> ## Documentation Index > Fetch the complete documentation index at: https://docs.augent.app/llms.txt > Use this file to discover all available pages before exploring further. # >
Welcome to Augent
Augent - Audio intelligence for agents *** ## What is Augent? Augent turns any audio or video source into structured, searchable intelligence for agents. Hours of content, seconds to master it. One install, full pipeline, entirely on your machine. **Who is it for?** Anyone who needs to pull real answers out of audio. Entrepreneurs, researchers, developers, legal teams, educators, analysts. If your workflow touches audio or video, Augent handles it. **What makes it different?** * **Full pipeline:** download, transcribe, search, analyze, export. Tools added and improved continuously. One install, all of it, and more * **Local and private:** everything runs on your machine, nothing leaves it * **Permanent memory:** every transcription is remembered. The first run transcribes; every search after that is instant * **Scale:** batch process entire libraries in one prompt with no file limit * **Agent-native:** compatible with any MCP client *** ## Quick start ```bash theme={null} curl -fsSL https://augent.app/install.sh | bash ``` Install demo Run `/mcp` to confirm Augent is connected.
Claude Code
Download these 10 podcasts and find every moment a host covers a product in a positive or unique way. Not just brand mentions, only real endorsements or life-changing recommendations. Give me the timestamps and exactly what they said: url1, url2, url3, url4, url5, url6, url7, url8, url9, url10
Need the full install and setup options? See [Quick start](/getting-started/quick-start). *** ## How it works (short) ```mermaid theme={null} graph TB subgraph Pipeline [" "] direction LR A["URL / File"] --> B["Download + Separate"] --> C["Transcribe"] --> D["Memory + Tag"] end D --> E["Search"] D --> F["Analyze"] D --> G["Export"] style A fill:#0d2618,stroke:#00f060,color:#00f060,stroke-width:2px style B fill:#0d2618,stroke:#00f060,color:#00f060,stroke-width:2px style C fill:#0d2618,stroke:#00f060,color:#00f060,stroke-width:2px style D fill:#0d2618,stroke:#00f060,color:#00f060,stroke-width:2px style E fill:#0a0a0a,stroke:#00f060,color:#00f060,stroke-width:2px style F fill:#0a0a0a,stroke:#00f060,color:#00f060,stroke-width:2px style G fill:#0a0a0a,stroke:#00f060,color:#00f060,stroke-width:2px style Pipeline fill:none,stroke:none linkStyle default stroke:#00f060,stroke-width:1.5px ``` Augent is a pipeline. Audio goes in as URLs or files and comes out as searchable, analyzable text. See the full [architecture](/architecture) for details. **Download** extracts audio-only from any URL using yt-dlp and aria2c with 16 parallel connections. **Transcribe** runs the file through faster-whisper locally. The result is **stored** by file hash in SQLite, so every subsequent operation on that file is instant. Once it's in memory, every tool works on the stored transcript: keyword search, semantic search, batch processing, speaker ID, chapters, notes, and text-to-speech. Install and run your first search in under a minute Full reference for all 21 tools How the pipeline, memory, and search work under the hood *** ## Through the wormhole The full architecture: Claude orchestrates, Augent feeds intelligence, automation platforms execute. Turn spoken workflows into complete, replicable systems with audio and visual context. Zero to working agentic workflow in 30 minutes. Step-by-step. Your audio memory as a navigable knowledge graph. ## Explore Full reference for every tool. Clips, highlights, source separation, workflows, and configuration. Make every .txt and .md file open directly in Obsidian. Local browser interface. No API keys, no internet required.