Alternatives to Relari

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

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.

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.

Coworker AI routes enterprise tasks across 13 models on top of OM2 organizational memory

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, self-hosted AI assistant and agent framework with unified model routing, a full RAG chain, and local/remote MCP tooling.

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

Logic turns a plain-English spec into a tested, versioned production AI agent you can call from anywhere.

Self-hosted AI agent runtime with an audit trail your auditors can actually read.

AgentX is an agent lifecycle platform for orchestrating, evaluating, tracing and deploying multi-agent workforces.

OpenBot is a chief-of-staff AI agent that routes your goal to Claude Code, Codex, Cursor and other specialists on a managed cloud computer.

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

ChatDev 2.0 (DevAll) is a zero-code, free multi-agent orchestration platform configured in YAML or JSON.

Kore.ai builds enterprise AI agents with runtime governance, Autoloop optimization, and voice CX at contact-center scale

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.

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

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

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

Open-source workspace for AI coworkers you run and automate from Slack or Telegram

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

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

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

DBOS adds durable workflows, queues, and cron to apps and AI agents using the Postgres database you already run.

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

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

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

Let your AI agent resolve a plain-language task into one ranked, install-ready agent skill with trust signals attached.

A framework-agnostic book on designing multi-agent LLM systems, written by AutoGen's Victor Dibia.