AI coding agent orchestration / developer tools
OpenHands is a self-hosted developer control center for running and orchestrating coding agents and automations, with support for multiple agent backends.
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
choose for a lightweight, embeddable agent toolkit with a TUI/CLI and unified LLM API, if you prefer building your own workflow over a full control center.
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
choose for a Python-based multi-agent framework with structured software company roles, if you want to orchestrate agents in code rather than via a control center.
π The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming
choose for a low-ceremony, chat-driven multi-agent collaboration simulation, if you prefer experimental research-style tooling.
ChatDev 2.0: Dev All through LLM-powered Multi-Agent Collaboration
choose for a single, lightweight terminal coding agent optimized for Qwen models, if you don't need a multi-agent control center.
An open-source AI coding agent that lives in your terminal.
choose for a focused autonomous development agent with research/planning, if you want a simple Python script over a full platform.
Develop software autonomously.
choose for a Go-based autonomous fleet that directly produces production PRs, if you want agent orchestration close to code review.
Autonomous software engineering fleet of AI agents for production-grade PRs on AgentField: plan, code, test, and ship.
choose for a DeepSeek-native terminal coding agent engineered for long-running sessions, if you use DeepSeek and want a single CLI.
DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability β leave it running.
choose for a TypeScript agent engineering framework to build custom agent systems, instead of using OpenHands' ready-made control center.
AI Agent Engineering Platform built on an Open Source TypeScript AI Agent Framework
choose for a lightweight, customisable autonomous agent framework with tool use, if you prefer low-level control over a pre-built platform.
Agent Zero AI framework
choose for a fast, extensible Rust-based agent CLI with install/execute/test capabilities, if you want an agent as a dependency instead of a server.
an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Does the same job, but ships as an app. Useful to a person, not swappable into a codebase.
choose for a desktop/cowork GUI that manages multiple CLI agents, if you prefer an app over a self-hosted server.
Open-source 24/7 Cowork app for OpenClaw, Hermes, Claude Code, Codex, OpenCode and 20+ more CLI Agent | Customize your assistants | Team them upο½Star if you like it!
These projects were analysed and named OpenHands among their alternatives. The relationship is not symmetric β how OpenHands rates them is a separate judgement, made when OpenHands is analysed in its own right.
calls OpenHands βPick it over the seed when you want a Docker-sandboxed, widely adopted coding agent with a large plugin/integration ecosystem.β
A self-improving RLM agent for coding workflows and long-running autonomous tasks.
calls OpenHands βChoose when you want a more mature, feature-rich agent with both CLI and web GUI, and a larger community.β
Trae Agent is an LLM-based agent for general purpose software engineering tasks.
calls OpenHands βAI-driven development platform with an interactive cloud IDE; choose if you want a hands-on agent environment instead of a preset software-company pipeline.β
π The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming
calls OpenHands βchoose it for an autonomous coding agent that plans and executes tasks directly, rather than defining YAML workflowsβ
The first open-source harness builder for AI coding. Make AI coding deterministic and repeatable.
calls OpenHands βchoose when you want a self-hosted web/CLI agent platform with sandboxed execution instead of Plandex's terminal diff-review workflow.β
Open source AI coding agent. Designed for large projects and real world tasks.
calls OpenHands βchoose when you want an agent with its own sandboxed runtime and web UI rather than shelling out to Claude Codeβ
Autonomous AI development loop for Claude Code with intelligent exit detection
calls OpenHands βPick it for a sandboxed Docker runtime with web UI and its own agent loop, at the cost of much heavier infra than a GitHub Actions job.β
The most autonomous AI agent framework: runs unattended on GitHub Actions, self-healing skills, drives Claude Code, Grok, Codex & more. No approval loops. Configure once, forget forever.
calls OpenHands βChoose for a mature software-engineering agent that operates a full dev environment, at the cost of a larger platform.β
Automata: A self-coding agent
calls OpenHands βChoose it when you need a mature software-engineering agent, accepting a narrower scope than AGNT's general workflows.β
The local-first operating system for building, running, and improving AI agents, workflows, and autonomous goals.