skills.rest
redis
redisOFFICIAL
Explore all skills by this author →
WebsiteGitHub

agent-filesystem

Mount Redis-backed workspaces via AFS for agent filesystem workflows.

30|6|Updated Apr 5, 2026
Search Tags:#MCP#agent workflow#workspace#checkpointing#Redis#filesystem mounting
One-click install
npx skills add https://github.com/redis/agent-filesystem --skill agent-filesystem
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-filesystem
Source: https://github.com/redis/agent-filesystem/tree/main
Command: npx skills add https://github.com/redis/agent-filesystem --skill agent-filesystem

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps agents work with code and documents as if they were on a normal filesystem, while keeping workspace state stored remotely in Redis for easy checkpointing, restoring, and forking.

Core Features & Use Cases

  • Mount workspaces for local work: Use AFS mounts so agents can run real tools against real directories while edits stay connected to the Redis-backed workspace.
  • Support agent workflows via MCP and checkpoints: Interact with AFS through afs mcp and create durable restore points using explicit checkpoints (afs cp ...).
  • Choose sync vs live mount: Use sync mode for a reconciled local directory, or mount mode for a live Redis-backed filesystem (NFS/FUSE depending on OS).

Use case: An agent needs to edit and run tests on a repository, search across prior notes, and later roll back to a known-good state—without tying the work to one machine’s local disk.

Quick Start

Ask the AI to create and mount a demo workspace so you can start editing files locally: make sure you have Redis available, then run: make commands, ./afs auth login, ./afs ws create demo, ./afs ws mount demo ~/demo, and cd into ~/demo.

Frequently Asked Questions about agent-filesystem

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I give an AI agent a filesystem backed by Redis for checkpointing?▼

You can give an AI agent a Redis-backed filesystem by mounting AFS workspaces, which allows agents to run real tools against local directories while workspace state stays stored in Redis for checkpointing and restoring.

What is the difference between sync mode and live mount mode for agent filesystems?▼

Sync mode provides a reconciled local directory copy, while live mount mode exposes a live Redis-backed filesystem using NFS or FUSE depending on the operating system for direct agent interaction.

How do I create and restore checkpoints when an agent edits files in a workspace?▼

Checkpoints are created and restored explicitly using AFS CLI commands like `afs cp`, ensuring durable restore points that let agents roll back workspace edits to a known-good state without tying work to one machine.

Can I use MCP to let an agent read and edit workspace files directly?▼

Yes, agent clients can read and edit workspace content through the integrated `afs mcp` interface, supporting agent-first filesystem workflows and remote workspace interactions via the AFS CLI.

What do I need to set up before mounting an agent workspace?▼

You need a Redis instance available and the AFS CLI to run auth login, workspace create, and workspace mount commands before agents can start editing files in the mounted directory locally.

Related Skills

Explore More Software Engineering Skills→
OceanswaveOceanswave

openclaw-tescmd

Guides installation and configuration of the OpenClaw Tesla tescmd integration.

Community
Advanced
junechen7414junechen7414

skills-cli

Discover, install, and manage Agent Skills via the skills CLI.

Community
Advanced
redisredis
30

codex-settings-sync

Migrates Codex state from ~/.codex to a Redis-backed Agent Filesystem workspace.

Official
Intermediate
dzhngdzhng
106

crm-cli

Manage CRM contacts, deals, and pipeline via a SQLite-backed CLI and virtual filesystem.

Community
Advanced