Alternatives to AgentPipe

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

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

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

Yao Agents is a self-hosted AI agent runtime that runs autonomous agents across every computer you own.

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

Hermes Desktop is a free, open-source desktop GUI for the Hermes Agent — a self-hosted AI agent with a built-in learning loop that turns

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.

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

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.

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

Capafy AI is an agent skills marketplace where you buy, run, and publish ready-made AI agent skills per task or per use.

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.

DeerFlow is an open-source SuperAgent harness that runs deep research, coding, and creation tasks in a persistent Docker sandbox.

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

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

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

MyClaw's managed hosting feature that turns a colleague's Slack, Teams, and GitHub trail into a portable AI agent Skill.

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

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

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

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

GitNexus turns any codebase into a deterministic knowledge graph of call chains and execution flows that AI coding agents query through 7 MCP tools.

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

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

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