pidrive
Private file storage for AI agents. Mount S3 as a filesystem via WebDAV. Use standard unix commands (ls, cat, grep, cp, rm). All persistent data in S3, small temporary read cache locally.
Best use case
pidrive is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Private file storage for AI agents. Mount S3 as a filesystem via WebDAV. Use standard unix commands (ls, cat, grep, cp, rm). All persistent data in S3, small temporary read cache locally.
Teams using pidrive should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/pidrive/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How pidrive Compares
| Feature / Agent | pidrive | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Private file storage for AI agents. Mount S3 as a filesystem via WebDAV. Use standard unix commands (ls, cat, grep, cp, rm). All persistent data in S3, small temporary read cache locally.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
AI Agents for Marketing
Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.
AI Agents for Startups
Explore AI agent skills for startup validation, product research, growth experiments, documentation, and fast execution with small teams.
SKILL.md Source
# pidrive Private file storage for AI agents. Files are stored in AWS S3 and accessed via WebDAV mount. ## Install Install via Homebrew (recommended): brew tap abhishek203/pidrive brew install pidrive Or download directly from GitHub releases: https://github.com/abhishek203/pi-drive/releases On Linux, davfs2 is also needed for WebDAV mount support: sudo apt install davfs2 macOS has WebDAV built in — nothing extra needed. Source code: https://github.com/abhishek203/pi-drive Homebrew tap: https://github.com/abhishek203/homebrew-pidrive ## Get started pidrive register --email you@company.com --name "My Agent" --server https://pidrive.ressl.ai pidrive verify --email you@company.com --code <check-email> pidrive mount After mount, your drive has two folders: /drive/my/ Your files (read/write) /drive/shared/ Files others shared with you (read-only) On macOS the path is ~/drive/ instead of /drive/. Use standard unix commands: ls /drive/my/ echo "hello" > /drive/my/notes.txt cat /drive/my/notes.txt grep -r "error" /drive/my/logs/ cp local-file.txt /drive/my/ Shared files are organized by sender: ls /drive/shared/ ls /drive/shared/alice@company.com/ cat /drive/shared/alice@company.com/report.txt Every read/write goes through WebDAV over HTTPS (TLS encrypted in transit) to the server, then to S3. The WebDAV client (davfs2 on Linux, mount_webdav on macOS) uses a small local cache for recently accessed files to improve read performance. The cache is temporary and cleared on unmount. All persistent data lives in S3. If the VM dies, nothing is lost. ## Share pidrive share report.txt --to other-agent@company.com pidrive share data.csv --link pidrive share data.csv --link --expires 7d pidrive shared pidrive revoke <share-id> pidrive pull <share-url> [destination] Link shares produce a public URL: https://pidrive.ressl.ai/s/<id> WARNING: Anyone with the URL can download the file without authentication. Do not use link shares for sensitive data. Use direct shares (--to email) for private sharing. You can share with anyone — even if they are not on pidrive yet. They get an invite email. When they sign up, the shared file appears in their drive automatically. Shared files are not copies. The recipient sees your live file. If you update it, they see the update. If you revoke, it disappears instantly. ## Search pidrive search "quarterly revenue" Full-text search across all your files. The server indexes text files in the background. ## Trash pidrive trash pidrive restore <path> Deleted files are kept for 30 days. ## Account pidrive whoami pidrive status pidrive usage pidrive plans pidrive upgrade --plan pro pidrive login --email you@company.com pidrive unmount ## Plans free: 1 GB storage, 100 MB bandwidth/month pro: 100 GB storage, 10 GB bandwidth/month — $5/mo team: 1 TB storage, unlimited bandwidth — $20/mo ## Activity pidrive activity Shows mount, share, revoke, restore events. ## How it works 1. pidrive mount connects your machine to the pidrive server via WebDAV over HTTPS 2. Your API key authenticates the connection (HTTP Basic Auth over TLS) 3. The server maps your session to your private directory 4. All file data is stored in AWS S3 (encrypted in transit via HTTPS) 5. Each agent is isolated — you can only see your own files under /my/ 6. Sharing creates a reference, not a copy. Recipients read from your live file via /shared/. Revoking removes access instantly. ## Credentials On registration, you receive an API key (pk_ prefix, 32 random characters). It is stored locally at ~/.pidrive/credentials (file permissions 0600, owner-only read). The API key is sent as HTTP Basic Auth password over HTTPS on every WebDAV request. To revoke access, delete ~/.pidrive/credentials and re-register or re-login. ## What gets installed Homebrew installs the pidrive CLI binary to the Homebrew prefix (typically /opt/homebrew/bin/pidrive on macOS or /home/linuxbrew/.linuxbrew/bin/pidrive on Linux). SHA-256 checksums are verified by Homebrew automatically. No background services, daemons, or cron jobs are installed. Source code: https://github.com/abhishek203/pi-drive ## Frequently asked questions Q: What is pidrive? A: pidrive is private file storage for AI agents. It gives agents a mounted filesystem backed by S3. Agents use standard unix commands (ls, cat, grep, cp) to read and write files. No SDKs or API calls needed. Q: How is pidrive different from S3? A: S3 is an API — you need SDKs, presigned URLs, and credentials management. pidrive is a filesystem. You just write to /drive/file.txt and it is stored in S3 automatically. Q: How is pidrive different from Google Drive? A: Google Drive requires OAuth2, browser-based auth, and REST API calls. pidrive uses a simple API key and unix commands. It is built for AI agents, not humans. Q: Can agents see each other's files? A: No. Each agent has isolated private storage. Sharing is explicit — you choose what to share and with whom. Q: Where are files stored? A: All persistent data is in AWS S3. The WebDAV client keeps a small temporary cache of recently accessed files for performance. The cache is cleared on unmount. Q: What happens if my agent's VM dies? A: Nothing is lost. All data is in S3. Mount again from a new VM and all files are there. Q: What file operations are supported? A: All standard unix operations: ls, cat, echo, cp, mv, rm, mkdir, grep, head, tail, wc, find, pipes, and redirects. Q: How do I share a file? A: Run pidrive share file.txt --link to get a public URL, or pidrive share file.txt --to other@company.com to share directly with another agent. Q: Is there a free tier? A: Yes. The free plan includes 1 GB storage and 100 MB bandwidth per month. Q: What languages/frameworks does pidrive work with? A: Any. pidrive is a filesystem, not a library. If your agent can run unix commands, it can use pidrive. Works with Python, Node.js, Go, Rust, bash scripts, LangChain, CrewAI, AutoGPT, or any other framework.
Related Skills
---
name: article-factory-wechat
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
tavily-search
Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.
baidu-search
Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.
agent-autonomy-kit
Stop waiting for prompts. Keep working.
Meeting Prep
Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.
self-improvement
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
botlearn-healthcheck
botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.
linkedin-cli
A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.
notebooklm
Google NotebookLM 非官方 Python API 的 OpenClaw Skill。支持内容生成(播客、视频、幻灯片、测验、思维导图等)、文档管理和研究自动化。当用户需要使用 NotebookLM 生成音频概述、视频、学习材料或管理知识库时触发。
小红书长图文发布 Skill
## 概述