fff
SHA-256fff is a file search toolkit for humans and AI agents, offering typo-resistant path and content search, frecency-ranked access, background watching, and a lightweight in-memory index. It outperforms ripgrep and fzf in long-running processes with multiple searches.
Smart Download
Download Download Version
v0.9.1 · 8.7 MB
A fast, frecency-ranked file search toolkit for AI agents and editors, faster than ripgrep and fzf in repeated searches.
Core Features
- Typo-resistant path and content search with automatic fuzzy fallback
- Frecency ranking: frequently opened files rank higher
- Background file watcher for real-time index updates
- Lightweight in-memory content index, faster than ripgrep/fzf on repeated queries
- MCP server for AI agents (Claude, Cursor, Codex, etc.)
What It Can't Do
- •Some features require a prebuilt binary or a Rust build environment; first run downloads the binary automatically so internet access is needed. MCP server works only with MCP-capable clients; configuration varies per client.
Use Cases
- Fast file and content search in large codebases, boosting developer productivity
- Backend search tool for AI coding assistants, reducing latency and token waste
Detailed Introduction
fff is a file search toolkit designed for both humans and AI agents. It provides typo-resistant path and content search, frecency-ranked file access, a background file watcher, and a lightweight in-memory content index. Compared to ripgrep and fzf, fff is significantly faster in any long-running process that performs multiple searches, thanks to its persistent index and smart caching. It includes an MCP server for AI agent integration, a Pi agent extension, and a Neovim plugin. It supports fuzzy search, smart-case handling, git-aware annotations, and definition-first hinting to reduce latency and token waste in AI workflows.
Tags
Getting Started
Download installer
Click the button above to download the installer for your system
Install the software
Double-click the downloaded installer and follow the prompts
Install MCP server on Linux/macOS with curl command, then follow printed wiring instructions for your AI client.
Install Neovim plugin via lazy.nvim or vim.pack, the plugin auto-downloads prebuilt binary.
Install Pi extension by running `pi install npm:@ff-labs/pi-fff`.
- Install MCP server on Linux/macOS with curl command, then follow printed wiring instructions for your AI client.
- Install Neovim plugin via lazy.nvim or vim.pack, the plugin auto-downloads prebuilt binary.
- Install Pi extension by running `pi install npm:@ff-labs/pi-fff`.
SHA-256 checksum verified
Checksum extracted from GitHub official Release page
SHA256 Checksum
40b87349c1e9cd58d389003af27bbd415567db817925cd3ec91a075e33208542This checksum is extracted from the GitHub Release page. Verify file integrity after download.
All SHA-256 checksums on this platform are extracted from the project's official GitHub Release page, without any modification. You can independently verify them on the GitHub Releases page.
Open Source Transparency
View GitHub SourceUninstall Info
MCP server: remove the downloaded script and config files. Neovim plugin: remove plugin declaration and clean cache. Pi extension: run `pi uninstall npm:@ff-labs/pi-fff`.
No Extra Dependencies
Ready to use after download. No additional runtime required.
Similar Projects
Visual Studio Code (Code - OSS)
A free, open-source code editor by Microsoft with rich extensions, debugging, and Git integration. The most popular developer tool worldwide.
scrcpy
Display and control your Android device from your computer via USB or TCP/IP. No root required, high performance, low latency, supports audio and video mirroring.
godot
Godot Engine is a free, open-source, cross-platform 2D and 3D game engine with a unified editor. Unlike Unity or Unreal, it's entirely MIT-licensed and community-driven, offering a lightweight yet powerful node-based workflow that runs on a single executable.