Best AI Coding Plans (2026)

The best OpenCode alternatives are the terminal coding agents developers say they moved to in blog posts and Hacker News threads, checked against independent hands-on reviews. If OpenCode feels bloated, get Pi, or oh-my-pi if you want Pi with the tools already built in. If you want one vendor's best models at a flat monthly price, get Claude Code or Codex CLI. That is the real OpenCode vs Claude Code difference: Claude Code runs only Claude models, OpenCode any provider. Codex sandboxes commands by default. For open source with any model and no single company in charge, get goose. For the nicest terminal interface, Crush. For an agent that asks before every edit, Cline CLI. To pay nothing for models, Freebuff, which shows ads. For a desktop app that runs any model, DeepSeek Harness. If you pay for GitHub Copilot, its CLI is included. OpenCode Go, the $10 model plan, also works in Pi, Claude Code and Codex. What the makers' pages won't tell you. On October 17, 2026 attackers broke into an older OpenCode system and reached provider keys saved in OpenCode Console, affecting 1.4% of Console users. TechCrunch reports charges above $1,000 on some accounts, and OpenCode's co-founder says the app and CLI were not affected. Revoke a saved key at the provider: deleting it in OpenCode doesn't stop a stolen copy. OpenCode 2 has a new plugin API, so OpenCode 1 plugins don't run on it. Crush grew out of an older Go project also called OpenCode, and its license is source-available, not open source. Gemini CLI stopped serving personal accounts on June 18, 2026; Antigravity CLI replaced it. Aider has had no commits since May 22, 2026. Kilo CLI is built on OpenCode, so switching to it changes little. A free agent still needs a model: you pay a provider per token or run one yourself. The list is ordered by how many independent developers and reviewers recommend each agent, then by GitHub stars, then by price. Prices checked October 24, 2026.

The best OpenRouter alternatives, hosted routers and gateways you run yourself, picked from developers who switched and reviewers who measured them. Each one still gives you one API for many AI models. Match the pick to your reason for leaving. If it is the 5.5% fee on credits, Vercel AI Gateway charges no markup, and Cloudflare AI Gateway is free when you bring your own provider keys. If you want no middleman at all, self-host LiteLLM, or Bifrost if LiteLLM's latency bothers you. If your data must stay in Europe, look at Cortecs or Requesty. If you are tired of one model behaving differently from host to host, buy from a single host such as Fireworks AI, Together AI or Groq, or use OpenCode Zen's short tested list. This market changed fast in 2026, so older guides are wrong in places. Stripe announced in August that it is buying OpenRouter. Palo Alto Networks bought Portkey in May. Helicone has been in maintenance mode since Mintlify bought it in March, and TensorZero's repository is archived, which is why neither is here. LiteLLM had two poisoned releases on PyPI in March (1.82.7 and 1.82.8), so pin your version. Self-hosting takes the gateway company out of the path, but your prompts still go to whichever model provider you call. And OpenRouter's fee is charged when you buy credits, with an $0.80 minimum, so small top-ups cost more than 5.5%. The list is ordered by how many independent developers and reviewers recommend each option, then by adoption, then by price. Prices checked October 11, 2026.

The best OpenCode plugins for OpenCode 2 (v2), from DCP to Superpowers, ranked by independent picks and hands-on tests. OpenCode 1 plugins won't load on 2. If your sessions run out of context, start with Dynamic Context Pruning. If you want the agent to plan before it codes, get Superpowers, or Plannotator to review plans in a browser. For a team of subagents, oh-my-opencode-slim is the one that runs on the current version. For memory that stays on your machine, opencode-mem. To see each provider's quota and token spend, opencode-quota. The thing no plugin page says loudly: plugins written for OpenCode 1 do not load on OpenCode 2, even when you rename the config entry. Check the Works with line on each pick before you upgrade; the OpenCode 2 sections below say what else changed. Two names to keep straight. The OpenCode here is the one at opencode.ai, now in the anomalyco/opencode repository on GitHub. An earlier Go project with the same name, opencode-ai/opencode, is archived and continues as Crush. And oh-my-opencode was renamed oh-my-openagent. Plugins that sign you in with a Claude or Gemini subscription are left out. Google and Anthropic treat that as against their terms, the popular Antigravity one is archived, and accounts have been flagged. A plugin runs with your full permissions, so read what you install. Ordered by how many independent recommendations each plugin has, then by downloads and stars. A plugin that does not load on the current OpenCode ranks below the ones that do. Numbers checked October 24, 2026.

The best Pi extensions for subagents, web search, plan mode and permissions, picked from the setups developers publish, each with its pi install command. Pi is deliberately bare: no sub-agents, no plan mode, no permission prompts. You add what you miss with one command, pi install npm:<package>. If you are starting out, three cover most of the gap with Claude Code: pi-subagents for delegation, pi-web-access for search, and rpiv-ask-user-question so the model asks before it guesses. Add Plannotator if you want plan mode, and pi-permission-system or pi-landstrip if you don't want the agent free to run anything. Three things have changed that older guides miss. Pi 1.0 shipped on October 1, 2026, and every pick here has had a release since except context-mode and pi-simplify, which we couldn't confirm on 1.x. Pi has had MCP support built in since version 0.99, so pi-mcp-adapter is now an upgrade and no longer a requirement. And several popular names have lookalikes: npm has at least four other packages named pi-mcp-adapter under other people's scopes, and more than one /btw and /simplify extension, so install by the exact name shown here. Extensions run with the same access to your machine that Pi has. Pi's catalog lists more than 5,000 packages, so read the source of anything that touches your shell or credentials, and pin versions you depend on. Ordered by how many independent users and reviewers recommend each one (Kay Rhodes's setup guide, Composio's tested top ten, XDA's hands-on, developers on Hacker News and Pi's own GitHub discussions), then by npm downloads and GitHub stars. Downloads count automated installs too, so treat them as a rough signal. Numbers checked October 24, 2026.

The best local LLM for coding depends on how much memory your machine has. This list ranks open-weight models you can run yourself, by independent benchmark runs and by developers who use them in coding agents. With 24 to 32 GB, start with Qwen3.8-27B. Its 17 GB 4-bit file matched the full model on Terminal-Bench 2.1 in Quesma's test. With 128 GB of unified memory, Qwen3.8-Flash-Next posted the top score in WonderRico's benchmark. With 16 GB, gpt-oss-20b fits whole on the card, and one developer reports useful work from a 2-bit Qwen3.8-27B. With 8 GB, try Qwen3.5-9B and keep the jobs small. At 64 GB, run the 27B models at 8-bit, a 29 GB file, with a longer context. The step above that needs about 100 GB. A coding agent only works if the model emits tool calls your server can parse. Gemma 4 shipped with broken tool calling that was fixed later, and Qwen chat templates have needed community fixes, so update Ollama, LM Studio or llama.cpp before blaming the model. Agents also need room: LM Studio loads models with an 8,192-token context unless you raise it. Scores on a model card are the maker's own. A mixture-of-experts model computes with a few billion parameters per token but still has to hold all of them in memory, and context takes memory on top of the file. Qwen3.8 thinks at its highest effort by default, which is slow on home hardware. Qwen3.8-Flash-Next is not Apache licensed. Older guides still recommend Qwen2.5-Coder, Qwen3-Coder and Devstral, which general-purpose models beat in the hands-on tests cited here. The list is ordered by how many independent testers and developers recommend each model for coding, then by downloads. Numbers checked October 11, 2026.

The best Claude Code plugins are Superpowers, a language server plugin for your language and Frontend Design, judged by the setups developers publish after pruning their installs and by what Hacker News users say they kept. A plugin is a bundle. One install can carry skills, slash commands, subagents, hooks and MCP servers. A skill is a single instruction file Claude loads when it judges it relevant, and an MCP server is a connection to an outside tool, so a plugin can contain both. If you install one thing, make it Superpowers, plus the LSP plugin for your language. Add Security Guidance if you ship code you don't read line by line, Plannotator if you want to mark up plans in a browser, and Claude HUD to see how full the context is. For web work, Frontend Design shapes the look, and Playwright or Chrome DevTools MCP lets Claude check the page in a real browser. Every enabled plugin adds to the context on every turn, and several of the writers quoted here deleted more than they kept. Token savers promise more than they deliver: a JetBrains test cut Caveman's advertised 65% to 8.5%. Plugins run code on your machine with your permissions, and Anthropic doesn't review third-party marketplaces, so read what a plugin will install before you say yes. Two names trip people up. Claude Code has a built-in review command alongside the Code Review plugin. And Anthropic's claude-security plugin, in beta, is a whole-repository scan, separate from Security Guidance. The list is ordered by how many independent people recommend each plugin, then by installs and GitHub stars. Numbers checked October 24, 2026.