CLI Coding Agents & Harnesses

Compare terminal-based AI coding agents (Claude Code, Codex CLI, Aider, OpenCode, Goose and more) and the harnesses that orchestrate them.

Compare the top CLI coding agents

CLI coding agentWhat it doesTypePricing
Open InterpreterOpen Interpreter is an open-source terminal coding agent maintained by Killian Lucas and the Open Interpreter community. It is designedCoding agentOpen Source
OpenCodeOpenCode is an open-source AI coding agent developed by Anomaly that operates across terminal environments, desktop applications, and IDE extensions.Coding agentOpen Source
AmpAmp (developed by AmpCode) is an autonomous coding agent platform and remote development harness designed to execute software engineering tasksCoding agentSubscription
AiderAider is an open-source terminal-based AI pair programming tool created by Paul Gauthier and the Aider-AI community. It operates directlyCoding agentOpen Source
OpenHandsOpenHands (formerly OpenDevin) is an open-source autonomous AI software development agent and orchestration platform. It provides an extensible runtime environmentCoding agentOpen Source
goosegoose is an open-source, general-purpose AI agent built in Rust, hosted under the vendor-neutral Agentic AI Foundation (AAIF) at theCoding agentOpen Source
Cursor CLICursor CLI is a terminal-based autonomous coding agent developed by Anysphere, the team behind the Cursor editor. It brings Cursor'sCoding agentOpen Source
SWE-agentSWE-agent is an open-source autonomous software engineering agent harness built and maintained by researchers from Princeton University and Stanford University.HarnessOpen Source
KiroKiro is an agentic engineering platform and CLI coding agent built and operated by AWS. It extends beyond standard code-completionCoding agentOpen Source
GitHub Copilot CLIGitHub Copilot CLI is a terminal-based AI coding assistant developed by GitHub. It integrates the Copilot coding agent runtime directlyCoding agentOpen Source

What is the best open-source alternative to Claude Code?

Aider and Cline are two prominent open-source alternatives to Claude Code. Aider operates directly inside local Git repositories to inspect files, write changes, and create structured commits. Cline provides an open-source autonomous agent runtime that operates across both terminal environments and code editors without tying users to a single model provider.

Do CLI coding agents work with local models?

Yes, several CLI agents support locally hosted open-weight models. Open Interpreter allows developers to connect local model runtimes to execute Bash and Python commands directly on the host machine. Aider also supports local models via OpenAI-compatible endpoints.

How do CLI coding agents handle multi-file changes across large codebases?

Agents like Plandex isolate multi-step tasks inside protected sandbox environments, planning dependencies across multiple files before applying diffs to the working tree. Aider maintains an in-memory repository map to track relevant files, while Cline executes iterative edits and validates results with local linters.

What is the difference between an AI terminal emulator and a standalone CLI agent?

A terminal emulator like Warp integrates AI assistance, command generation, and execution blocks directly into the terminal window rendering pipeline. In contrast, standalone tools like Claude Code, Qwen Code, and Gemini CLI run as discrete terminal commands inside any standard shell such as Bash or Zsh.

Can CLI coding agents be used inside traditional IDEs?

Yes. Tools like OpenCode and Cline offer cross-platform architectures that bridge terminal consoles and IDE extensions. Developers can also run standalone tools like GitHub Copilot CLI, Aider, or Crush directly within the embedded terminal windows of code editors.

How do CLI agents manage system execution permissions?

Most CLI agents require explicit confirmation before running shell commands or modifying files. Open Interpreter, Claude Code, and Kiro prompt users interactively to approve system-level executions, package installations, and disk modifications unless configured with non-interactive flags.

  • Parallel Harness Pets — Parallel Harness Pets (parallel-harness-pets) is an open-source companion tool and harness plugin created by TevvvB. It is designed for developers running terminal-based AI coding agents,…
  • ralph-orchestrator — Ralph Orchestrator is an open-source, Rust-based harness created by Mikey O'Brien that implements the Ralph Wiggum technique for autonomous AI agent execution. Instead of terminating…
  • Catnip — Catnip is an agent harness and orchestrator project under the Weights & Biases (wandb) organization designed to manage, execute, and monitor automated coding agent workflows.…
  • Construct — Construct is an open-source terminal-based orchestrator and multi-harness manager developed by the construct-worlds organization. It functions as a meta-tool and execution harness for running, isolating,…
  • Tessl — Tessl is an AI developer platform and agent orchestration harness built to develop, evaluate, and optimize agent skills and coding workflows. It provides a structured…
  • ORCH — ORCH is an open-source multi-agent orchestration harness created by oxgeneral. It acts as a supervisory control layer for running, coordinating, and automating complex software engineering…
  • Supacode — Supacode is an open-source terminal orchestration workspace and agent harness developed by Supabit. Built on top of a native terminal layer embedding Ghostty, it offers…
  • AgentPack — AgentPack is an open-source orchestration harness and configuration management framework developed by Vishal (vishal2612200) for multi-agent coding environments. It standardizes agent behavior, steering rules, and…
  • Dahrk Node — Dahrk Node is an open-source agent harness and edge-node execution engine developed by the Dahrk AI team. Built as a TypeScript monorepo using pnpm workspaces,…
  • Zeroshot — Zeroshot is an open-source AI coding agent harness and orchestration framework developed by The Open Engine organization. Designed to coordinate agentic workflows with strict validation…
  • cliclaw — cliclaw is an open-source CLI agent harness and orchestrator developed by Younggi Choi. Built with TypeScript and targeted at runtimes like Bun and Node.js, the…
  • LoopTroop — LoopTroop is an open-source AI coding agent harness and orchestration framework maintained by the looptroop-ai organization on GitHub. Built with TypeScript, it is designed to…
  • Fab-kit — Fab-kit is an open-source terminal agent harness and developer toolkit maintained by Sahil Ahuja (sahil87). It provides a structured CLI environment for orchestrating automated coding…
  • agent-browser — agent-browser is an open-source browser automation harness and agent tool developed by Vercel Labs. It provides autonomous AI agents with structured interfaces to navigate web…
  • AgentsMesh — AgentsMesh is an open-source agent harness and orchestration framework designed to standardize, validate, and execute portable agent skills across heterogeneous AI coding agent environments. In…
  • Claude Code Tools — Claude Code Tools (cctools) is an open-source orchestration harness and plugin distribution toolkit developed by Prasad Chalasani (pchalasani). It is built to extend Anthropic's Claude…
  • Handoff — Handoff is an open-source CLI-based agent orchestration harness developed by dazuiba. Distributed as a Python package, it is designed to manage, coordinate, and monitor delegated…
  • Concord MCP — Concord MCP is an open-source orchestration harness and Model Context Protocol (MCP) server developed by Get Concord AI. It provides structured task orchestration, state inspection,…
  • agentdiff — agentdiff is an open-source, Rust-based provenance tracking tool designed to establish Git-native attribution for AI-generated code. Created by Prakhar (codeprakhar25), it records which specific AI…
  • Zosma QA — Zosma QA is an open-source testing-focused agent harness and orchestration framework created by Zosma AI. It provides scaffolding, structured prompt templates, and execution environments designed…
  • ActPlane — ActPlane is an open-source agent execution and policy enforcement harness developed by the Eunomia-bpf organization. It functions as a security and control plane designed to…
  • agent-lsp — agent-lsp is an open-source agent harness and orchestrator developed by Blackwell Systems. Built in Go, it bridges AI coding agents and Language Server Protocol (LSP)…
  • Context Bridge — Context Bridge is an open-source CLI agent harness and context orchestration utility developed by serdardb. It is built to facilitate seamless context switching and conversation…
  • Agent Manager — Agent Manager is an open-source terminal-based agent harness and session orchestrator developed by Yoan Wai. It is built to run, monitor, and manage the execution…
  • AI Tools
  • Categories
  • Industries
  • CLI Coding Agents
  • MCP Servers
  • MCP Categories