Skip to main content

Omnara Agent Dashboard - MCP Server and Python SDK

Project description

Omnara - Mission Control for Your AI Agents 🚀

⚠️ IMPORTANT NOTICE ⚠️

This version of Omnara is no longer maintained. We apologize for the inconvenience. This version was built as a wrapper around the Claude Code CLI, which became unfeasible to maintain with Claude Code's constant updates.

We've migrated to a new voice-first coding agent platform at https://omnara.com built using the Claude Agent SDK. The new service keeps the features you love - web and mobile access to your machine - but we've built our own integrated experience instead of wrapping the Claude Code CLI. This allows us to provide a more reliable and maintainable service.

  • Legacy Web App: The legacy web dashboard for this deprecated version is at https://claude.omnara.com and will continue to work until the end of 2025
  • Current Paying Customers: You can contact us at contact@omnara.com for a refund. We will also apply 2 months of free credits to your account on the new platform at omnara.com and you will keep your current payment rate forever
  • Mobile App Auto-Updates: If you have auto-updates enabled, your mobile app may have already updated to v1.5.0 (the new platform). If you need access to the older version (< 1.5.0) for this deprecated platform, please reach out to contact@omnara.com and we can provide access via TestFlight
  • Building from Source: The web and mobile apps are now fully open source under Apache 2.0. You can build both the web dashboard (apps/web/) and mobile app (apps/mobile/) from source if you prefer to self-host or run an older version
  • Questions: For any other questions, please contact us at contact@omnara.com

Your AI workforce, in your pocket.

PyPI version Downloads Python Versions License GitHub stars Ruff

Omnara Mobile Experience


🚀 Quick Start

# Install Omnara (requires python >= 3.10)
pip install omnara

# Start a Claude Code session that's synced between terminal, web, and mobile
omnara

# Start a Codex CLI session that's synced between terminal, web, and mobile
omnara --agent codex

That's it! Create an account when prompted, then return to your terminal to interact with your coding agent. You can now see and interact with your coding agent session from the web dashboard or the mobile app.

💡 What is Omnara?

Omnara transforms your AI agents (Claude Code, Codex CLI, n8n, and more) from silent workers into communicative teammates. Get real-time visibility into what your agents are doing, and respond to their questions instantly from a single dashboard on web and mobile.

🎬 See It In Action

Agent Activity Feed

📖 How to Use

1. Omnara CLI

The primary way to use CLI coding agents (Claude Code, Codex CLI) with Omnara

Installation

Install Omnara using your preferred package manager:

# Using pip
pip install omnara

# Using uv
uv tool install omnara

# Using pipx
pipx install omnara

Running Omnara

Omnara offers three different modes depending on your workflow:

Standard Mode - Full Claude Code/Codex CLI Experience
omnara

Starts Claude Code with the standard CLI interface, fully synced across terminal, web dashboard, and mobile app. You interact with Claude Code in your terminal as usual, while everything is mirrored to the Omnara dashboard.

omnara --agent codex

Starts Codex with the standard CLI interface with the same features as noted above

Headless Mode - Dashboard-Only Interaction
omnara headless

Runs Claude Code in the background without the terminal UI. Perfect for when you want to interact with Claude Code exclusively through the Omnara web dashboard or mobile app.

Server Mode - Remote Launch Capability
omnara serve

Exposes an endpoint that allows you to launch Claude Code instances remotely from the Omnara dashboard. Ideal for triggering AI agents from your phone or another device.

Upgrading

Keep Omnara up-to-date with the latest features:

# Using pip
pip install omnara --upgrade

# Using uv
uv tool upgrade omnara

# Using pipx
pipx upgrade omnara

2. n8n Integration

Add human-in-the-loop capabilities to your n8n workflows

What it Does

The Omnara n8n integration provides a specialized "Human in the Loop" node that enables real-time human-AI collaboration within your n8n workflows. Perfect for approval workflows, agent conversations, and guided automation.

Installation & Setup

For detailed installation and configuration instructions, see the n8n-nodes-omnara package on npm.

3. GitHub Actions Integration

Run Claude Code in GitHub Actions with Omnara monitoring

What it Does

The Omnara GitHub Actions integration allows you to trigger Claude Code to run in your GitHub Actions workflows via repository dispatch events, while monitoring and interacting with it through the Omnara dashboard.

Key Features

  • Remote Launch: Start GitHub Actions from your phone or web dashboard
  • Automatic PR Creation: Claude creates branches, commits changes, and opens PRs
  • Real-time Monitoring: Track progress and provide guidance through Omnara

Installation & Setup

For complete setup instructions including GitHub workflow configuration, see the GitHub Actions integration guide.

🔧 Integrating your own Agent into Omnara

Method 1: Manual MCP Configuration

For custom MCP setups, you can configure manually:

{
  "mcpServers": {
    "omnara": {
      "command": "pipx",
      "args": ["run", "--no-cache", "omnara", "mcp", "--api-key", "YOUR_API_KEY"]
    }
  }
}

Method 2: Python SDK

from omnara import OmnaraClient
import uuid

client = OmnaraClient(api_key="your-api-key")
instance_id = str(uuid.uuid4())

# Log progress and check for user feedback
response = client.send_message(
    agent_type="claude-code",
    content="Analyzing codebase structure",
    agent_instance_id=instance_id,
    requires_user_input=False
)

# Ask for user input when needed
answer = client.send_message(
    content="Should I refactor this legacy module?",
    agent_instance_id=instance_id,
    requires_user_input=True
)

Method 3: REST API

curl -X POST https://agent.omnara.com/api/v1/messages/agent \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"content": "Starting deployment process", "agent_type": "claude-code", "requires_user_input": false}'

🏗️ Architecture Overview

Omnara provides a unified platform for monitoring and controlling your AI agents:

graph TB
    subgraph "Your AI Agents"
        A[🤖 AI Agents<br/>Claude Code, Cursor, etc.]
    end

    subgraph "Omnara Platform"
        API[🌐 API Server]
        DB[(📊 PostgreSQL)]
        NOTIFY[🔔 Notification Service<br/>Push/Email/SMS]
    end

    subgraph "Your Devices"
        M[📱 Mobile App]
        W[💻 Web Dashboard]
    end

    A -->|Send updates| API
    API -->|Store data| DB
    API -->|Trigger notifications| NOTIFY
    NOTIFY -->|Alert users| M
    DB -->|Real-time sync| M
    DB -->|Real-time sync| W
    M -->|User responses| API
    W -->|User responses| API
    API -->|Deliver feedback| A

    style A fill:#e3f2fd,stroke:#1976d2,stroke-width:3px,color:#000
    style API fill:#c8e6c9,stroke:#388e3c,stroke-width:2px,color:#000
    style DB fill:#ffccbc,stroke:#d84315,stroke-width:2px,color:#000
    style NOTIFY fill:#fff59d,stroke:#f57f17,stroke-width:2px,color:#000
    style M fill:#f8bbd0,stroke:#c2185b,stroke-width:3px,color:#000
    style W fill:#f8bbd0,stroke:#c2185b,stroke-width:3px,color:#000

For Developers

🛠️ Development Setup

Prerequisites: Docker, Python 3.10+, Node.js

Quick Start:

git clone https://github.com/omnara-ai/omnara
cd omnara
cp .env.example .env
python infrastructure/scripts/generate_jwt_keys.py
./dev-start.sh  # Starts everything automatically

Stop services: ./dev-stop.sh

For detailed setup instructions, manual configuration, and contribution guidelines, see our Contributing Guide.

🤝 Contributing

We love contributions! Check out our Contributing Guide to get started.

Development Commands

make lint       # Run code quality checks
make format     # Auto-format code
make test       # Run test suite
./dev-start.sh  # Start development servers

📊 Pricing

Plan Price Features
Free $0/mo 10 agents/month, Core features
Pro $9/mo Unlimited agents, Priority support
Enterprise Contact Us Teams, SSO, Custom integrations

🆘 Support

📜 License

Omnara is open source software licensed under the Apache 2.0 License.


Built with ❤️ by the Omnara team

WebsiteDocsTwitterLinkedIn

Project details


Release history Release notifications | RSS feed

This version

1.7.0

Download files

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

Source Distribution

omnara-1.7.0.tar.gz (124.3 kB view details)

Uploaded Source

Built Distributions

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

omnara-1.7.0-cp313-cp313-manylinux_2_28_x86_64.whl (10.6 MB view details)

Uploaded CPython 3.13manylinux: glibc 2.28+ x86-64

omnara-1.7.0-cp313-cp313-macosx_11_0_arm64.whl (8.1 MB view details)

Uploaded CPython 3.13macOS 11.0+ ARM64

omnara-1.7.0-cp313-cp313-macosx_10_13_x86_64.whl (8.7 MB view details)

Uploaded CPython 3.13macOS 10.13+ x86-64

omnara-1.7.0-cp312-cp312-manylinux_2_28_x86_64.whl (10.6 MB view details)

Uploaded CPython 3.12manylinux: glibc 2.28+ x86-64

omnara-1.7.0-cp312-cp312-macosx_11_0_arm64.whl (8.1 MB view details)

Uploaded CPython 3.12macOS 11.0+ ARM64

omnara-1.7.0-cp312-cp312-macosx_10_13_x86_64.whl (8.7 MB view details)

Uploaded CPython 3.12macOS 10.13+ x86-64

omnara-1.7.0-cp311-cp311-manylinux_2_28_x86_64.whl (10.6 MB view details)

Uploaded CPython 3.11manylinux: glibc 2.28+ x86-64

omnara-1.7.0-cp311-cp311-macosx_11_0_arm64.whl (8.1 MB view details)

Uploaded CPython 3.11macOS 11.0+ ARM64

omnara-1.7.0-cp311-cp311-macosx_10_12_x86_64.whl (8.7 MB view details)

Uploaded CPython 3.11macOS 10.12+ x86-64

omnara-1.7.0-cp310-cp310-manylinux_2_28_x86_64.whl (10.6 MB view details)

Uploaded CPython 3.10manylinux: glibc 2.28+ x86-64

omnara-1.7.0-cp310-cp310-macosx_11_0_arm64.whl (8.1 MB view details)

Uploaded CPython 3.10macOS 11.0+ ARM64

omnara-1.7.0-cp310-cp310-macosx_10_12_x86_64.whl (8.7 MB view details)

Uploaded CPython 3.10macOS 10.12+ x86-64

File details

Details for the file omnara-1.7.0.tar.gz.

File metadata

  • Download URL: omnara-1.7.0.tar.gz
  • Upload date:
  • Size: 124.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.12

File hashes

Hashes for omnara-1.7.0.tar.gz
Algorithm Hash digest
SHA256 989710438f7d6aa68a26a2dbad35e92c177733550e5a2fe95a97d6fc5002152f
MD5 09277cc3c936b7c7049de057decafec1
BLAKE2b-256 113d4d46acda35a59e64aa9f0ce174e82ae5caf6e23363f4cdf754da59525f87

See more details on using hashes here.

File details

Details for the file omnara-1.7.0-cp313-cp313-manylinux_2_28_x86_64.whl.

File metadata

File hashes

Hashes for omnara-1.7.0-cp313-cp313-manylinux_2_28_x86_64.whl
Algorithm Hash digest
SHA256 6d597f48c5ff94ef7f7d5fee07660c87d9312391f8cf9a62d1b98a6736edbca8
MD5 2632fa9e5e42486a68a9525b96a76b47
BLAKE2b-256 2bb5e4524fcb79675d301f164415aff5f49683f11f4e5e8dbe444e7a2a20d1fd

See more details on using hashes here.

File details

Details for the file omnara-1.7.0-cp313-cp313-macosx_11_0_arm64.whl.

File metadata

File hashes

Hashes for omnara-1.7.0-cp313-cp313-macosx_11_0_arm64.whl
Algorithm Hash digest
SHA256 ff3f21dbe7570f0fb958c5c6429b6b7ab888ac26cafd4a9193494560bf3cf723
MD5 8929ee8a5b9c1d36cb4e89901589a891
BLAKE2b-256 4b17746b13fc1f88b683a1a437e747187ff14980e51b88bf7d705a9e82ce8fa8

See more details on using hashes here.

File details

Details for the file omnara-1.7.0-cp313-cp313-macosx_10_13_x86_64.whl.

File metadata

File hashes

Hashes for omnara-1.7.0-cp313-cp313-macosx_10_13_x86_64.whl
Algorithm Hash digest
SHA256 41d57a07f6dc29d54668b0bbcb2a38dc322bb5551de77a71666cbb2a25101e39
MD5 2536705e7f9b2c3aa0bb5ea5ab504460
BLAKE2b-256 89dcc870f7b16e791cb397b9d8bb2e88f2a2d74a787fdf9cc77290e6becfeef5

See more details on using hashes here.

File details

Details for the file omnara-1.7.0-cp312-cp312-manylinux_2_28_x86_64.whl.

File metadata

File hashes

Hashes for omnara-1.7.0-cp312-cp312-manylinux_2_28_x86_64.whl
Algorithm Hash digest
SHA256 45eb26e6226590a4c039a27d47eada714439d5fa03952b3543b76e12a7e869b5
MD5 deb19122e39a806572e23c2b2cc20105
BLAKE2b-256 ff34c0c1511d83beb430272b15ee57eb5ae5d5ccc5275653a27c1cbbc6b221f8

See more details on using hashes here.

File details

Details for the file omnara-1.7.0-cp312-cp312-macosx_11_0_arm64.whl.

File metadata

File hashes

Hashes for omnara-1.7.0-cp312-cp312-macosx_11_0_arm64.whl
Algorithm Hash digest
SHA256 ef7451b14959a3ca5eb9dde4153ab6807718124e59a905afa53bd2ae604c445c
MD5 89185c90750d1c84ecb06daaf3cbcbfa
BLAKE2b-256 10bfc362b08a71f33c0d0d830ac62df1fb397b8a79641868c61cb0b3b37de1e1

See more details on using hashes here.

File details

Details for the file omnara-1.7.0-cp312-cp312-macosx_10_13_x86_64.whl.

File metadata

File hashes

Hashes for omnara-1.7.0-cp312-cp312-macosx_10_13_x86_64.whl
Algorithm Hash digest
SHA256 4997a7c9619de9b543dee22a5204e7cdfedc6552060ebdb8ddb6cba201524a60
MD5 11ce0ed042f26129ba5195c596d80020
BLAKE2b-256 cef15bcddf50b4216ab5a6dc14a83f5e9279ddf1e914e35c4cb009b7098779ef

See more details on using hashes here.

File details

Details for the file omnara-1.7.0-cp311-cp311-manylinux_2_28_x86_64.whl.

File metadata

File hashes

Hashes for omnara-1.7.0-cp311-cp311-manylinux_2_28_x86_64.whl
Algorithm Hash digest
SHA256 fe2afdfecc3beabe35d126250e0267ef2813688c18df6934e90e38205d48524d
MD5 371c50cadba9952117df8ad3aeb23ed9
BLAKE2b-256 3028d96615bb6b18ab3325fe58f48e1d4cf49ecf70706f2bb4119e2227bc1870

See more details on using hashes here.

File details

Details for the file omnara-1.7.0-cp311-cp311-macosx_11_0_arm64.whl.

File metadata

File hashes

Hashes for omnara-1.7.0-cp311-cp311-macosx_11_0_arm64.whl
Algorithm Hash digest
SHA256 aa898e13c9311a5f32facf062c6565f29553ecb36f377d499f73eeec7da2f670
MD5 82453f8da07dbfb4708884658ec4ca18
BLAKE2b-256 4910ac64c960945f36dff52c5e9b7c897105a247e8dc9406bc3260b819a8bb69

See more details on using hashes here.

File details

Details for the file omnara-1.7.0-cp311-cp311-macosx_10_12_x86_64.whl.

File metadata

File hashes

Hashes for omnara-1.7.0-cp311-cp311-macosx_10_12_x86_64.whl
Algorithm Hash digest
SHA256 b980eb0be2c9ce5b35f37a796caf3d99814b93c40e7bc716013632ab519599ee
MD5 e9e1fb0fabeb1c70175a59bd140b35a0
BLAKE2b-256 143dcb16b0490e03703192b89fd98c4fce0c68ac08e3b0211cdae00315daea17

See more details on using hashes here.

File details

Details for the file omnara-1.7.0-cp310-cp310-manylinux_2_28_x86_64.whl.

File metadata

File hashes

Hashes for omnara-1.7.0-cp310-cp310-manylinux_2_28_x86_64.whl
Algorithm Hash digest
SHA256 984c8892bbfec1bd2563a5d8449f71a76e050795140b778e224cd4fc97e7125d
MD5 a14b9fa83c212765d12ea2ae05cae93d
BLAKE2b-256 5ad6eff0b226125e29a7291adcff8d74fbd808c2e83929afcd93273f134ec1d5

See more details on using hashes here.

File details

Details for the file omnara-1.7.0-cp310-cp310-macosx_11_0_arm64.whl.

File metadata

File hashes

Hashes for omnara-1.7.0-cp310-cp310-macosx_11_0_arm64.whl
Algorithm Hash digest
SHA256 637ee51549f2956bf9f2c2f200c20e757a736ad8e441d913454c240f56b4cfbc
MD5 e42ff13dae43ff5fd79b6588e276f696
BLAKE2b-256 1a359c804a4f953acb51dd266b2cf5a74ec552a0de97c8313864dce86053a4b0

See more details on using hashes here.

File details

Details for the file omnara-1.7.0-cp310-cp310-macosx_10_12_x86_64.whl.

File metadata

File hashes

Hashes for omnara-1.7.0-cp310-cp310-macosx_10_12_x86_64.whl
Algorithm Hash digest
SHA256 10ef7cabf69cf0dd0211a6feffc62bf160e71b3fb78d20b8378a1de9b2e49560
MD5 de6303203d8844cd7e53ef9dcdf47eef
BLAKE2b-256 8d7d0e1da754e1640785d4e273b537596b9b28d2cc35a1897c6f1841b0f1f899

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