Index Agentica

Terminal coding agents compared

Claude Code, Codex CLI, Gemini CLI, GitHub Copilot CLI, OpenCode, Cline, goose and Aider compared on license, model access, instruction files, sandboxing, headless mode, MCP and Agent Skills support.

Type
Comparison
Author
Agentica Author
Published
Last verified

Comparison

Terminal coding agents compared
EntryLicenseModels and accessInstruction filesSandbox and approvalsHeadless modeMCPAgent SkillsLatest release
Claude CodeProprietary (Anthropic Commercial Terms)Claude models; needs a Pro, Max, Team, Enterprise or Console account (not the free plan), or Bedrock, Google Cloud or Microsoft providersCLAUDE.md; also reads AGENTS.md; auto memoryPermission modes plus an OS-enforced Bash sandbox (macOS, Linux, WSL2), off by default; sandboxed network goes through a domain allowlist proxyclaude -p, plus the Agent SDK for Python and TypeScriptYes (stdio and HTTP; remote OAuth)Yesv2.1.287 (2026-10-01)
OpenAI Codex CLIApache-2.0OpenAI models; sign in with ChatGPT (Free, Go, Plus, Pro, Business, Edu, Enterprise) or use an API keyAGENTS.mdSandbox on by default (Seatbelt on macOS, bubblewrap on Linux/WSL2); modes read-only, workspace-write (default), danger-full-access; approvals on-request or never, optional auto-review agentcodex execYes, as a client. The codex mcp-server command was removed; integrations use the app serverYes (custom prompts deprecated in favor of skills)rust-v0.160.0 (2026-10-01)
Gemini CLIApache-2.0Gemini models; free tier with a personal Google account (60 requests/min, 1,000/day), API key or Vertex AIGEMINI.md by default; context file name configurable (e.g. AGENTS.md)Opt-in sandbox (-s or GEMINI_SANDBOX): macOS Seatbelt, Docker, Podman, gVisor (runsc) or LXCgemini -pYesYes, enabled by defaultv0.62.0 (2026-09-29)
GitHub Copilot CLIProprietary (GitHub Copilot CLI License; redistribution of unmodified copies allowed)Several models selectable with /model; needs an active Copilot subscription; usage consumes AI credits by tokensAGENTS.md, .github/copilot-instructions.md, CLAUDE.md, GEMINI.md and *.instructions.md, all combinedTool approvals (--allow-tool); local sandbox via /sandbox enable and cloud sandboxes, both public previewcopilot -pYes; ships with GitHub's MCP server by defaultYesv1.0.91 (2026-10-01)
OpenCodeMIT75+ providers via the AI SDK and Models.dev, plus local models; bring your own keysAGENTS.md (project and global); falls back to CLAUDE.md and reads .claude/skillsPer-tool allow, ask or deny rules, with a read-only plan agent and an --auto mode; no OS sandbox documented in the sources usedopencode run, and opencode serve for a headless serverYesYesv1.18.34 (2026-09-30); site announces OpenCode v2
ClineApache-2.0 (JetBrains plugin not open source)Many providers (Anthropic, OpenAI, Bedrock, Gemini, OpenRouter, local), Claude Code or Codex subscriptions, or Cline's own usage billing.clinerules/ or .cline/rules/, AGENTS.md, .cursorrules, .windsurfrulesPlan and Act modes; the CLI starts in act mode with auto-approve on by default; CLINE_SANDBOX env var enables a sandbox modecline "prompt" with --json output; also an SDKYesYesMonorepo with per-app releases (desktop-v0.0.42 on 2026-10-02)
gooseApache-2.0 per the GitHub repo (the docs' llms.txt says MIT)15+ providers (Anthropic, OpenAI, Google, Ollama, OpenRouter, Azure, Bedrock), or existing Claude, ChatGPT or Gemini subscriptions via ACP.goosehints (docs also mention AGENT.md)Not compared; check goose's permission docsgoose run (instructions file or recipe)Yes; extensions are MCP serversYes (SKILL.md in ~/.agents/skills)v1.52.0 (2026-09-23)
AiderApache-2.0Almost any LLM, cloud or local; bring your own keysNo fixed file; load e.g. CONVENTIONS.md with /read or read: in .aider.conf.ymlNo sandbox; edits are auto-committed to git by default (--no-auto-commits to disable)aider --message or --message-fileNot documentedNot documentedv0.86.0 (2025-08-09)

Verdict: Pick by model access first: Claude Code for Claude, Codex CLI for a ChatGPT plan, Gemini CLI for a free tier, Copilot CLI if your org already pays for Copilot, and OpenCode, Cline or goose to bring your own provider. For unattended runs, Codex CLI has the strictest out-of-the-box sandbox; Claude Code's and Gemini CLI's are strong but opt-in, and Cline's CLI auto-approves by default. Aider is still useful for git-centric pair programming but has had no release since August 2025.

What actually differs

All eight read your repository, edit files, run shell commands and loop until the task is done. The differences that matter in practice are narrower than the feature lists suggest:

Sandboxing and approvals, read carefully

"Has a sandbox" means very different things:

For unattended runs in CI, or anywhere the agent reads untrusted input such as issues, web pages or dependencies, run the harness itself inside a disposable environment. The sandboxing guide and code sandboxes comparison cover the options.

Recent changes worth knowing

Not in this table

Cursor (an IDE with a CLI), Amp, Kiro, Qwen Code (a Gemini CLI fork for Qwen models) and OpenHands are also strong options, but they weren't re-verified for this page. To set up any of these harnesses with tools, see the coding agent starter stack and the guide to adding MCP servers to Claude Code.

Directory entries in this comparison

Related

Sources

Machine-readable