Skip to main content

Dockrion - Deploy and manage AI agents with ease

Project description

Dockrion

PyPI version Python 3.11+ License: Apache 2.0 GitHub

Deploy and manage AI agents with ease.

Dockrion provides a complete toolkit for building, validating, and deploying AI agents powered by LangGraph, LangChain, and other frameworks. Define your agent in a simple YAML file and deploy it anywhere.

🚀 Installation

pip install dockrion

Optional Features

# LangGraph framework support
pip install dockrion[langgraph]

# LangChain framework support
pip install dockrion[langchain]

# Runtime server (FastAPI + Uvicorn)
pip install dockrion[runtime]

# JWT authentication
pip install dockrion[jwt]

# Everything included
pip install dockrion[all]

⚡ Quick Start

1. Initialize a New Project

dockrion init my-agent
cd my-agent

This creates a Dockfile.yaml template:

version: "1.0"

agent:
  name: my-agent
  entrypoint: app.graph:build_agent
  framework: langgraph

io_schema:
  input:
    type: object
    properties:
      messages:
        type: array
  output:
    type: object
    properties:
      response:
        type: string

expose:
  port: 8080

2. Validate Your Configuration

dockrion validate

3. Test Locally

dockrion test --payload '{"messages": [{"role": "user", "content": "Hello!"}]}'

4. Run the Server

dockrion run

Your agent is now accessible at http://localhost:8080.

5. Build & Deploy

# Build Docker image
dockrion build

# Deploy to your infrastructure
dockrion deploy

📦 What's Included

The dockrion package bundles everything you need:

Module Description
dockrion_cli Command-line interface for all operations
dockrion_sdk SDK for building and testing agents
dockrion_runtime FastAPI server for deployed agents
dockrion_schema Dockfile YAML schema validation
dockrion_adapters Framework adapters (LangGraph, LangChain)
dockrion_events Streaming and event infrastructure for agent executions
dockrion_policy Policy engine for redaction & tool gating
dockrion_telemetry Prometheus metrics & structured logging
dockrion_common Shared utilities and error handling

✨ Features

  • 🚀 Simple Configuration — Define your agent in a declarative YAML Dockfile
  • 🔧 Framework Agnostic — Works with LangGraph, LangChain, and custom frameworks
  • 🛡️ Built-in Safety — Policy engine for PII redaction and tool gating
  • 📊 Observability — Prometheus metrics and structured JSON logging
  • 🔐 Security — JWT authentication and API key support out of the box
  • 🐳 Container Ready — Docker-first deployment with auto-generated Dockerfiles
  • Fast Development — Hot reload and local testing without containers
  • 🧪 Testing Tools — Test your agent with payloads before deployment

🔧 CLI Commands

Command Description
dockrion init <name> Create a new agent project
dockrion validate Validate Dockfile configuration
dockrion test Test agent with sample payloads
dockrion run Run agent server locally
dockrion build Build Docker image
dockrion deploy Deploy to target environment
dockrion logs View agent logs
dockrion doctor Diagnose setup issues
dockrion version Show version information

📚 Documentation

For full documentation, examples, and guides:

🤝 Contributing

We welcome contributions! Please see our GitHub repository for:

  • Issue tracking
  • Pull request guidelines
  • Development setup instructions

👥 Authors

📄 License

Apache-2.0 — See LICENSE for details.

Project details


Download files

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

Source Distribution

dockrion-0.0.3.tar.gz (978.4 kB view details)

Uploaded Source

Built Distribution

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

dockrion-0.0.3-py3-none-any.whl (1.0 MB view details)

Uploaded Python 3

File details

Details for the file dockrion-0.0.3.tar.gz.

File metadata

  • Download URL: dockrion-0.0.3.tar.gz
  • Upload date:
  • Size: 978.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for dockrion-0.0.3.tar.gz
Algorithm Hash digest
SHA256 c4b4521c4b6b800ec7926af2c8c6b2d846bf48133aaa36137514f2c2cf92cde3
MD5 9c9559061ba26b42bd9d89580538e9f1
BLAKE2b-256 d1e47a49fb2a83bf156090124617624c1562ca3b8beee7920d48e3e5c51c3edc

See more details on using hashes here.

File details

Details for the file dockrion-0.0.3-py3-none-any.whl.

File metadata

  • Download URL: dockrion-0.0.3-py3-none-any.whl
  • Upload date:
  • Size: 1.0 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for dockrion-0.0.3-py3-none-any.whl
Algorithm Hash digest
SHA256 22457589b0656bafb29d239b055f4d2e723a326c4687951405e7719e2d4ececa
MD5 efda68dfc7e9309a4f00137bf1586ffc
BLAKE2b-256 3143d37efce8d1710f8d414bc10c3d0963ef5b140c98398830287b111b2799a1

See more details on using hashes here.

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