Alternatives to DBOS

Durable execution platform that keeps AI agents and long-running workflows alive through crashes, retries, and abandoned sessions.

Open source durable execution SDK for background jobs, workflows, and AI agents — wrap code in step.run() and get retries, flow control,

Open-source TypeScript agent framework with durable workflows, memory, and observability built into one stack.

Open-source TypeScript platform for durable AI agents and long-running background jobs that survive redeploys and crashes.

OpenAI Agents SDK: a free MIT-licensed Python framework for building multi-agent workflows with handoffs, guardrails, sandbox agents, and

Google Agent Development Kit (ADK) is the MIT-licensed framework for building production AI agents with graph workflows

Aeon turns 86 skills into self-healing AI agents that run unattended on GitHub Actions cron schedules.

Self-hosted Agent Protocol server that runs LangGraph agents on your own Postgres with the same LangGraph SDK.

Open-source platform where a Chief Agent Operator hires, schedules and reports on a 24/7 team of AI agents.

Enterprise agent runtime that runs Claude Code, Codex, and OpenCode agents inside your own cloud with governance and budgets

StackAI is the enterprise AI agent factory IT teams use to build, deploy, and govern AI agents across regulated organizations.

CrewAI is an enterprise multi-agent platform: visual builder plus a governed control plane for production agent workflows.

OpenAgents is an open-source platform for running and hosting language agents — Data, Plugins and Web agents from one chat UI.

Haystack is deepset's open-source Python framework for building inspectable RAG pipelines and production-grade AI agents

Hugging Face's Apache-2.0 Python library for AI agents that write and run their actions as code.

MIT-licensed agent harness that bundles sub-agents, a pluggable filesystem, and human approval so long-horizon agents actually finish.

LangGraph is an MIT-licensed, low-level agent orchestration framework for building stateful, controllable AI agents as graphs of states and transitions.

Clawdi hosts always-on Hermes and OpenClaw AI agents in the cloud with shared memory, skills, and vaults across every agent you run.

Lyzr's Opencontroller is a control plane to run, monitor and govern AI agents built on any framework.

Buda runs a multi-agent AI workspace where an Organizer dispatches work to specialist agents on persistent cloud computers.

Open Multi-Agent is a self-hosted TypeScript framework for multi-agent orchestration with durable approvals and offline-verifiable run

Build stateful multi-agent LLM apps in Go with graph workflows, time travel and file checkpoints.

Ruflo is an agent meta-harness from Cognitum.One for running coordinated swarms of AI agents with shared memory.

Give Claude Code and Codex agents a persistent identity and shared rooms so teammates can message them directly.

Open-source meta-harness that runs Claude Code, Codex, Pi and your own agents under one policy, sandbox and cost layer

Enterprise agent workforce platform for building, operating, and governing AI agents across on-prem, hybrid, and multi-cloud environments.

Coze Studio is an Apache-2.0, self-hosted AI agent builder with a visual workflow engine, RAG, plugins, and databases — you run the stack.

Open-source Python SDK plus AgentOS runtime for serving agents as a REST API and MCP server you host yourself.

Paperclip is an open-source AI agent control plane for running a team of AI agents with org charts, budgets, and approvals.

Open-source Python multi-agent orchestration with named swarm topologies, reasoning agents, and MCP tooling