardingWizard.tsx @@ -92,31 +92,31 @@ const FEATURE_CARDS = [ const QUICKSTART_PATHS = [ { icon: Key, - title: 'Add Your API Key', - desc: 'Go to Settings β†’ API Keys to configure your LLM provider.', + title: 'Add One Provider Key', + desc: 'Configure OpenAI first so the demo pipeline can run end-to-end.', route: '/settings', color: 'text-blue-400', bg: 'bg-blue-500/10', border: 'border-blue-500/20', }, + { + icon: Rocket, + title: 'Run the Research Brief Demo', + desc: 'Activate a prebuilt 3-agent pipeline and watch a real team run.', + route: '/', + color: 'text-emerald-400', + bg: 'bg-emerald-500/10', + border: 'border-emerald-500/20', + }, { icon: Store, - title: 'Browse Marketplace', - desc: 'Install a pre-built agent or team template to get started instantly.', + title: 'Browse Templates', + desc: 'Install a pre-built agent or workflow template when you want more examples.', route: '/marketplace', color: 'text-amber-400', bg: 'bg-amber-500/10', border: 'border-amber-500/20', }, - { - icon: LayoutGrid, - title: 'Explore the Canvas', - desc: 'Open the visual canvas to build and visualize your agent workflows.', - route: '/canvas', - color: 'text-emerald-400', - bg: 'bg-emerald-500/10', - border: 'border-emerald-500/20', - }, ] // ─── Component ────────────────────────────────────────────────────────────── @@ -209,11 +209,11 @@ export function OnboardingWizard() {

Welcome to CrewForm

- Build, deploy, and orchestrate AI agent teams. + Build, run, and observe interoperable AI agent systems.

- Let's take a quick look at what you can do. This only takes 30 seconds β€” - or skip anytime to start exploring on your own. + Let's take a quick look at the runtime layer: agents, teams, protocols, + tools, memory, and live execution.

Β· { @@ -47,6 +48,7 @@ export function useDemoWorkspace() { return { isDemoSeeded, isDemoDismissed, + demoTeamId, seedDemo: seedMutation.mutateAsync, removeDemo: removeMutation.mutateAsync, isSeeding: seedMutation.isPending,