F

Fuxi

FuXi is a terminal-based AI coding assistant supporting code editing, command execution, and tool-driven workflows.

🌍 OverseasFreeOpen sourceDev开源桌面操作API
Platforms: DesktopAPI
Region
Overseas
Pricing
Free
Open source
Yes
GitHub Stars
★ 1.8k
Views
4
Source
GitHub
Added
2026-08-24
Last verified
2026-08-24

Overview

FuXi is a fast and self-contained terminal AI coding agent that enables code editing, command execution, and tool driving within the terminal. It supports cost-aware routing across multiple LLM providers with automatic failover. Built in Go, FuXi delivers a single static binary with no runtime dependencies. It is designed to enable the Think → Act → Verify loop for any OpenAI-compatible model, enhancing its performance. Users can use their own API keys or sign in via FuXi OAuth.

Key features

  • 50+ built-in tools, including file read/write and shell commands
  • Security measures ensuring safe autonomous operation
  • Persistent sessions and memory management
  • Support for multiple LLM providers
  • Extensibility with plugin support and hot reloading

Use cases

Code editing and debuggingAutomated script generationProject management and maintenanceCode review and refactoring

Pros

  • Free with no runtime dependencies
  • Supports multiple LLM providers
  • Rich built-in toolset
  • Automatic update feature

Limitations / notes

  • Requires internet connectivity
  • Higher learning curve

Who it's for

DevelopersSoftware engineersTechnical teams

This overview was compiled by AI from public sources and may contain inaccuracies — please refer to the official site.

FAQ

Is it free?

Yes, FuXi is free for individuals, teams, and enterprises.

Does it support Chinese?

The documentation has a simplified Chinese version, but specific support details need further confirmation.

Can it be used commercially?

Yes, FuXi is free for both personal and commercial use.

Do I need to use a proxy or scientific internet access?

Possibly, depending on the LLM provider being used.

Similar agents

Something wrong? Let us know on the About page and we'll fix it.