Form your AI crew

Open-source AI Agent Orchestration Platform — with all 3 agentic protocols

The first platform with native MCP (Tools) + A2A (Agent-to-Agent) + AG-UI (Frontend Streaming)

Website · Docs · Discord · Twitter

---

If you find CrewForm useful, please consider giving it a ⭐ — it helps others discover the project!

---

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

📸 More Screenshots

Create agents with models, prompts, and tools	Chain agents into pipeline teams
Watch pipeline runs execute in real-time	Browse and install community agent templates
Connect to external A2A agents
Visual workflow builder for pipeline teams	Track token usage, costs, and performance

🔌 Protocols & Standards

CrewForm is the first platform with native support for all three agentic protocols:

Protocol	Direction	What It Does
MCP (Model Context Protocol)	🔌 Client + 🔧 Server	Client: Agents discover and call tools from any MCP server. Server: Expose your agents as MCP tools for Claude Desktop, Cursor, and other MCP clients.
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)	📡 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) — all out of the box.

✨ Features at a Glance

🔌 MCP Client + Server Use external tools & expose agents as MCP tools	🤝 A2A Bidirectional Agent-to-Agent interop — consume & publish	🖥️ AG-UI Streaming Real-time SSE events with rich interactions	🤖 16 LLM Providers OpenAI, Anthropic, Gemini, Groq, Ollama, +11 more
🔀 3 Team Modes Pipeline, Orchestrator, and Collaboration	📚 Knowledge Base (RAG) Hybrid search: pgvector + full-text + reranking	🎨 Visual Workflow Canvas Drag-and-drop with live execution visualization	🐳 Local AI via Ollama Air-gapped — zero data leaving your network
💬 Chat Widget Embed agents on any website — one script tag	📡 Observability OpenTelemetry + Langfuse tracing	⚡ Zapier + Channels 7,000+ apps, Discord, Slack, Telegram, Email	🏪 Agent Marketplace Browse, install, and publish agent templates
🔀 Fan-Out Branching Parallel pipeline steps with merge agents	📦 Export & Import Portable JSON for agents and teams	🔄 Fallback Models Auto-switch to backup models on failure	🏠 Self-Hostable Docker Compose — your data, your infra
🔑 BYOK Your API keys, your cost — zero markup	🧠 Team Memory pgvector semantic search across runs	🛡️ RBAC & Workspaces Role-based access, multi-tenant isolation	📊 Analytics Track tokens, costs, and agent performance

🚀 Quick Start

Hosted (Fastest)

Sign up at crewform.tech — free tier includes 3 agents and 50 tasks/month.

Self-Hosted (Docker)

git clone https://github.com/CrewForm/crewform.git
cd crewform
cp .env.example .env  # Edit with your config
docker compose up -d

Open http://localhost:3000 — done!

⚡ Local Models: Install Ollama alongside CrewForm for fully local AI — zero API keys, zero data leaving your network. Run ollama pull llama3.3 and select Ollama as a provider in Settings.

Development

git clone https://github.com/CrewForm/crewform.git
cd crewform
npm install
cp .env.example .env.local
npm run dev

📖 See the Self-Hosting Guide for production deployment details.

Table of Contents

• Protocols & Standards
• Why CrewForm?
• How It Works
• Who It's For
• Key Features
• Editions & Pricing
• Documentation
• Architecture
• Tech Stack
• Contributing
• Community
• FAQ
• How CrewForm Compares
• License

Why CrewForm?

CrewForm gives you everything you need to orchestrate multi-agent AI workflows — a visual UI, team management, real-time monitoring, and an agent marketplace — while you keep full control of your API keys, your data, and your infrastructure.

• 🖥️ UI-First — Create, configure, and monitor agents from a visual interface. No code required to get started
• 🔑 BYOK (Bring Your Own Key) — Connect your own LLM provider keys. Pay your provider directly at their standard rates, zero markup
• 🏠 Self-Hostable — Deploy on your own infrastructure with Docker. Your data stays with you
• 🔀 3 Orchestration Modes — Pipeline (sequential), Orchestrator (brain + workers), and Collaboration (multi-agent discussion)
• 🔌 MCP Protocol — 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 — Agent-to-Agent interoperability — expose agents to external AI systems and delegate tasks to remote agents
• 🖥️ AG-UI Protocol — Real-time SSE event streaming for frontend integration — the standard for agent-to-UI communication
• 📚 Knowledge Base (RAG) — Upload docs (TXT, MD, CSV, JSON), auto-chunk and embed with pgvector, then search via agents
• 🏪 Agent Marketplace — Browse and install community-built agent templates, or publish your own
• ⚡ Integrations Ecosystem — Zapier (7,000+ apps), Discord, Slack, Telegram, Email, webhooks, and output routes
• 🔒 Secure by Default — AES-256-GCM key encryption, Row-Level Security, GDPR-ready
• 📊 Built-in Analytics — Track token usage, costs, and performance per agent and task

CrewForm is the first platform with all three agentic protocols — MCP (tools) + A2A (agents) + AG-UI (frontend). Built for developers and teams who want production-ready AI agent orchestration.

How It Works

CrewForm supports 4 execution modes — choose the right one for your workflow:

Mode	Description
Single Task	Send a prompt to one agent — it uses its LLM and tools, then returns the result. The simplest way to get work done.
Pipeline	Chain multiple agents in sequence. Each agent completes its task and passes the output to the next. Great for research → write → review workflows.
Orchestrator	A brain agent breaks down the task, delegates sub-tasks to worker agents, reviews their outputs, and assembles the final result.
Collaboration	Multiple agents discuss the task in a shared thread, debate approaches, and converge on a consensus result.

Who It's For

🧑 Solo User — Freelancer / Indie Hacker

Pick agents from the marketplace (or build your own) and throw tasks at them — "Research competitors for X", "Write a blog post about Y", "Review this code". Agents work in the background; you get results.

Daily loop: Dispatch tasks → review results → ship to clients.

👥 Small Team — Agency / Startup

Set up a shared workspace with a crew of agents matching your workflow — a Researcher, a Coder, a Writer, a QA agent. Tasks get assigned, agents run in pipeline or collaboration mode, results land in one place.

Daily loop: Create task → assign to agent → agent does the legwork → human reviews → done.

🏢 Enterprise — Agency / Multi-Tenant

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.

---

The core habit CrewForm builds: I have a task → I assign it to an agent → I review the output. It becomes as natural as assigning work in Slack — the difference is the agent actually does the work.

Where it really shines:

• Repetitive but complex tasks (reports, summaries, code reviews)
• Multi-step workflows with handoffs between skills (research → write → format)
• Teams that want AI leverage without every member needing prompt engineering skills

Key Features

Community Edition (Free & Open Source)

• 🔑 BYOK (Bring Your Own Key) — Pay your LLM provider directly. Zero markup, zero middleman
• 🤖 Agent Management — Create, configure, and monitor AI agents from a visual UI
• 🏪 Marketplace — Browse and install agent templates built by the community
• 👥 Pipeline Mode — Chain agents together in sequential workflows
• ✅ Single Tasks — Send a prompt to any agent and get results in real-time
• 🔌 MCP Protocol — Connect agents to external MCP tool servers for dynamic tool discovery, and expose agents as MCP tools for Claude Desktop and Cursor
• 📚 Knowledge Base (RAG) — Upload documents, auto-chunk and embed, and search via agents
• 🏠 Self-Hostable — Run on your own infrastructure with Docker Compose
• 🔒 Secure by Default — AES-256-GCM key encryption, Row-Level Security, GDPR-ready
• ⚡ Real-Time — Watch your agents work in real-time with live task execution updates
• 🎨 Visual Workflow Canvas — Drag-and-drop agents onto an interactive canvas with live execution visualization, glassmorphism nodes, transcript panel, tool activity heatmap, keyboard shortcuts, and camera auto-follow
• 🎙️ Voice Profiles — Control agent tone, custom instructions, and output format hints; save as reusable brand voice templates
• 📝 Output Templates — Format results with {{variable}} placeholders for consistent, structured output
• 🔀 Fan-Out Branching — Parallel pipeline steps that dispatch to multiple agents simultaneously, then merge results
• 📊 Usage Tracking — Monitor token usage, costs, and performance per agent and task
• 💬 Chat Widget — Embed any agent on your website with a single <script> tag — streaming responses, domain whitelisting, customizable themes
• 📦 Export & Import — Download agent/team configs as portable JSON; import into any workspace with automatic ID remapping
• 📡 Observability — Opt-in OpenTelemetry + Langfuse integration for tracing LLM calls, tool use, and team runs
• 🤝 AG-UI Rich Interactions — Agents can pause and request approval, data confirmation, or choices from the user mid-execution

Enterprise Edition (Paid Plans)

• 🔗 Orchestrator Mode — Brain agent coordinates sub-agents via delegation trees (Pro)
• 🛠️ Custom Tools — Extend agents with custom tool integrations (Pro)
• 💬 Collaboration Mode — Agents discuss and debate tasks in real-time threads (Team)
• 🧠 Team Memory — Shared pgvector semantic search across agents (Team)
• 👤 RBAC — Role-based access control and workspace member invitations (Team)

Integrations

• ⚡ Zapier — Connect CrewForm to 7,000+ apps. Trigger agents from Gmail, Slack, forms, or schedules
• 📡 Messaging Channels — Trigger agents from Discord, Slack, Telegram, and Email
• 📤 Output Routes — Deliver results to Discord channels, Slack, webhooks, MS Teams, and more
• 📈 Advanced Analytics — Charts, CSV export, prompt history with diffs (Pro)
• 💬 Chat Widget — Embed agents on any website (Pro)
• 📋 Audit Logs — Full audit trail with Datadog/Splunk streaming (Enterprise)
• 🐝 Swarm — Multi-runner concurrency pool (Enterprise)

Editions & Pricing

CrewForm uses an open-core model: a free Community Edition under AGPL-3.0 and a proprietary Enterprise Edition.

	Free	Pro	Team	Enterprise
Agents	3	25	Unlimited	Unlimited
Tasks/month	50	1,000	Unlimited	Unlimited
Teams	1	10	Unlimited	Unlimited
Members	1	3	25	Unlimited
MCP Protocol	✅	✅	✅	✅
AG-UI Protocol	✅	✅	✅	✅
Knowledge Base	3 docs	25 docs	Unlimited	Unlimited
A2A Consume	✅	✅	✅	✅
A2A Publish	—	✅	✅	✅
Chat Widget	—	✅	✅	✅
Pipeline Mode	✅	✅	✅	✅
Orchestrator Mode	—	✅	✅	✅
Collaboration Mode	—	—	✅	✅
Team Memory	—	—	✅	✅
Audit Logs	—	—	—	✅
Self-Hosting	✅ (CE)	✅	✅	✅

See LICENSING.md for full details on the dual-license model.

Documentation

Guide	Description
Quick Start	Get running in under 5 minutes
Agents Guide	Models, system prompts, and agent lifecycle
Pipeline Teams	Multi-agent sequential workflows
Orchestration Teams	Brain agent with delegation trees
Collaboration Teams	Multi-agent real-time discussion
Channels	Discord, Slack, Telegram, Email triggers
Discord Integration	Slash commands and bot setup
Output Routes	Deliver results to external destinations
MCP Protocol	Connect agents to external tool servers
MCP Server Publishing	Expose agents as MCP tools for Claude Desktop, Cursor
Knowledge Base	RAG document upload, chunking, and search
A2A Protocol	Agent-to-Agent interoperability
AG-UI Protocol	Real-time SSE streaming for frontends
API Reference	REST API endpoints and authentication
Self-Hosting	Docker Compose production deployment
Visual Workflow Builder	Interactive canvas with live execution observability
Chat Widget	Embed agents on any website with a script tag
Observability	OpenTelemetry + Langfuse tracing setup
Changelog	Release notes and version history

Architecture

┌──────────────────────────────────────────────────────────────────┐
│                        CrewForm UI                               │
│             React + TypeScript + Tailwind + ShadCN               │
│      Visual Workflow Canvas · AG-UI SSE Streaming · Chat Widget  │
├──────────────────────────────────────────────────────────────────┤
│                      Supabase Layer                              │
│         Auth · PostgreSQL · Realtime · Storage                   │
│         Edge Functions (REST API) · pgvector (RAG)               │
├──────────────────────────────────────────────────────────────────┤
│                       Task Runner                                │
│                   Node.js · Multi-Provider LLM                   │
│   ┌─────────────────────────────────────────────────────────┐    │
│   │  OpenAI · Anthropic · Gemini · Groq · Mistral · Cohere │    │
│   │  NVIDIA · Perplexity · Together · OpenRouter · HuggingFace│  │
│   │  MiniMax · Moonshot · Venice · Ollama (local) · xAI     │    │
│   └─────────────────────────────────────────────────────────┘    │
├──────────────────────────────────────────────────────────────────┤
│                     Protocol Layer                               │
│  ┌──────────────┐  ┌──────────────┐  ┌───────────────────────┐   │
│  │ MCP Protocol  │  │ A2A Protocol │  │    AG-UI Protocol     │   │
│  │ Client+Server │  │ Bidirectional│  │ SSE + Rich Interactions│  │
│  └──────────────┘  └──────────────┘  └───────────────────────┘   │
├──────────────────────────────────────────────────────────────────┤
│                      Integrations                                │
│  Channels (Discord · Slack · Telegram · Email) · Output Routes   │
│  Zapier (7,000+ apps) · Webhooks · Chat Widget · REST API        │
├──────────────────────────────────────────────────────────────────┤
│                    Observability                                 │
│         OpenTelemetry · Langfuse · Datadog · Jaeger              │
├──────────────────────────────────────────────────────────────────┤
│                  Your LLM Providers                              │
│              BYOK — Your Keys, Your Cost                         │
└──────────────────────────────────────────────────────────────────┘

Tech Stack

Layer	Technology
Frontend	React 18 · TypeScript · Vite · Tailwind CSS · ShadCN UI
State	TanStack Query · Zustand
Backend	Supabase (Auth, PostgreSQL, Realtime, Edge Functions)
Task Runner	Node.js · 16 LLM providers + Ollama (local)
Vector Search	pgvector — hybrid search (cosine + full-text + reranking)
Protocols	MCP (client + server) · A2A (bidirectional) · AG-UI (SSE + rich interactions)
Observability	OpenTelemetry · Langfuse · Datadog · Jaeger
Integrations	Zapier · Discord · Slack · Telegram · Email · Webhooks · Chat Widget
Validation	Zod
Deployment	Vercel · Docker Compose

Contributing

We welcome contributions from everyone! Please see CONTRIBUTING.md for:

• 🐛 How to report bugs
• 💡 How to suggest features
• 🔧 Development setup guide
• 📋 Coding standards

Community

• 💬 Discord — Chat with the team and community
• 🗣️ GitHub Discussions — Ideas, Q&A, and show & tell
• 🐦 Twitter/X — Product updates and AI ecosystem commentary
• 📧 Email — team@crewform.tech

FAQ

What is CrewForm?

CrewForm is an open-source AI orchestration platform that lets you deploy, manage, and collaborate on multi-agent AI workflows through a visual UI — without vendor lock-in or LLM cost markup.

Is CrewForm free to use?

Yes. CrewForm's Community Edition is open-source under the AGPL v3 license. You can self-host it for free. We also offer a hosted version with a free tier at crewform.tech. Paid plans (Pro $39/mo, Team $99/mo, Enterprise custom) unlock additional features.

What is the CE/EE split?

CrewForm uses an open-core model. All code outside ee/ is Community Edition (AGPL-3.0, free). Code inside ee/ is Enterprise Edition (proprietary, requires a license key). CE includes agents, pipeline teams, marketplace, and self-hosting. EE adds orchestrator mode, collaboration, memory, audit logs, and more.

What does BYOK mean?

BYOK stands for Bring Your Own Key. You connect your own API keys from providers like Anthropic, Google, or OpenAI. CrewForm never touches your LLM spend — you pay your provider directly at their standard rates.

Can I self-host CrewForm?

Yes! CrewForm supports Docker-based self-hosting. See our self-hosting guide for instructions.

What LLM providers are supported?

CrewForm supports 16 cloud providers + Ollama for local models:

OpenAI, Anthropic, Google Gemini, Groq, Mistral, Cohere, NVIDIA NIM, Perplexity, Together, OpenRouter, HuggingFace, MiniMax, Moonshot, Venice, xAI, and Ollama (local — Llama 3, Mistral, Phi, etc.).

Ollama enables fully air-gapped setups — zero API keys, zero data leaving your network. More providers can be added via the modular provider architecture.

What integrations are available?

CrewForm integrates with Zapier (7,000+ apps), messaging channels (Discord, Slack, Telegram, Email, Trello), output routes (webhooks, MS Teams, Asana, Trello, and more), and three agentic protocols: MCP (Model Context Protocol) for connecting to thousands of external tool servers, A2A (Agent-to-Agent) for delegating tasks to external AI agents, and AG-UI (Agent-User Interface) for real-time SSE streaming to any frontend.

How does CrewForm differ from CrewAI or LangGraph?

CrewForm is a visual, UI-first platform — 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).

How CrewForm Compares

Capability	CrewForm	Others
Visual UI	✅ Drag-and-drop canvas + live execution	Often code-only or basic flow editors
Multi-Agent Teams	✅ 3 modes — Pipeline, Orchestrator, Collaboration	Usually single-mode or code-defined
MCP Protocol	✅ Client + Server (bidirectional)	Typically client-only or unsupported
A2A Protocol	✅ Bidirectional (consume + publish)	Not supported
AG-UI Protocol	✅ SSE + rich interactions	Not supported
All 3 Protocols	✅ MCP + A2A + AG-UI — native	Zero or one
LLM Providers	✅ 16 + Ollama (local)	Often limited or requires plugins
BYOK (zero markup)	✅ Your keys, your cost	Often limited providers or markup fees
Local Models (Ollama)	✅ Native, fully air-gapped	Varies
RAG / Knowledge Base	✅ Hybrid search + retrieval tester	Sometimes available, often requires plugins
Chat Widget	✅ One script tag, streaming, domain security	Rare — usually requires custom dev
Observability	✅ OTLP + Langfuse	Sometimes available
Fan-Out (Parallel)	✅ Built-in branching + merge	Rare in UI-first platforms
Agent Marketplace	✅ Browse, install, publish	Rare in open-source tools
Data Portability	✅ JSON export/import for agents and teams	Usually locked to platform
Self-Hosting	✅ One-command Docker Compose	Often cloud-only or complex setup
Open Source	✅ AGPL-3.0	Varies

CrewForm is the only platform with all three agentic protocols (MCP + A2A + AG-UI) — giving your agents access to thousands of tools, cross-framework interop, and real-time UI streaming out of the box.

License

CrewForm uses a dual-license model:

• Community Edition (everything outside ee/) — GNU Affero General Public License v3.0
• Enterprise Edition (inside ee/) — CrewForm Enterprise License

You can use, modify, and distribute the Community Edition freely. Enterprise features require a valid license key. See LICENSING.md for full details.

⭐ Star History

🏢 Who's Using CrewForm

Using CrewForm in production? Open an issue and we'll add you here!

Be the first to showcase your team here!

---

CrewForm — Form your AI crew ⚡

Website · Docs · Discord · Twitter

_{If CrewForm is useful to you, please consider ⭐ starring the repo — it really helps!}