omnara-ai/omnara

The open-source alternative to Claude Managed Agents

What it solves

Omnara provides a production-grade platform for running managed agents. It removes the complexity of managing agent execution and state, allowing developers to focus on defining the agent's logic, tools, and the models they use.

How it works

Omnara acts as an orchestration layer that handles the state and execution of agents. Users define agent profiles using YAML files that specify the model, instructions, and tools. These agents can be launched via a CLI, SDK, or API, and can be run on various machines (sandboxes or VMs) and use models from providers like OpenRouter, LiteLLM, and Ollama.

Who it’s for

  • Developers building internal or customer-facing agentic applications via an API.
  • Teams who want to interact with agents directly through a dashboard or a Slack connector.

Highlights

  • Durable State: Agent state is committed to Postgres, allowing agents to recover automatically from crashes or disconnects.
  • Flexible Infrastructure: Supports sandboxes from providers like Blaxel, Daytona, and Modal, or connection to personal VMs/laptops.
  • LMM Model Agnostic: Supports various API formats (OpenAI, Anthropic) and providers (OpenRouter, Ollama, etc.).
  • Tool Integration: Integrates with built-in tools, custom tools, and HTTP MCP servers.
  • Deployment Options: Available as a managed cloud service or self-hosted via Docker.
  • Enterprise Features: Includes Role-Based Access Control (RBAC) and queryable state for analytics and evals in self-hosted versions.

Related

  • Project
    n-WN/SubgroupX

    A multi-user agent platform that allows AI agents to execute tasks on private, non-publicly routable machines via an outbound connector or cloud sandboxes.

  • Project
    Agenta-AI/agenta

    An open-source workspace for building and running AI agents that can automate work through interactive chat or scheduled background tasks.

  • Dispatch
    OpenAI Agents API Launch – Managed Harness for Durable Cloud Agents

    OpenAI introduced the Agents API, a managed Codex harness that lets developers run durable, tool‑enabled agents in hosted or self‑hosted sandboxes, with session persistence and multi‑agent support.

  • Project
    agentspan-ai/agentspan

    A durable runtime for AI agents that prevents execution loss during process crashes and supports long-running, event-driven workflows with human-in-the-loop approvals.

  • Project
    cloudflare/agents

    Cloudflare Agents is a TypeScript SDK that turns Cloudflare Durable Objects into persistent, real‑time AI/agent workloads. It provides type‑safe RPC (`@callable`), WebSocket sync, scheduling, AI chat, tool‑calling, voice, email, payments (x402), workflows, and a full React hook library. Agents hibernate when idle and can be deployed at millions‑scale with zero idle cost.