search — independent software & tools
-
wigolo
The go-to web for your agent!
-
NAUTILUS
ENERV — a fast metadata facet-system for organizing tech and knowledge roots from the command line.
-
@copilotkit/pathfinder
The knowledge server for AI agents — index docs, code, Notion, Slack, and Discord into searchable, agent-accessible knowledge via MCP. Supports OpenAI, Ollama, and local transformers.js embeddings.
-
exa-mcp-server
A Model Context Protocol server with Exa for web search and web crawling. Provides real-time web searches with configurable tool selection, allowing users to enable or disable specific search capabilities. Supports customizable result counts, live crawlin
-
firecrawl-cli
Command-line interface for Firecrawl. Scrape, crawl, and extract data from any website directly from your terminal.
-
@lancedb/lancedb
LanceDB: A serverless, low-latency vector database for AI applications
-
mcp-searxng
MCP server for SearXNG integration
-
napkin-ai
🧻 Knowledge system for agents. Local-first, file-based, progressively disclosed.
-
obsidian-hybrid-search
[](https://www.npmjs.com/package/obsidian-hybrid-search) [](https://github.com/flowing-a
-
pi-vault-mind
Passive Obsidian vault extension for pi. Watches @agent markers, dispatches forked subagents (Miner, Broadcaster, Heavy-Lifter), stores in LanceDB with vector + FTS + graph. Multi-agent 'Drop & Forget' workflow for the pi agent ecosystem.
-
@swarmvaultai/engine
Core engine for SwarmVault: ingest, compile, query, lint, and provider abstractions.
-
@tavily/core
Official JavaScript library for Tavily.
-
@tobilu/qmd
Query Markup Documents - On-device hybrid search for markdown files with BM25, vector search, and LLM reranking
-
linkynotes.com
📝 Create your own linked notes system. Store, organize, and filter notes with tags using Markdown and HTML. Visit linkynotes.com for more.
-
retro-md-notes
This project hosts a collection of .md (Markdown) notes on a static page (index.html) with client-side search and pagination, all styled in a retro green-on-black theme. The site uses a Python script to build a db.json file, which serves as the data source for the front-end.
-
@ericthered926/duckduckgo-mcp-server
A Model Context Protocol (MCP) server for DuckDuckGo web and news search
-
inquirer-checkbox-plus-prompt
Checkbox with autocomplete and other additions for Inquirer
-
libnpmsearch
Programmatic API for searching in npm and compatible registries.