(01)The most complete harness available. The Agent SDK gives you the same tools, agent loop and context management that power Claude Code, programmable in Python and TypeScript. Built in: file, shell, search and web tools, hooks at every stage of the loop, subagents, MCP, permission modes, resumable and forkable sessions, automatic context compaction, skills and plugins loaded from the project. Limitations: built for Claude models; the TypeScript SDK and the bundled Claude Code binary fall under Anthropic's Commercial Terms, not an open-source licence; third-party products may not offer claude.ai login and must use API-key authentication. For a fully hosted variant, Anthropic also offers Managed Agents.
Production agents with Claude Code's loop, tools, hooks, subagents and permissions as a librarySDK free to install; model usage billed via the Claude API
(02)Practically level with the Claude Agent SDK and the strongest fully open-source harness from a model vendor. The Codex CLI is Apache-2.0 and written in Rust; codex app-server exposes the same agent over JSON-RPC 2.0 and powers rich clients such as the Codex VS Code extension. The Codex SDK (TypeScript and Python) controls local Codex agents for CI/CD, custom agents and internal tools, with threads you can resume and explicit sandbox modes (read-only, workspace-write, full access). Hooks, sandboxing, AGENTS.md, MCP, skills and subagents are documented. Other harnesses reuse it: OpenClaw ships a Codex harness plugin on top of app-server. Tuned for GPT models.
Open-source coding harness with app-server protocol and SDK for embeddingCLI free (Apache-2.0); usage via a ChatGPT plan or an OpenAI API keyAI-Native
(03)The reference for always-on, self-hosted assistants. A local Gateway acts as control plane for sessions, tools, events and channels, and brings the agent to more than 20 messaging services plus native apps (per the project README). Models and even agent harnesses are swappable plugins, including a Codex harness that lets Codex own the low-level session. Optional sandboxing moves tool execution into Docker, Podman, SSH and other backends (off by default), plus hooks, skills, subagents, MCP and an ACP bridge for IDEs. Stewarded by the independent OpenClaw Foundation, with no paid tier or hosted service. Our separate OpenClaw production guide covers operations in depth.
Self-hosted personal and team assistant with multi-channel gateway and pluggable harnessesFree (MIT); you pay your model providerAI-Native
(04)Nous Research's self-improving agent and OpenClaw's closest competitor. Its distinguishing feature is a built-in learning loop: agent-curated memory, skills created from experience and refined during use, and full-text search over past sessions; skills follow the agentskills.io standard. It runs any model (Nous Portal, OpenRouter, OpenAI, custom endpoints and more), ships six terminal backends (local, Docker, SSH, Modal, Daytona, Vercel Sandbox), spawns isolated subagents, supports MCP and runs as an ACP server inside editors. A built-in importer migrates settings, memories and skills from OpenClaw, Claude Code, Codex CLI or Cursor. The self-improvement claims are the vendor's description; test them against your own tasks.
Self-improving assistant with learning loop, cron automations and messaging gatewayFree (MIT); you pay your model providerAI-Native
(05)The leading provider-agnostic open-source coding harness. OpenCode separates primary agents (Build with all tools, Plan restricted to analysis) from subagents (General, Explore) that primary agents call automatically or you invoke with an @-mention; hidden system agents handle compaction and summaries. Supports MCP servers, skills, granular permissions, ACP for editors such as Zed and JetBrains IDEs, and a server plus SDK for programmatic use. Works with dozens of hosted providers and local models. Best for teams that want to own the model layer.
Provider-agnostic coding harness with primary agents, subagents and permissionsFree (MIT); you pay your model providerAI-Native
(06)The batteries-included harness for teams that build their own agents in code. Deep Agents adds planning (a to-do tool), a virtual filesystem with pluggable backends, a task tool that spawns isolated subagents, summarization and context offloading for long runs, skills loaded from SKILL.md, persistent instructions from AGENTS.md and human-in-the-loop approvals. Sandbox backends add shell execution. It runs on the LangGraph runtime for durable execution and streaming and works with models from Anthropic, OpenAI, Google, OpenRouter, Ollama and others. A JavaScript port (deepagentsjs) is maintained alongside.
Code-first harness on LangGraph: planning, filesystem, subagents, context offloadingFree (MIT); you pay your model providerAI-Native
(07)The minimalist's harness. Pi describes itself as a minimal, extensible agent harness: it ships strong defaults but deliberately skips sub-agents and plan mode, and you add what you need through extensions, skills, prompt templates and shareable Pi packages. Use it interactively, in print or JSON mode, over RPC or through the TypeScript SDK; the same repository contains a unified multi-provider LLM API (including OpenAI-compatible local servers such as Ollama) and a standalone MCP client package. The Pi README names OpenClaw as a real-world integration. Ideal if you want to understand and own every part of the loop.
Minimal, extensible harness and toolkit: unified LLM API, agent loop, TUI, SDKFree (MIT); you pay your model provider or use an existing subscription loginAI-Native
(08)A general-purpose open-source agent beyond coding: research, writing, automation and data work. goose runs as a native desktop app, a CLI and an embeddable API, is written in Rust and works with many providers including Anthropic, OpenAI, Google, Ollama, OpenRouter, Azure and Bedrock. Extensions connect via MCP, subagents are documented, and ACP providers let it use existing agent subscriptions. goose is part of the Agentic AI Foundation (AAIF) at the Linux Foundation, which makes it a governance-friendly choice for organisations wary of single-vendor projects.
General-purpose desktop and CLI agent with MCP extensions under neutral governanceFree (Apache-2.0); you pay your model providerAI-Native
(09)DeepSeek's own open-source harness, published on GitHub on 13 August 2026. Built on the Cordis framework, it follows an everything-is-a-plugin design: model adapters, tool registry, session log and even the agent loop are replaceable plugins. Durable state lives in an append-only session log. It ships a web UI, headless, SDK (TypeScript and Python) and ACP profiles plus a desktop app, with DeepSeek adapters and a multi-provider adapter for other APIs and self-hosted servers. Ranked last only for maturity: the project is a developer preview with announced breaking changes, the latest tags are pre-releases, and its own safety notice says it has not been security-audited and is not production-ready.
Plugin-first harness (Cordis), web UI, SDK and ACP profiles, developer previewFree (MIT); you pay your model providerAI-Native
