AI agents running tests are non-reproducible; hand-written Playwright is hard to maintain. Four tools that emerged in 2024-2025 each tackle this dilemma with very different design philosophies.
Antigravity CLI is a terminal agent Google announced at I/O on May 19, 2026. Written in Go (versus Gemini CLI's Node.js), its binary is called agy, and it shares the same agent harness as the desktop Antigravity 2.0. It is also Gemini CLI's successor — the personal-tier Gemini CLI service ends on June 18, 2026.
/loop is Claude Code's native cron feature — set schedules in plain English and let Claude monitor, auto-fix PRs, and run recurring tasks in the background. Session-scoped and expires after 7 days; for cross-session scheduling, use Routines or Desktop scheduled tasks.
Akira runs a Threads → Blog → Docs three-tier funnel with agent-assisted publishing, building a sustainable knowledge monetization model in the Chinese-language AI content market.
Claude Code only reads CLAUDE.md; Codex only reads AGENTS.md. Teams using both end up maintaining two identical files. Fix: make CLAUDE.md a symlink pointing to AGENTS.md — one source of truth.
code-review-graph uses Tree-sitter to parse your codebase and build a persistent knowledge graph, tracks the blast radius of changes, and feeds only truly relevant context to the AI — claiming an average 8.2x reduction in token usage.
Claude Code is Anthropic's agentic coding tool that runs in the terminal, IDEs, Slack, GitHub, and on the web. Its core extension system has six layers: CLAUDE.md (persistent context), Skills (on-demand workflows), Hooks (deterministic automation), Subagents (isolated delegation), MCP (external tool connections), and Agent Teams (multi-agent collaboration).
Codex CLI is OpenAI's open-source terminal coding agent built in Rust. It supports MCP, subagents, image input, and code review. Paired with the codex-1 (o3-optimized) or GPT-5-Codex model, it can read, write, and execute code directly on your local machine.
Gemini CLI is Google's open-source terminal AI agent (Apache 2.0). ⚠️ Announced end-of-service on 2026/06/18 — official migration path is Antigravity CLI. Free accounts get 60 requests/minute and 1,000 requests/day; Skills, Hooks, and Subagents all carry over.
OpenCode is an open-source AI coding agent built in Go (95K+ GitHub stars) with a built-in TUI, support for 75+ LLMs, LSP integration, Vim-style editing, and SQLite session management. Free, no subscription required — works with local or cloud models.
Pi is a minimalist coding agent built in TypeScript by Mario Zechner, featuring just 4 core tools (read, write, edit, bash) and a 300-word system prompt. It's extensible via Extensions, Skills, and Prompt Templates, runs on the Bun runtime, and ships with built-in Ollama support via `ollama launch pi`.
When processing requests, Claude Code randomly displays one of 185 built-in verbs (like Thinking, Brewing, Clauding), then picks one of 8 completion verbs with elapsed time. You can customize these via spinnerVerbs in settings.json, using either replace or append mode. All data in this post is verified directly from cli.js source code.
Claude Code has five permission modes: default (confirm each step), acceptEdits (auto-accept edits), plan (read-only planning), auto (background AI classifier review), and bypassPermissions (YOLO, skip everything). Switch with Shift+Tab or configure via settings.json. Auto mode is the sweet spot — no step-by-step confirmations, but with safety guardrails.