by ceilf6 · MCP Server · ★ 107
FrontAgent Enterprise-grade AI Agent System - Constrained by SDD, Powered by MCP for Controlled Perception and Execution 中文文档 Design Doc FrontAgent is an AI Agent system designed specifically for frontend engineering, addressing core challenges faced when deploying agents in real-world engineering scenarios: Distilled Planner Model: FrontAgent's Planner stage has been distilled into a standalone small model frontagent-planner-7B-lora. Load the LoRA adapter on top of Qwen2.5-Coder-7B to generate frontend execution plans directly, without calling large LLM APIs.
| Stars | 107 |
| Forks | 15 |
| Language | TypeScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 67.2387899643089/100 |
| Open Issues | 8 |
| Last Updated | 2026-07-01 |
| Created | 2025-12-16 |
| Platforms | browser, cli, mcp, node |
| Est. Tokens | ~25k |
These tools work well together with FrontAgent for enhanced workflows:
Explore other popular mcp server tools:
FrontAgent is Frontend AI coding agent platform with CLI, VS Code extension, desktop app, MCP server, RAG planning, Skills, SDD guardrails, browser automation, and LoRA planner models | 面向前端工程的 AI Agent 平台,支持 CLI、V. It is categorized as a MCP Server with 107 GitHub stars.
FrontAgent is primarily written in TypeScript. It covers topics such as agent, controllable, feedback.
You can find installation instructions and usage details in the FrontAgent GitHub repository at github.com/ceilf6/FrontAgent. The project has 107 stars and 15 forks, indicating an active community.
FrontAgent is released under the MIT license, making it free to use and modify according to the license terms.