#564 · Primary category： AI Agents & Automation
open-webSearch
Multi-engine MCP server, CLI, and local daemon for agent web search and content retrieval — skill-guided workflows, no API keys.
Project last updated：08/28/26
GitHub Stars
1.8K
Forks
185
Contributors
12
License
Apache-2.0
Why we included this project
open-webSearch gives AI agents a live search-and-fetch layer without requiring API keys or paid search accounts. It runs three ways: as an MCP server for clients like Claude Desktop, Cursor, or Cherry Studio; as a one-shot CLI for shell scripts; or as a local daemon exposing simple HTTP endpoints. The multi-engine search is the real draw, querying Bing, DuckDuckGo, Baidu, Brave, Exa, and others, and returning structured results with titles, URLs, and descriptions instead of raw HTML. It also fetches readable article text from supported sites and GitHub READMEs, which is handy when an agent needs the actual content, not just links. Proxy support and zero-cost operation make it a practical fit for teams that want a dependable search tool without vendor lock-in.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
openclaw
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
hermes-agent
The agent that grows with you
n8n
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
deepseek-harness
DeepSeek Harness: Everything is a Plugin.
AutoGPT
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.