Skip to main content

Add your description here

Project description

Orcheo

CI Coverage PyPI - Core PyPI - Backend PyPI - SDK

Orcheo is a tool for creating and running workflows.

For users

Quick start

The project ships with everything needed to spin up the FastAPI runtime on SQLite for local development.

  1. Install dependencies

    For development (from source):

    uv sync --all-groups
    

    Or install from PyPI:

    uv add orcheo orcheo-backend orcheo-sdk
    
  2. Activate the virtual environment (optional but recommended)

    source .venv/bin/activate  # On macOS/Linux
    # or
    .venv\Scripts\activate     # On Windows
    

    Once activated, you can run commands without the uv run prefix.

  3. Run the API server

    orcheo-dev-server
    

    If you enable authentication, configure a bootstrap token first to create your initial service tokens:

    # Generate a secure random token
    python -c "import secrets; print(secrets.token_urlsafe(32))"
    
    # Configure bootstrap token and authentication
    export ORCHEO_AUTH_BOOTSTRAP_SERVICE_TOKEN="your-secure-random-token"
    export ORCHEO_AUTH_BOOTSTRAP_TOKEN_EXPIRES_AT="2025-05-01T12:00:00Z"  # optional expiry
    export ORCHEO_AUTH_MODE=required
    
    # Start the server
    orcheo-dev-server
    

    Bootstrap tokens are special environment-based service tokens for initial setup only:

    • Not stored in the database - read directly from environment
    • Full admin access by default (configurable with ORCHEO_AUTH_BOOTSTRAP_TOKEN_SCOPES)
    • Optional expiration via ORCHEO_AUTH_BOOTSTRAP_TOKEN_EXPIRES_AT
    • Should be removed after creating persistent tokens

    After the server starts, use the bootstrap token to create persistent service tokens:

    export ORCHEO_SERVICE_TOKEN="your-secure-random-token"  # Use bootstrap token
    orcheo token create --id production-token \
      --scope workflows:read \
      --scope workflows:write \
      --scope workflows:execute
    

    Then switch to the new persistent token and remove the bootstrap token:

    export ORCHEO_SERVICE_TOKEN="<new-token-from-previous-command>"
    unset ORCHEO_AUTH_BOOTSTRAP_SERVICE_TOKEN
    
  4. Verify the setup

    orcheo-test
    

CLI

Orcheo ships with a LangGraph-friendly CLI for node discovery, workflow inspection, credential management, and reference code generation.

Getting Started

After activating the virtual environment, get started with:

orcheo --help

Shell Auto-Completion

Enable fast shell auto-completion for commands and options:

orcheo --install-completion

This installs completion for your current shell (bash, zsh, fish, or PowerShell). After installation, restart your shell or source your shell configuration file.

Available Commands

Command Description
orcheo node list [--tag <tag>] List registered nodes with metadata (name, category, description). Filter by tag.
orcheo node show <node> Display detailed node schema, inputs/outputs, and credential requirements.
orcheo agent-tool list [--category <category>] List available agent tools with metadata. Filter by category.
orcheo agent-tool show <tool> Display detailed tool schema and parameter information.
orcheo workflow list [--include-archived] List workflows with owner, last run, and status.
orcheo workflow show <workflow> Print workflow summary, publish status/details, Mermaid graph, and latest runs.
orcheo workflow run <workflow> [--inputs <json>] Trigger a workflow execution and stream status to the console.
orcheo workflow upload <file> [--name <name>] Upload a workflow from Python or JSON file.
orcheo workflow download <workflow> [-o <file>] Download workflow definition as Python or JSON.
orcheo workflow delete <workflow> [--force] Delete a workflow with confirmation safeguards.
orcheo workflow publish <workflow> [--require-login] [--chatkit-public-base-url <url>] Publish a workflow for public ChatKit access, optionally requiring OAuth login and overriding the share-link origin for that run.
orcheo workflow unpublish <workflow> Revoke public access and invalidate existing share links.
orcheo credential list [--workflow-id <id>] List credentials with scopes, expiry, and health status.
orcheo credential create <name> --provider <provider> Create a new credential with guided prompts.
orcheo credential delete <credential> [--force] Revoke a credential with confirmation safeguards.
orcheo token create [--id <id>] [--scope <scope>] Create a service token for CLI/API authentication.
orcheo token list List all service tokens with their scopes and status.
orcheo token show <token-id> Show detailed information for a specific service token.
orcheo token rotate <token-id> [--overlap <seconds>] Rotate a service token with grace period overlap.
orcheo token revoke <token-id> [--reason <reason>] Immediately invalidate a service token.
orcheo code template [-o <file>] [--name <name>] Generate a minimal Python LangGraph workflow template file.
orcheo code scaffold <workflow> Generate Python SDK code snippets to invoke an existing workflow.

Published workflows remain accessible until you run orcheo workflow unpublish <workflow> or toggle the --require-login flag to gate public chats behind OAuth.

Offline Mode

Pass --offline to reuse cached metadata when disconnected:

orcheo node list --offline
orcheo workflow show <workflow-id> --offline

Authentication

Orcheo supports flexible authentication to protect your workflows and API endpoints.

Authentication Modes

Configure via the ORCHEO_AUTH_MODE environment variable:

  • disabled: No authentication (development only)
  • optional: Validates tokens when provided but not required
  • required: All requests must include valid credentials (recommended for production)
export ORCHEO_AUTH_MODE=required

Service Tokens

Service tokens are ideal for CLI usage, CI/CD pipelines, and automated integrations.

Create a token:

# Basic token
orcheo token create

# Token with scopes and workspace access
orcheo token create --id my-ci-token \
  --scope workflows:read \
  --scope workflows:execute \
  --workspace ws-production

Use with CLI:

export ORCHEO_SERVICE_TOKEN="your-token-secret-here"
orcheo workflow list

Use with Python SDK:

from orcheo_sdk import OrcheoClient

client = OrcheoClient(
    api_url="https://orcheo.example.com",
    token=os.environ["ORCHEO_SERVICE_TOKEN"]
)

Rotate tokens:

orcheo token rotate my-ci-token --overlap 300

JWT Authentication

For production deployments with Identity Providers (Auth0, Okta, Keycloak):

# Symmetric key (HS256)
export ORCHEO_AUTH_JWT_SECRET="your-secure-secret-key"

# Asymmetric key (RS256) with JWKS
export ORCHEO_AUTH_JWKS_URL="https://your-idp.com/.well-known/jwks.json"
export ORCHEO_AUTH_AUDIENCE="orcheo-production"
export ORCHEO_AUTH_ISSUER="https://your-idp.com/"

For detailed configuration, security best practices, and troubleshooting, see docs/authentication_guide.md.

MCP (Model Context Protocol)

Orcheo SDK includes an MCP server that allows AI assistants like Claude to interact with your workflows.

Claude Desktop

To configure it in Claude Desktop, add the following to your claude_desktop_config.json:

"Orcheo": {
  "command": "/path/to/uvx",
  "args": ["--from", "orcheo-sdk@latest", "orcheo-mcp"],
  "env": {
    "ORCHEO_API_URL": "http://localhost:8000"
  }
}

Note: This configuration requires the Orcheo development backend to be running locally (see Run the API server).

Claude CLI

To configure the MCP server in Claude CLI:

claude mcp add-json Orcheo --scope user '{
  "command": "/path/to/uvx",
  "args": [
    "--from",
    "orcheo-sdk@latest",
    "orcheo-mcp"
  ],
  "env": {
    "ORCHEO_API_URL": "http://localhost:8000"
  }
}'

Note: Replace /path/to/uvx with your actual uvx binary path (find it with which uvx).

Codex CLI

To configure the MCP server in Codex CLI:

codex add server Orcheo \
  /path/to/uvx \
  --from orcheo-sdk@latest orcheo-mcp \
  --env ORCHEO_API_URL=http://localhost:8000

Note: Replace /path/to/uvx with your actual uvx binary path (find it with which uvx).

For developers

Repository layout

  • src/orcheo/ – core orchestration engine and FastAPI implementation
  • apps/backend/ – deployment wrapper exposing the FastAPI ASGI app
  • packages/sdk/ – lightweight Python SDK for composing workflow requests
  • apps/canvas/ – React + Vite scaffold for the visual workflow designer

Opening the repository inside VS Code automatically offers to start the included dev container with uv and Node.js preinstalled. The new quickstart flows in examples/quickstart/ demonstrate the visual designer and SDK user journeys, and examples/ingest_langgraph.py shows how to push a Python LangGraph script directly to the backend importer, execute it, and stream live updates.

See docs/deployment.md for Docker Compose and managed PostgreSQL deployment recipes.

Seed environment variables

To set up your development environment:

orcheo-seed-env

Pass --force to overwrite an existing .env file.

Configuration

The CLI reads configuration from:

  • Environment variables: ORCHEO_API_URL, ORCHEO_SERVICE_TOKEN
  • Config file: ~/.config/orcheo/cli.toml (profiles for multiple environments)
  • Command flags: --api-url, --service-token, --profile

See docs/cli_tool_design.md for detailed design, roadmap, and future MCP server integration plans.

Workflow repository configuration

The FastAPI backend now supports pluggable workflow repositories so local development can persist state without depending on Postgres. By default the app uses a SQLite database located at ~/.orcheo/workflows.sqlite. Adjust the following environment variables to switch behaviour:

  • ORCHEO_REPOSITORY_BACKEND: accepts sqlite (default) or inmemory for ephemeral testing.
  • ORCHEO_REPOSITORY_SQLITE_PATH: override the SQLite file path when using the SQLite backend.

Refer to .env.example for sample values and to docs/deployment.md for deployment-specific guidance.

Project details


Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

orcheo-0.11.0.tar.gz (1.1 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

orcheo-0.11.0-py3-none-any.whl (126.0 kB view details)

Uploaded Python 3

File details

Details for the file orcheo-0.11.0.tar.gz.

File metadata

  • Download URL: orcheo-0.11.0.tar.gz
  • Upload date:
  • Size: 1.1 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for orcheo-0.11.0.tar.gz
Algorithm Hash digest
SHA256 c4a6c5e94ac2b618bd42e8925e07377574b2e79ad48c1f3bc4fa27c67dda4ed9
MD5 569d942d6a71fd96ecbfa46a58d7e5c5
BLAKE2b-256 d5aed7a356a9ef7e78f8e94938d2418dcac32c30afce15c7a273999d28eb7fa2

See more details on using hashes here.

Provenance

The following attestation bundles were made for orcheo-0.11.0.tar.gz:

Publisher: ci.yml on ShaojieJiang/orcheo

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file orcheo-0.11.0-py3-none-any.whl.

File metadata

  • Download URL: orcheo-0.11.0-py3-none-any.whl
  • Upload date:
  • Size: 126.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for orcheo-0.11.0-py3-none-any.whl
Algorithm Hash digest
SHA256 e2085546bafdd343cd6b6e24070f68505bdb7a6f60432271bdadf67182955370
MD5 5b5607bd294e27cab2e0c765de57e0ca
BLAKE2b-256 b146604114e5e8a2e1c604694f8fef3b8b5737aeb221ba98091da5c245ffabbb

See more details on using hashes here.

Provenance

The following attestation bundles were made for orcheo-0.11.0-py3-none-any.whl:

Publisher: ci.yml on ShaojieJiang/orcheo

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page