Omnara gives developers an open-source API to build, run, and manage AI agents. It handles execution and agent state, including recovery after interruptions, so you can focus on what your agents do. Choose your own models, tools, and machines, then use Omnara’s managed cloud or host it in your own environment.
Key Features
- One API for your agents: Create agents, send instructions, track their work, and respond when they need input.
- State and recovery: Keep agent history and state so work can resume after an interruption.
- Choice of models: Bring your own API keys and use supported providers or compatible model endpoints.
- Flexible execution: Run agents on connected machines or use managed sandboxes.
- Tools and integrations: Add custom tools, reusable skills, and MCP integrations.
- Hosting options: Use Omnara Cloud or self-host the open-source platform.
Benefits
- Spend less time building the infrastructure needed to run agents.
- Choose models and execution environments that fit each use case.
- Keep track of agent activity and step in when approval is needed.
- Self-host when you need greater control over your agent data and infrastructure.
