# Add to your Claude Code skills
git clone https://github.com/docsagent/docsagent
SKILL.md
name: docsagent
description: Search and manage private, local document collections (PDF, PPTX, DOCX) offline. Use when you need to find information within your private files, not for web research.
DocsAgent Skill
DocsAgent is a local-first documentation engine designed to perform lightning-fast hybrid search (text and semantic search) over your private local files.
Key Features
Privacy-First: All indexing and searching happen 100% locally on your machine. No documents or data ever leave your system.
Hybrid Search: Combines semantic and keyword-based text search for high accuracy.
Supported Formats: Optimized for PDF, PPTX, and DOCX files.
No Web Dependency: This tool does not perform web searches. It relies on a local index you create.
Privacy Guarantee
100% Local: All processing, indexing, and search operations are performed entirely on your machine.
Zero Data Leakage: No data is sent to external servers. Your documents remain private.
When to use
Use this when searching for information within your own private documentation, research papers, reports, or presentations.
Do not use this for general internet queries, news, or public website information.
Installation
DocsAgent is a CLI toolkit, when you install the global docsagent package, You can directly use 'docsagent' command.
npm install -g @docsagent/docsagent
For more information, please see https://github.com/docsagent/docsagent.
Usage Guidelines
1. Add Documentation
Adds directory or file paths (PDF, DOCX, PPTX) to the index. You can pass multiple paths at once.
# Add a single directory
docsagent add ./documents/manuals
# Add multiple files and directories at once
docsagent add ./reports/q1.pdf ./presentation.pptx ./notes/meeting-files
Use case: Use to index folders or specific private files for searchability.
README.md
DocsAgent 🛡️
The High-Performance Local Intelligence Layer for AI Agents.
DocsAgent is a professional, local-first documents intelligence engine and MCP (Model Context Protocol) server. It provides a secure, near-instant bridge between your private local files and advanced agentic platforms like OpenClaw, Claude Code, and Cursor.
100% Local. 100% Private. Zero Data Leakage.
🔥 Why DocsAgent?
Modern AI Agents are incredibly smart, but they are "blind" to your private desktop documents. DocsAgent acts as a High-Performance Intelligence Engine that indexes your local data, allowing agents to search, read, and analyze thousands of files (1,000+) with absolute privacy.
🔒 Absolute Privacy: All document parsing, indexing, and vector storage happen strictly on your own hardware. Your data never leaves your machine.
⚡ High-Performance Core: Powered by a native C++ engine. Experience millisecond-level retrieval even across massive document libraries.
🔌 MCP Native: Built-in support for the Model Context Protocol (MCP), making it instantly compatible with the latest AI tools.
📂 Format Mastery: Native parsing for PDF, Word (.docx), PPTX.
🚀 Quick Start
📄 SKILL.md
This file provides detailed instructions and guidelines for using the DocsAgent skill, including its purpose, features, and usage examples.
Performs a hybrid search (text + semantic) across your indexed private documents.
# Search for a specific topic
docsagent search "how to configure local encryption"
# Search for technical concepts
docsagent search "API authentication process"
The tool returns the most relevant snippets with their source paths and scores.
Important: Ensure your documents have been indexed using the add operation before searching.
3. List Indexed Sources
Lists all files currently being monitored or indexed.
docsagent list
4. Check Status
Shows the indexing progress and service health.
docsagent status
5. Stop Agent
Stops the indexing service.
docsagent stop
Workflow: Answering Questions from Local Docs
Check Index: If unsure if the documents are indexed, you can try a search first.
Search: Execute search with a specific query derived from the user's request.
Analyze: Review the context returned. If multiple snippets are found, synthesize them into a coherent answer.
Cite Sources: Always mention the file path and page number (if available) in your response.
Error Handling
If search returns "No results found", inform the user and ask if they want to index a specific directory using add.
If a path is not found during add, verify the path exists before retrying.
DocsAgent provides a powerful CLI with convenient aliases (dag, da):
| Command | Alias Example | Description |
| :--- | :--- | :--- |
| server | da server | Start the MCP server service |
| add | dag add <path> | Add directories or files to the index |
| search | da search "query"| Search for documents directly from CLI |
| status| dag status | Check engine and indexing status |
| stop | da stop | Stop the background engine service |
📂 Support Matrix
| Format | Status | Features |
| :--- | :--- | :--- |
| PDF | ✅ Full | Deep layout analysis & high-speed parsing |
| Word (.docx) | ✅ Full | Table extraction & heading hierarchy preserved |
| PPTX | ✅ Full | Extracts slides, shapes, and speaker notes |
🤝 Community & Contributing
We are building the open standard for Local RAG. Join us in making AI respect personal data sovereignty!
GitHub Issues: Found a bug? Have a feature request? Open an issue.
Star the Repo: If DocsAgent improved your workflow, please give us a ⭐ to help others find the project!
⚖️ License
DocsAgent is open-source under the Apache-2.0 License.
Desktop Sovereignty is here. Empower your Agents with DocsAgent.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
A Claude Code plugin that automatically captures everything Claude does during your coding sessions, compresses it with AI (using Claude's agent-sdk), and injects relevant context back into future sessions.
