How to add my own AI agent to Omnara?

Use the Python SDK to send messages and check for user feedback, or manually configure via MCP. The README includes code examples for both methods, requiring API key setup.

Is Omnara free or paid?

Omnara has a free tier with 10 agents per month, plus Pro ($9/mo) and Enterprise plans. Pricing details are in the README, with core features available for free.

Can I self-host the Omnara dashboard?

Yes, the web and mobile apps are open source under Apache 2.0, and the README provides development setup with Docker and scripts for building from source.

Omnara vs running AI agents locally in terminal?

Omnara adds multi-device real-time sync and collaboration features, allowing remote monitoring and control, whereas local terminals offer only direct, single-device interaction without built-in oversight.

What happens if I don't migrate from the deprecated version?

The legacy web dashboard will work until end of 2025, but after that, features may break as it's unmaintained. Users are encouraged to switch to the new platform at omnara.com.

How does Omnara handle data privacy?

Data is stored in PostgreSQL via the API server, and while self-hosting is possible, the cloud-based version may involve external services, so review the architecture for compliance needs.

Omnara

Apache-2.0TypeScriptv1.7.0

A unified platform to monitor and interact with AI agents like Claude Code and Codex CLI from web and mobile interfaces.

Visit Website GitHub

2.6k stars191 forks0 contributors

What is Omnara?

Omnara is a platform that transforms AI agents from silent workers into communicative teammates by providing real-time visibility and control. It enables users to monitor agent activity and respond to their questions instantly from a unified dashboard accessible via web and mobile. The platform integrates with CLI agents like Claude Code and Codex CLI, as well as automation tools like n8n and GitHub Actions.

Target Audience

Developers and teams using AI coding agents (like Claude Code or Codex CLI) who need to monitor and interact with agent sessions remotely. It's also for engineers building automation workflows with n8n or GitHub Actions who require human-in-the-loop approval steps.

Value Proposition

Developers choose Omnara for its multi-platform real-time sync, allowing them to see and control AI agents from any device. Its unique selling point is turning opaque agent processes into collaborative, transparent workflows with human oversight, unlike running agents solely in a local terminal.

Overview

Omnara (YC S25) - Talk to Your AI Agents from Anywhere!

Use Cases

Best For

Monitoring and interacting with CLI-based AI coding agents (like Claude Code) from a mobile device or web browser.

Related Projects

Community-curated · Updated weekly · 100% open source

Found a gem we're missing?

Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.

Submit a project Star on GitHub

Adding human-in-the-loop approval nodes to n8n automation workflows for guided decision-making.

Triggering and overseeing GitHub Actions workflows that use AI agents, with remote launch from a phone or dashboard.

Running AI agents in headless mode and interacting with them exclusively through a web or mobile interface.

Building custom integrations with the Omnara Python SDK or REST API to add visibility to proprietary AI agents.

Self-hosting the open-source web and mobile apps to maintain control over the agent monitoring platform.

Not Ideal For

Projects requiring long-term stability with Claude Code integration, as the wrapper is deprecated due to frequent upstream changes.
Teams using AI agents outside the supported list (Claude Code, Codex CLI, n8n, GitHub Actions) without custom SDK work.
Environments with strict offline requirements or data sovereignty concerns, given the cloud-based sync architecture.

Pros & Cons

Pros

Multi-Platform Real-Time Sync

Agent activity and user responses are synchronized instantly across terminal, web dashboard, and mobile apps, enabling seamless remote monitoring and interaction from any device.

Human-in-the-Loop Integrations

Provides specialized n8n nodes for approval workflows and GitHub Actions triggers, allowing guided automation with real-time human feedback directly in the dashboard.

Remote Launch Capabilities

Users can start AI agent instances from mobile or web, including launching GitHub Actions workflows remotely, as demonstrated in the CLI serve mode and integrations.

Open Source Flexibility

The web and mobile apps are fully open source under Apache 2.0, allowing for self-hosting or customization, with clear development setup instructions in the README.

Cons

Deprecated Legacy Version

The open-source version is no longer maintained due to unfeasible maintenance with Claude Code's constant updates, forcing a disruptive migration to a new platform.

Limited Out-of-the-Box Support

Primarily integrates with Claude Code and Codex CLI; supporting other AI agents requires manual configuration via the SDK or REST API, not native integrations.

Cloud Dependency and Complexity

Full functionality relies on Omnara's API server and external services, adding setup overhead and potential points of failure for offline or self-hosted scenarios.

Frequently Asked Questions

Home

Claude Code

Superpowers

An agentic skills framework & software development methodology that works.

Stars164,590

Forks14,401

Last commit8 days ago

Everything Claude Code

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1

Stars55,774

Forks9,183

Last commit10 days ago

Claude Code Templates

CLI tool for configuring and monitoring Claude Code

Stars24,956

Forks2,468

Last commit2 days ago

#real-time-monitoring