Master AI Agents through hands-on building

50+ lessons paired with 50+ runnable agents and swarms: ReAct, Reflexion, Graph RAG, text-to-SQL. Open one in your browser, fork it, and break it.

8
Tracks
50+
Lessons
50+
Agents & Swarms
97
Notebooks
21
Decks
25
Build Labs

Free during beta · Generous AI usage credit · No credit card

Templates

Runnable templates from real industry use cases

Start from a working multi-agent system, not a blank canvas. Each template ships wired agents, tools, memory, and a swarm you can run in one click — export in your choice of framework, modify and run in your choice of environment.

agentswarms.fyi/templates
Operations

Operations Swarm

An orchestrator routes work across specialist agents — intake, research, and synthesis — handing off context at each step until the task is done.

agentswarms.fyi/templates
Finance · Research

Market Report Agents

Parallel agents pull signals, score sentiment, and a synthesis agent writes the final memo — the analyst workflow as a runnable swarm.

agentswarms.fyi/templates
Engineering

Ship-Code Agents

A release pipeline of agents plans the change, writes and reviews the diff, then gates the deploy on a human approval node before it ships.

Voice

Build agents you can actually talk to

Give any agent a voice. You speak, it transcribes, thinks with its full tools, knowledge and guardrails, then answers out loud — the whole speech-to-speech loop, wired for you.

You speak

Mic captured in the browser

01

Speech-to-text

Transcribed by gpt-4o-transcribe

02

The agent thinks

LLM + tools + knowledge + guardrails

03

The agent speaks

Spoken back in a natural voice

04

One switch turns an agent into a voice agent

New Voice Agent gives you a dedicated Voice tab — pick a voice, a greeting, and the speech models. No pipelines to wire.

The full agent brain, spoken

Every spoken reply runs through the same tool loop, RAG retrieval, memory, and guardrails as a chat agent — voice is a channel, not a downgrade.

Ready-to-talk samples

Open the Voice Playground and talk to a support-triage, sales-discovery, or language-tutor agent. Fork any of them into your own workspace.

Embeds

Drop your agents & swarms into any website

Turn any agent or swarm you build here into a chat or task widget on your own site. One iframe, anonymous visitors, no login — runs on your AgentSwarms account with a domain-locked key.

your-site.com

Support Agent

AI Assistant

Hi! How can I help?
Do you ship to the EU?
Yes — EU orders ship in 3-5 days…

One snippet, agent or swarm

Paste an iframe on any page. Agent embeds stream chat replies with tools, RAG, and guardrails. Swarm embeds run the whole graph server-side and hand back the final output.

Domain-locked API keys

Each embed has its own sk_embed_ key, allowed-domains list, and daily request cap. Rotate or revoke in one click when you need to.

Anonymous visitors, your account

Nobody has to sign in. Sessions persist per browser so returning visitors resume. Model calls bill to your AgentSwarms usage — capped by your daily limit.

Why AgentSwarms

Most courses make you watch. We make you build and break.

This is a learning and POC platform, not a production runtime. The fastest way to actually understand agentic AI is to run it, wire it, and watch it fail.

A real builder, not a toy

The same visual Agent Builder and drag-and-drop swarm canvas you'd prototype with — guardrails, tools, memory, RAG, evals, and human approval included.

Router
Agent
Evaluate
Output

Learn by building, not watching

Every concept maps to a runnable agent or swarm you open in the browser. Read it, run it, fork it — no setup, no API keys to start.

We teach the failure modes

Diagnose and repair deliberately-broken swarms in Failure-Mode Labs — hallucinating RAG, runaway loops, dead branches. Almost nobody else teaches this.

New ways to learn

More than a curriculum

Pick the format that fits how you learn — animated explainers, guided builds, or hands-on debugging.

21 decks

Interactive Presentations

Animated, click-through decks on LLMs, prompting, RAG, agentic patterns, orchestration, security, observability, and inference internals.

Open presentations

Deck 04 · Agentic patterns

ReAct: reason, act, observe, repeat

Thought
Action
Observation
12 / 31
25 labs

Build-Along Labs

Step-by-step guides that build 10 standalone agents and 15 multi-agent swarms in the real builder — with diagrams, exact settings, and deep links.

Start building
A multi-agent swarm canvas building a Stock Investment CIO Swarm in AgentSwarms
4 labs

Failure-Mode Labs

Fix swarms that are deliberately broken. The platform verifies your repair — the fastest way to build real intuition for what goes wrong.

Diagnose a swarm
Researcher
Tool Loop

max_iterations exceeded — agent re-called the same tool 3 times

Your job: find the missing stop condition and repair the loop.

97 notebooks

Interactive Notebooks

Runnable TypeScript notebooks in your browser — foundations, advanced topics, and every major framework (LangChain, LlamaIndex, OpenAI Agents SDK, Vercel AI SDK, Google ADK), plus 10 reproduced failure-mode examples.

Open notebooks
Notebooks67
Foundations2
Agentic Evals8
LangChain5
LlamaIndex.ts7
OpenAI Agents6
Vercel AI SDK6
Failure Modes10

fnd-prompt-engineering.ipynb

1 · Anatomy of a chat request

{
"model": "gemini-3-flash",
"messages": [...]
}
▶ RunShift + Enter
Field engineering

Interactive Blogs

Long-form field-engineering posts with live widgets baked in — VRAM estimators, cost calculators, latency simulators. Drag the sliders and watch the answer change in real time.

Read the blog
3B8B14B32B70B405B
model size70B params
context length109K tokens
VRAM needed71.6 GB
24GB
48GB
80GB
141GB

How it works

Four steps from zero to swarm

No installs. No API keys to start. Open a demo, follow the guided prompts, then make it your own.

01

Try a Live Demo

Pick any template — Product Support, Research Assistant, Code Reviewer — and a working agent is provisioned in seconds.

02

Follow the Guided Tour

Each demo opens with a side-panel lesson. Suggested prompts walk you through RAG, guardrails, and approvals.

03

Fork & Experiment

Tweak the system prompt, swap models, wire up your own knowledge base. Break things — that's how you learn.

04

Build Your Own

Compose your own agents, chain them into a swarm, and watch traces light up in the observability dashboard.

Your first agent is one click away

Open a template, send the suggested prompt, watch the trace stream. The whole thing takes a minute.