OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Coding Agents

Frontagent

Frontagent is an open-source AI coding agent for frontend engineering. It plans and executes code changes through a CLI, VS Code extension, desktop app or local MCP server, using repository-aware retrieval, SDD constraints and browser-aware automation.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Frontagent — OpenViST project profile in Coding Agents.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Frontagent when a frontend task benefits from repository-aware planning, explicit project constraints and an agent workflow that can be operated in a terminal, editor, desktop app or MCP host.

Who it is for

  • Frontend developers who want an agent to create or refactor web application code.
  • Teams that need project-specific rules and approval requirements to shape agent work.
  • Developers who want to use frontend agent tasks from an MCP host.

Documented uses

  • Generate or refactor React, TypeScript, Vite and Tailwind CSS code.
  • Plan changes using project structure, repository retrieval and module dependencies.
  • Inspect pages and support browser-aware validation.
  • Apply minimal code patches and use error recovery during multi-phase tasks.
  • Connect an MCP host to Frontagent's agent-level planning and task capabilities.
Before you choose

Requirements & limits

The CLI requires Node.js 20 or later. The repository identifies the project as MIT-licensed.

  • The documented CLI setup uses an OpenAI or Anthropic provider configuration; published planner adapters also support plan generation on specified Qwen Coder base models.
  • The interfaces differ: CLI for terminal tasks, VS Code for an editor task console, desktop for a standalone task console, and MCP for host-integrated agent functions.
  • Shell commands require user approval; SDD can encode protected files and approval requirements.
  • The MCP server binds each process to one resolved project root.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up the Frontagent CLI for a project

Install the CLI, configure an LLM provider and initialize SDD in a frontend project.

Before you start

  • Node.js 20 or later
  • An OpenAI or Anthropic provider configuration with base URL, model and API key

Steps

  1. Install Frontagent globally with npm, pnpm or yarn.

  2. Set PROVIDER, BASE_URL, MODEL and API_KEY for OpenAI or Anthropic.

  3. Change to the project directory and run fa init to initialize SDD.

Expected outcome

The CLI is installed, provider settings are configured, and SDD is initialized in the project.

Guide limitations

  • The documented setup does not include a task execution step.
  • Provider credentials are required for the documented direct LLM configuration.
Documentation 1 ↗
Source-based practical guide

Configure Frontagent as an MCP server

Add the installed Frontagent CLI as a local stdio MCP server in an MCP host.

Before you start

  • Frontagent installed as a CLI
  • An MCP host that can launch a command-based stdio server

Steps

  1. Add an mcpServers entry with command fa and args mcp, serve to the host configuration.

  2. If the host cannot find fa because its PATH differs from the terminal, configure absolute paths for Node.js and the CLI.

  3. Set provider environment variables in the host configuration if using direct LLM fallback.

Expected outcome

The host configuration points to Frontagent's local MCP server, which exposes agent-level status, planning and task functions.

Guide limitations

  • One server process is bound to one resolved project root.
  • MCP mode exposes upper-level agent capabilities, not raw internal tools such as file operations, shell commands or browser tools.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for AI coding assistance

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
FrontagentGenerate or refactor React, TypeScript, Vite and Tailwind CSS code.CLI, Desktop, WebThe CLI requires Node.js 20 or later. The repository identifies the project as MIT-licensed.
LlmcodeInspect a project's directory structure with `/tree`.CLIThe documented setup requires an API key and supports an API base URL and model setting. The project is open source under Apache-2.0.
Klaat CodeOpen a project directory for terminal-based coding assistance.CLI, ServerThe README provides a global npm installation command and documents browser sign-in with a KlaatAI account. It also identifies the repository as open source under Apache 2.0.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
13 October 2026
Original website title
ceilf6/FrontAgent · Official homepage title · retained in its source language
How we review sourcesSuggest a correction