AgentOS is an open-source Python microkernel runtime for building and running autonomous agents. Below are 9 autonomous agents & workflows apps with similar functionality to AgentOS, matched by what each product actually does — not ranked or scored. Explore each to find the closest fit for your use case.
AgentOS is an open-source TypeScript framework for building production-ready autonomous AI agents. It offers features like cognitive memory, multi-agent orchestration, runtime tool generation, and support for multiple LLM providers. Designed for AI developers and researchers building advanced agent systems.
air-agent is an open-source Python framework for building lightweight AI agents with support for OpenAI tool calling, Model Context Protocol (MCP), and parallel subagents. It is designed for developers who want to orchestrate and extend AI agent capabilities efficiently.
Capability-first Codex control plane for long-running developer workflows.
agent-core-py is an open-source Python runtime for building agentic AI applications and workflows that can leverage multiple LLM providers. It is designed for developers who need flexibility and extensibility in constructing agent-based systems.
agentsoss is an open-source command-line tool that acts as an autonomous LLM agent to assist with open source contributions. It integrates with GitHub and leverages LLMs to automate code-related tasks for developers.
Agent Kernel is an open-source platform designed to facilitate the building and deployment of scalable and compliant enterprise AI agents. It functions as an operating system for enterprise AI, providing a runtime and orchestration layer to streamline the development and management of AI agents across various business workflows. The platform is intended for a broad audience, including business leaders seeking to integrate AI agents without technical complexity, developers new to AI agent creation, and AI engineers requiring a production-grade execution framework. A key feature of Agent Kernel is its flexibility in deployment. It supports running the same agent code across major cloud providers—AWS, Azure, and Google Cloud Platform—as well as on-premises via Docker, without code rewrites. The platform includes production-ready Terraform modules to facilitate best-practice deployments, supporting both serverless and containerized environments such as AWS Lambda, AWS ECS/Fargate, Azure Functions, Azure Container Apps, and Google Cloud Run. For knowledge base support, Agent Kernel provides built-in integrations with ChromaDB, Neo4j, and Starburst Galaxy, and offers a custom adapter API for connecting to other backends. Agent Kernel is built with a focus on security and compliance, operating within an environment certified to ISO 27001 standards and independently audited against the AICPA SOC 2 framework for security, availability, and confidentiality. The platform also features tools for messaging, memory, guardrails, and observability, aiming to simplify monitoring and debugging of agents in production. 0 open-source license, with no licensing costs or vendor lock-in. Users can access Agent Kernel via a command-line interface, with installation available through pip. The platform is developed by Yaala Labs and is positioned as an open-source solution for organizations looking to build, deploy, and manage enterprise AI agents at scale.
agentao is an open-source governed agent runtime designed for running AI agents locally with a focus on privacy and embeddability. It supports multimodal agents, integrates with MCP, and is suitable for developers building private, local-first AI solutions.
Kronos Agent OS (KAOS): self-hosted runtime for durable AI agents with memory, skills, MCP tools, automations, and sub-agent coordination
agent-runtimes is an open-source Python package that provides runtime infrastructure for building and executing agent-based applications. It is designed for Python developers who need reusable components to manage agent lifecycles and execution environments. The package is BSD-3-Clause licensed and available on PyPI and GitHub.
