bytechef

AI Agents — built in, not bolted on

A drag-and-drop AI Agent component runs the full agent loop — model → tool selection → execution → observation → next step — with streaming and structured output.

Build Workflows with Ease using Copilot

Build AI agents and workflows by talking to ByteChef. The Copilot generates workflows from a sentence, drops in configured agent steps, explains failed runs and suggests fixes.

---

Quick Start

Docker Compose (Fastest Setup)

Requirement: Docker Desktop

This is the fastest way to start ByteChef. Download the docker-compose.yml file from the repository:

curl -O https://raw.githubusercontent.com/bytechefhq/bytechef/master/docker-compose.yml
docker compose -f docker-compose.yml up

Both PostgreSQL database and ByteChef containers will start automatically.

Open http://localhost:8080/login → Create Account → sign in.

Docker (Manual Setup)

If Docker Compose isn't supported in your environment, follow these steps:

1. Create Docker Network

docker network create -d bridge bytechef_network

2. Start PostgreSQL Container

docker run --name postgres -d -p 5432:5432 \
    --env POSTGRES_USER=postgres \
    --env POSTGRES_PASSWORD=postgres \
    --hostname postgres \
    --network bytechef_network \
    -v /opt/postgre/data:/var/lib/postgresql/data \
    postgres:15-alpine

3. Start ByteChef Container

docker run --name bytechef -it -p 8080:8080 \
    --env BYTECHEF_DATASOURCE_URL=jdbc:postgresql://postgres:5432/bytechef \
    --env BYTECHEF_DATASOURCE_USERNAME=postgres \
    --env BYTECHEF_DATASOURCE_PASSWORD=postgres \
    --env BYTECHEF_SECURITY_REMEMBER_ME_KEY=e48612ba1fd46fa7089fe9f5085d8d164b53ffb2 \
    --network bytechef_network \
    docker.bytechef.io/bytechef/bytechef:latest

Note: Use -d flag instead of -it to run in detached mode.

Open http://localhost:8080/login → Create Account → sign in.

Build your first agent in 60 seconds

1. New Project → New Workflow,
2. Add a trigger
3. Add the AI Agent component
4. Pick a model, attach tools from 200+ connectors, optionally add a knowledge base and guardrails
5. Fill the necessary credentials
6. Configure each component's parameters in the properties panel
7. Test your workflow
8. Deploy

---

Workflow Automation

• Visual editor with JSON underneath, Git-friendly
• Flow controls — condition · switch · loop · each · parallel · branch · sub-workflows
• Triggers — webhook · schedule · polling · app-event · manual · form
• Polyglot code — Java · JavaScript · Python · Ruby on GraalVM
• Durable execution on the Atlas runtime, Postgres-backed, queue-mode for horizontal scale (memory · Redis · RabbitMQ · Kafka · JMS · AMQP · SQS)
• Workflows-as-APIs — workflows can be an authenticated HTTP endpoint
• Git-native — push from the UI, environments backed by branches

---

The Unification

• Agents inside workflows — an agent is a step; downstream branches react to its decisions
• Workflows as agent tools — a "refund order" workflow with retries and approvals becomes one tool
• Sub-agents — coordinator agents call specialist agents
• Human-in-the-loop — pause on approval, route to Slack/email, resume on response
• One audit log — agent decisions, tool calls, workflow runs, human approvals, all in one trail

---

180+ connectors

CRM · marketing · communication · e-commerce · cloud storage · databases · AI/ML · helpdesk · finance. Every connector is also an agent tool, also an MCP tool. Browse the full catalog.

---

Open core — Apache 2.0 + EE

Capability	CE (Apache 2.0)	EE
Visual editor, AI agents, workflows, 200+ connectors	✅	✅
Polyglot code (Java/JS/Python/Ruby)	✅	✅
Knowledge bases, vector stores, guardrails, MCP server	✅	✅
Agent skills, agent evaluations	🚧 in development	🚧 in development
Self-host (Docker / Kubernetes / Helm)	✅	✅
Workflows-as-APIs	—	✅
Git-native	—	✅
Microservices deployment	—	🚧 in development
AI Copilot	—	✅
SSO / SAML / OIDC, SCIM, advanced RBAC	—	🚧 in development
Connection scope sharing (Workspace / Project / Organization)	—	🚧 in development
Multi-environment promotion, audit log with correlation IDs	—	✅
AI Gateway - model routing, quotas, cost controls	—	🚧 in development
Embedded iPaaS - ship integrations and AI agents inside your SaaS product	—	✅

---

Contributing

If you would like to contribute to the software, read the contributing guide to get started.

---

License

This project is licenced under Apache 2.0 for the core (everything outside /ee/) and the ByteChef Enterprise License for code under /ee/ (microservices, embedded, AI Copilot, SSO/SCIM, advanced RBAC)

---

Contributors

---

Credits

ByteChef started as a fork of Piper.