{"data":{"slug":"itzcrazykns-vane","name":"Vane","tagline":"Vane is an AI-powered answering engine.","github_url":"https://github.com/ItzCrazyKns/Vane","owner":"ItzCrazyKns","repo":"Vane","owner_avatar_url":"https://avatars.githubusercontent.com/u/95534749?v=4","primary_language":"TypeScript","stars":36187,"forks":4009,"topics":["ai-agents","ai-search-engine","answering-engine","artificial-intelligence","llm","machine-learning","open-source-ai-search-engine","perplexica","rag","search-engine","searxng","searxng-copilot","self-hosted-ai","vane"],"archived":false,"github_pushed_at":"2026-04-11T14:33:06+00:00","maintenance_label":"Slowing","stars_delta_30d":503,"url":"https://www.graphcanon.com/tools/itzcrazykns-vane","markdown_url":"https://www.graphcanon.com/tools/itzcrazykns-vane.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/itzcrazykns-vane","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=itzcrazykns-vane","description":"Vane is an AI-powered answering engine.","homepage_url":null,"license":"MIT","open_issues":347,"watchers":201,"ai_summary":"An open-source AI-powered answering engine developed in TypeScript.","readme_excerpt":"## Installation\n\nThere are mainly 2 ways of installing Vane - With Docker, Without Docker. Using Docker is highly recommended.\n\n---\n\n### Getting Started with Docker (Recommended)\n\nVane can be easily run using Docker. Simply run the following command:\n\n```bash\ndocker run -d -p 3000:3000 -v vane-data:/home/vane/data --name vane itzcrazykns1337/vane:latest\n```\n\nThis will pull and start the Vane container with the bundled SearxNG search engine. Once running, open your browser and navigate to http://localhost:3000. You can then configure your settings (API keys, models, etc.) directly in the setup screen.\n\n**Note**: The image includes both Vane and SearxNG, so no additional setup is required. The `-v` flags create persistent volumes for your data and uploaded files.\n\n#### Using Vane with Your Own SearxNG Instance\n\nIf you already have SearxNG running, you can use the slim version of Vane:\n\n```bash\ndocker run -d -p 3000:3000 -e SEARXNG_API_URL=http://your-searxng-url:8080 -v vane-data:/home/vane/data --name vane itzcrazykns1337/vane:slim-latest\n```\n\n**Important**: Make sure your SearxNG instance has:\n\n- JSON format enabled in the settings\n- Wolfram Alpha search engine enabled\n\nReplace `http://your-searxng-url:8080` with your actual SearxNG URL. Then configure your AI provider settings in the setup screen at http://localhost:3000.\n\n#### Advanced Setup (Building from Source)\n\nIf you prefer to build from source or need more control:\n\n1. Ensure Docker is installed and running on your system.\n2. Clone the Vane repository:\n\n   ```bash\n   git clone https://github.com/ItzCrazyKns/Vane.git\n   ```\n\n3. After cloning, navigate to the directory containing the project files.\n\n4. Build and run using Docker:\n\n   ```bash\n   docker build -t vane .\n   docker run -d -p 3000:3000 -v vane-data:/home/vane/data --name vane vane\n   ```\n\n5. Access Vane at http://localhost:3000 and configure your settings in the setup screen.\n\n**Note**: After the containers are built, you can start Vane directly from Docker without having to open a terminal.\n\n---\n\n### Non-Docker Installation\n\n1. Install SearXNG and allow `JSON` format in the SearXNG settings. Make sure Wolfram Alpha search engine is also enabled.\n2. Clone the repository:\n\n   ```bash\n   git clone https://github.com/ItzCrazyKns/Vane.git\n   cd Vane\n   ```\n\n3. Install dependencies:\n\n   ```bash\n   npm i\n   ```\n\n4. Build the application:\n\n   ```bash\n   npm run build\n   ```\n\n5. Start the application:\n\n   ```bash\n   npm run start\n   ```\n\n6. Open your browser and navigate to http://localhost:3000 to complete the setup and configure your settings (API keys, models, SearxNG URL, etc.) in the setup screen.\n\n**Note**: Using Docker is recommended as it simplifies the setup process, especially for managing environment variables and dependencies.\n\nSee the [installation documentation](https://github.com/ItzCrazyKns/Vane/tree/master/docs/installation) for more information like updating, etc.","github_created_at":"2024-04-09T10:51:32+00:00","created_at":"2026-07-07T17:31:49.285324+00:00","updated_at":"2026-08-16T12:02:01.57562+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"slug":"data-retrieval","name":"Data & Retrieval","url":"https://www.graphcanon.com/categories/data-retrieval","markdown_url":"https://www.graphcanon.com/categories/data-retrieval.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/data-retrieval"}],"tags":[{"slug":"ai-agents","name":"ai-agents"},{"slug":"ai-search-engine","name":"ai-search-engine"},{"slug":"answering-engine","name":"answering-engine"},{"slug":"artificial-intelligence","name":"artificial-intelligence"},{"slug":"llm","name":"llm"},{"slug":"machine-learning","name":"machine-learning"},{"slug":"open-source-ai-search-engine","name":"open-source-ai-search-engine"},{"slug":"perplexica","name":"perplexica"}],"trust":{"provenance":{"is_fork":false,"github_id":784181462,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-16T12:02:00.502Z","maintenance":{"label":"Slowing","score":36,"methodology":"github_public_v1","releases_90d":0,"days_since_push":126,"last_release_at":"2026-04-10T13:30:52Z","stars_delta_30d":503,"open_issues_delta_30d":15},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T10:57:54.288Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"mcp":{"source":"repo_scan","observed_at":"2026-08-16T12:02:00.997Z","server_manifest":false},"scan":{"source":"repo_scan","observed_at":"2026-08-16T12:02:00.997Z"},"deploy":{"source":"dockerfile:Dockerfile","self_host":true,"observed_at":"2026-08-16T12:02:00.997Z","managed_saas":false},"has_cli":{"value":true,"source":"package.json:bin|scripts","observed_at":"2026-08-16T12:02:00.997Z"},"languages":{"value":["typescript","javascript"],"source":"github.language+package.json","observed_at":"2026-08-16T12:02:00.997Z"},"has_docker":{"value":true,"source":"dockerfile:Dockerfile","observed_at":"2026-08-16T12:02:00.997Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-08-16T12:02:00.997Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When you need a self-hosted AI search capability built on TypeScript - Vane provides a solid foundation without relying on cloud services, giving you more control over your data.","If you aim to integrate an answering engine that supports Retrieval-Augmented Generation (RAG), Vane can provide a seamless integration experience due to its well-defined architecture in this area."],"when_not_to_use":["For users requiring real-time updates from vast, dynamic datasets frequently changing at the sub-minute level, as Vane might not be optimized for extremely high-frequency updating needs.","If you are looking for an extensive pre-built knowledge base or a service that continuously trains models with new internet data, Vane is more of a framework to build upon rather than a fully curated,","When the project requires Python or other languages, Vane's TypeScript foundation may need extra development effort for integration into non-TypeScript settings."],"source":"enrich:decision_facts","observed_at":"2026-07-11T12:53:49.663Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"Vane is a TypeScript-based, open-source AI-powered answering engine designed for robust data retrieval and processing. It stands out with its unique features in the category."}]}}