Alternatives to DeepAgents

LangGraph is a low-level agent orchestration framework for building stateful, controllable AI agents as graphs.

TabTin is an open-source team agent harness where sub-agents and people share one task surface for code, docs and spreadsheets.

Open-source meta-harness that runs Claude Code, Codex and custom AI agents under one policy, sandbox and cost layer

Swarms is an open-source Python framework for multi-agent orchestration with named swarm topologies and reasoning agents

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

Open-source AI agent harness that plans tasks, runs tools, and keeps long-term memory across sessions.

Microsoft Agent Framework is an open-source SDK for building agentic AI agents and workflows in Python or C#, now with the GA Agent Harness

AgentScope is an open-source Python framework for building multi-agent AI systems with debate, routing, and plan-based reasoning.

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

Open source durable execution SDK for background jobs, workflow orchestration, and AI agents

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

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

Open-source web UI for prototyping multi-agent AI teams on Microsoft's AutoGen AgentChat without writing orchestration code.

Open-source AI agent orchestration: run a team of AI agents with org charts, budgets, and approval gates.

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 multi-agent framework that assigns PM, architect, engineer and QA roles to GPTs for structured software tasks

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

Hello Agents is a free, open-source 16-chapter tutorial for building AI agents from scratch in Python.

Learn Claude Code is an open-source tutorial that builds a Claude Code-style agent harness in Bash across 20 runnable sessions.

xpander.ai runs Claude Code, Codex, and OpenCode agents inside your own Kubernetes with budgets and every turn logged

OpenAgents runs Data Agent, Plugins Agent and Web Agent from one open chat UI, self-hostable under Apache-2.0.

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

Agenta is an open-source workspace for building and automating AI coworkers that work in Slack or Telegram

Trigger.dev runs durable AI agents and long-running background jobs in TypeScript with no execution timeout.

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 is a multi-agent AI workspace: an Organizer dispatches work to specialist agents on persistent cloud computers.

Open Multi-Agent is an MIT-licensed TypeScript runtime for audit-ready multi-agent orchestration with durable approvals.

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

OpenMA runs Claude Managed Agents and OpenAI Agents API sessions on your own infrastructure, Apache 2.0 licensed.