Coding Agents
8apps · local AI compatibility & hardware requirements
AI coding agents autonomously explore your codebase, edit files across multiple locations, run terminal commands, and iterate on their own output. Some are local-first (Aider, Continue), some are hybrid (Cline, Roo Code, Kilo Code), and some are cloud-only (Cursor, Claude Code). The key hardware question is whether your GPU can run the models these agents need — not the agent itself.
- AiderAI pair programming in your terminal. The most local-model-friendly coding agent with a tiny ~2K token system prompt and deep git integration.· OpenRouter
- Claude CodeAnthropic's official agentic coding CLI. Reads your entire codebase, plans and executes changes across files, runs tests, and iterates on failures.· OpenRouter
- ClineOpen-source AI coding agent for VS Code. Autonomously explores your codebase, edits files, runs terminal commands, and uses browser automation.· OpenRouter
- ContinueOpen-source AI code assistant for VS Code and JetBrains. Tab autocomplete, chat, and agent mode with separate models per role — like a local Copilot.· OpenRouter
- CursorAI-native IDE built on VS Code. Integrated tab completion, inline editing, chat, and agent mode — all in one editor. Cloud-only, no local model support.
- Kilo CodeOpen-source AI coding agent for VS Code, JetBrains, and CLI. The only Cline-family agent with JetBrains support. Claims highest-volume consumer on OpenRouter.· OpenRouter
- Roo CodeOpen-source multi-agent AI coding extension for VS Code. Customizable modes for coding, architecture, debugging, and review — with a smaller system prompt than Cline.· OpenRouter
- ZedHigh-performance code editor with AI features via API keys. Bring your own Anthropic or OpenAI key for inline code generation and chat.
Want to check if your GPU can run the models these apps need? Use the homepage calculator to see which models fit your hardware with estimated tokens per second.