Alternatives to Runtime

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

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

Open-source stack pairing a drag-and-drop multi-agent workflow builder with a Rust/Python actor-model runtime for edge and IoT deployments.

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

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

Pydantic AI is the typed, open-source Python agent framework that returns Pydantic-validated objects from every run.

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

AutoGen is Microsoft's open-source framework for building conversational and event-driven multi-agent AI apps in Python and .NET.

Microsoft Agent Framework is an open-source SDK for building agentic AI with workflows, checkpoints, and the GA Agent Harness runtime.

AgentScope is an open-source Python framework from Alibaba for building distributed multi-agent AI systems.

Microsoft's open-source, code-first Python framework for building stateful, data-intensive conversational AI agents.

VCPToolBox is the open-source runtime that gives LLM agents persistent memory, tool calling and multi-agent coordination via the VCP

Open-source Python framework for building multi-agent AI teams that deliver results straight to Telegram, Slack, Discord and WhatsApp.

Free 16-chapter Datawhale open-source tutorial that teaches you to build AI agents from scratch in Python, including your own HelloAgents framework.

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

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

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

AgenticX: build multi-agent Python systems with MCP, A2A and layered memory in one local-first runtime

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

Hermes Agent: a self-hosted open-source AI agent with persistent memory that builds reusable skills across 20+ chat platforms.

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

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

Microsoft's open-source SDK for building AI agents and copilots with plugins, memory, and multi-agent orchestration.

Xagent is an open-source autonomous AI agent engine that plans tasks from stated outcomes instead of workflows.

CowAgent is an open-source AI agent harness that plans tasks, runs tools, and grows long-term memory across sessions.

Open-source library of 817 structured cybersecurity skill files your AI coding agent loads on demand, mapped to MITRE ATT&CK and licensed Apache 2.0.

TabTin is an open-source team agent harness that runs sub-agents and people on one shared task surface for code, docs and spreadsheets.