fuxicodex/fuxi

FuXi is a fast, self-contained AI coding agent that lives in your terminal — edit code, run commands, and drive tools, with cost-aware routing across LLM...

View on GitHub ↗Jump to charts ↓Open shareable report

Summary Information

Updated 1 hour ago
Added to GitGenius on September 20th, 2026
Created on August 4th, 2026
Open Issues & Pull Requests: 0 (+0)
GitHub issues: Enabled
Number of forks: 228
Total Stargazers: 3,352 (+0)
Total Subscribers: 93 (+0)

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 0
New in 7 days: 0
Closed in 7 days: 0
Avg open age: N/A days
Stale 30+ days: 0
Stale 90+ days: 0

Recent activity

Opened in 7 days: 0
Closed in 7 days: 0
Comments in 7 days: 0
Events in 7 days: 0

Top labels

No label distribution available yet.

Most active issues this week

No issue events were indexed in the last 7 days.

Detailed Description

FuXi is a terminal-based AI coding agent that automates code editing, command execution, and tool interaction while routing requests across LLM providers based on cost.

The tool addresses the friction of switching between code editors, terminals, and AI assistants by embedding an autonomous agent directly in your terminal environment. It operates as a self-contained application that can read and modify files, execute shell commands, and invoke external tools without requiring manual context-switching. The cost-aware routing mechanism selects among available LLM providers based on pricing and performance characteristics, allowing developers to optimize their spending while maintaining capability.

FuXi suits developers who spend significant time in terminal workflows and want to accelerate repetitive coding tasks without leaving their shell environment. It works well for projects where rapid iteration and direct command execution are valuable, particularly when working across multiple codebases or managing infrastructure-as-code. The tool's support for OpenAI-compatible providers gives flexibility in choosing which LLM backend to use, rather than locking users into a single service.

The project shows active development with regular commits addressing bug fixes and feature improvements. Work spans multiple areas including core agent functionality, provider integrations, and terminal interface refinement. The codebase maintains focus on the stated goals of speed and self-containment rather than expanding into unrelated domains.