dmtrKovalenko

fff.nvim

Other#Neovim#AI#Fuzzy Search#Rust #Developer Tools

// summary

fff.nvim is an opinionated, high-performance fuzzy file picker designed for both Neovim users and AI agents. It features advanced search capabilities including grepping, globbing, and typo-resistant fuzzy matching with built-in memory for improved results. The tool integrates seamlessly with git and provides cross-mode suggestions to ensure developers find the right files quickly.

// technical analysis

FFF is an opinionated, high-performance fuzzy file finder and grep tool designed for both Neovim users and AI agents. Its architecture prioritizes speed and intelligent search results by incorporating built-in memory features like frecency, git status awareness, and file metadata analysis. By providing a unified interface for file discovery and content searching, it aims to reduce token consumption for AI agents and improve developer workflow efficiency through typo-resistant matching and advanced filtering capabilities.

// key highlights

Implements a high-performance fuzzy matching algorithm that supports typo-resistant searches and Smith-Waterman scoring.

Provides an MCP-compatible interface that allows AI agents to perform faster, context-aware file searches with reduced token usage.

Features cross-mode suggestions that automatically offer content matches when file searches fail, and vice versa.

Supports complex search constraints, including git status filtering, glob patterns, and negation logic for precise result refinement.

Integrates deeply with Neovim, offering multi-select functionality, quickfix list integration, and highly customizable UI layouts.

Includes built-in memory mechanisms like frecency tracking and query history to boost the relevance of search results over time.

// use cases

High-performance fuzzy file searching and live grepping within Neovim

Memory-enhanced file search tools for AI agents to reduce token usage

Advanced file filtering using git status, glob patterns, and frecency-based scoring

// getting started

For Neovim, install the plugin using a manager like lazy.nvim, which will automatically handle binary downloads or local builds. For AI agents, use the provided bash script to install the MCP dependency and configure your agent's CLAUDE.md to utilize the fff tools. Once installed, use the default keybindings like 'ff' for file finding or 'fg' for live grep to begin searching your project.